Results for CD.net 2014

Results, all categories combined.

Warning!!!

Methods with the "(supervised method)" tag involve a supervised machine learning algorithm potentially trained on the groundtruth data used to produce the metrics reported in this page. Thus, these methods should not be compared directly with the other unsupervised methods without further investigation and careful analysis. Please refer to the original papers for more details.

Click on method name for more details.

Method Average ranking across categories Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 6.55 6.43 0.9544 0.9990 0.0010 0.0456 0.2272 0.9501 0.9472
RT-SBS-v2 [53] 18.91 15.00 0.8361 0.9941 0.0059 0.1639 0.9439 0.8045 0.7934
Multiscale Spatio-Temporal BG Model [12] 52.18 50.71 0.6621 0.9542 0.0458 0.3379 5.5456 0.5141 0.5536
SuBSENSE [13] 25.64 26.71 0.8124 0.9904 0.0096 0.1876 1.6780 0.7408 0.7509
WisenetMD [42] 22.64 25.29 0.8179 0.9904 0.0096 0.1821 1.6136 0.7535 0.7668
SOBS_CF [14] 44.73 44.71 0.7805 0.9442 0.0558 0.2195 6.0709 0.5883 0.5831
RMoG (Region-based Mixture of Gaussians) [15] 44.09 44.00 0.5940 0.9865 0.0135 0.4060 2.9638 0.5735 0.6965
FgSegNet_S (FPM) (Supervised Method) [44] 3.55 3.57 0.9896 0.9997 0.0003 0.0104 0.0461 0.9804 0.9751
FgSegNet_v2 (Supervised Method) [45] 3.36 2.71 0.9891 0.9998 0.0002 0.0109 0.0402 0.9847 0.9823
AAPSA [16] 41.64 40.00 0.6498 0.9905 0.0095 0.3502 2.0734 0.6179 0.6916
Multimode Background Subtraction Version 0 (MBS V0) [17] 34.82 31.57 0.7192 0.9929 0.0071 0.2808 1.3922 0.7139 0.7435
Multimode Background Subtraction [18] 31.82 29.71 0.7389 0.9927 0.0073 0.2611 1.2614 0.7288 0.7382
M4CD Version 2.0 [30] 27.00 32.00 0.7885 0.9841 0.0159 0.2115 2.3011 0.7038 0.7423
GraphCutDiff [19] 42.82 47.43 0.6297 0.9780 0.0220 0.3703 3.6774 0.5684 0.6666
Sample based background subtractor (SBBS) [31] 38.00 39.14 0.7073 0.9827 0.0173 0.2927 2.4315 0.6711 0.7221
Fast BSUV-Net 2.0 [56] 15.55 13.00 0.8181 0.9956 0.0044 0.1819 0.9054 0.8039 0.8425
EFIC [20] 33.55 35.00 0.7855 0.9779 0.0221 0.2145 2.7941 0.7088 0.7224
BSUV-net + SemanticBGS (supervised method) [51] 20.55 15.86 0.8179 0.9944 0.0056 0.1821 1.1326 0.7986 0.8319
RT-SBS-v1 [52] 29.09 27.57 0.7406 0.9935 0.0065 0.2594 1.5098 0.7153 0.7743
IUTIS-1 [21] 41.36 45.43 0.7654 0.9499 0.0501 0.2346 5.7503 0.5789 0.5928
IUTIS-2 [22] 38.00 42.14 0.6621 0.9838 0.0162 0.3379 3.1547 0.6026 0.7120
IUTIS-3 [23] 21.82 22.86 0.7779 0.9940 0.0060 0.2221 1.2985 0.7551 0.7875
CVABS [47] 26.82 23.00 0.7818 0.9934 0.0066 0.2182 1.3090 0.7701 0.7782
SWCD [43] 27.73 24.57 0.7839 0.9930 0.0070 0.2161 1.3414 0.7583 0.7527
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 4.91 4.57 0.9836 0.9998 0.0002 0.0164 0.0559 0.9770 0.9758
CL-VID [46] 44.45 41.43 0.8316 0.9289 0.0711 0.1684 7.4772 0.5813 0.5529
FgSegNet_v2_CO (Supervised learning) [54] 1.18 1.57 0.9890 0.9998 0.0002 0.0110 0.0395 0.9850 0.9828
SharedModel [28] 26.64 25.14 0.8098 0.9912 0.0088 0.1902 1.4996 0.7474 0.7503
C-EFIC [24] 29.64 31.14 0.7976 0.9782 0.0218 0.2024 2.6316 0.7307 0.7543
WeSamBE [33] 25.36 25.00 0.7955 0.9924 0.0076 0.2045 1.5105 0.7446 0.7679
DeepBS (supervised method) [34] 21.36 28.57 0.7545 0.9905 0.0095 0.2455 1.9920 0.7458 0.8332
BMOG [35] 39.00 40.29 0.7265 0.9813 0.0187 0.2735 2.9757 0.6543 0.6981
FgSegNet_v2_GOP (supervised learning) [49] 1.18 1.57 0.9890 0.9998 0.0002 0.0110 0.0395 0.9850 0.9828
PAWCS [25] 23.36 21.86 0.7718 0.9949 0.0051 0.2282 1.1992 0.7403 0.7857
MU-Net1 (Supervised Method) [55] 9.27 8.43 0.9277 0.9990 0.0010 0.0723 0.2097 0.9147 0.9414
Cascade CNN(supervised method) [29] 10.36 9.43 0.9506 0.9968 0.0032 0.0494 0.4052 0.9209 0.8997
Euclidean distance [1] 53.64 51.71 0.6803 0.9449 0.0551 0.3197 6.5423 0.5161 0.5480
KDE - ElGammal [2] 45.82 47.14 0.7375 0.9519 0.0481 0.2625 5.6262 0.5688 0.5811
SemanticBGS [38] 18.00 16.00 0.7890 0.9961 0.0039 0.2110 1.0722 0.7892 0.8305
GMM | Stauffer & Grimson [3] 48.82 46.29 0.6846 0.9750 0.0250 0.3154 3.7667 0.5707 0.6025
GMM | Zivkovic [4] 50.00 48.71 0.6604 0.9725 0.0275 0.3396 3.9953 0.5566 0.5973
Mahalanobis distance [5] 41.91 42.14 0.1644 0.9931 0.0069 0.8356 3.4750 0.2267 0.7403
CwisarDRP [26] 28.09 28.86 0.7062 0.9947 0.0053 0.2938 1.7197 0.7095 0.7880
IUTIS-5 [27] 17.64 18.71 0.7849 0.9948 0.0052 0.2151 1.1986 0.7717 0.8087
BSGAN (supervised method) [40] 8.09 8.57 0.9476 0.9983 0.0017 0.0524 0.3281 0.9339 0.9232
MU-Net2 (Supervised Method) [58] 7.45 7.57 0.9454 0.9991 0.0009 0.0546 0.2347 0.9369 0.9407
BSUV-Net (supervised method) [50] 20.55 15.71 0.8203 0.9946 0.0054 0.1797 1.1402 0.7868 0.8113
BSUV-Net 2.0 [57] 11.91 12.29 0.8136 0.9979 0.0021 0.1864 0.7614 0.8387 0.9011
CwisarDH [6] 33.27 31.00 0.6608 0.9948 0.0052 0.3392 1.5273 0.6812 0.7725
Spectral-360 [7] 37.64 37.14 0.7345 0.9861 0.0139 0.2655 2.2722 0.6732 0.7054
DCB [32] 49.36 45.57 0.3892 0.9897 0.0103 0.6108 2.8789 0.3975 0.6309
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 26.36 28.14 0.7657 0.9922 0.0078 0.2343 1.3763 0.7283 0.7696
SC_SOBS [9] 44.18 43.43 0.7621 0.9547 0.0453 0.2379 5.1498 0.5961 0.6091
AMBER [10] 40.00 41.14 0.7035 0.9794 0.0206 0.2965 2.9009 0.6577 0.7163
CP3-online [11] 49.27 45.57 0.7225 0.9705 0.0295 0.2775 3.4318 0.5805 0.5559
Simplified Self-Organized Background Subtraction [37] 52.73 51.86 0.4895 0.9710 0.0290 0.5105 4.8631 0.3977 0.5116

Results, for the bad weather category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 7.29 0.9566 0.9996 0.0004 0.0434 0.1004 0.9644 0.9725
RT-SBS-v2 [53] 30.57 0.8441 0.9970 0.0030 0.1559 0.5543 0.8279 0.8345
Multiscale Spatio-Temporal BG Model [12] 54.14 0.5964 0.9892 0.0108 0.4036 1.6752 0.6371 0.7680
SuBSENSE [13] 22.43 0.8213 0.9989 0.0011 0.1787 0.4527 0.8619 0.9091
WisenetMD [42] 22.86 0.8213 0.9989 0.0011 0.1787 0.4534 0.8616 0.9084
SOBS_CF [14] 52.86 0.5791 0.9941 0.0059 0.4209 1.1926 0.6370 0.7762
RMoG (Region-based Mixture of Gaussians) [15] 39.57 0.5572 0.9991 0.0009 0.4428 0.8739 0.6826 0.8955
FgSegNet_S (FPM) (Supervised Method) [44] 3.57 0.9888 0.9999 0.0001 0.0112 0.0321 0.9897 0.9907
FgSegNet_v2 (Supervised Method) [45] 3.14 0.9869 0.9999 0.0001 0.0131 0.0296 0.9904 0.9939
AAPSA [16] 31.14 0.6738 0.9993 0.0007 0.3262 0.6650 0.7742 0.9255
Multimode Background Subtraction Version 0 (MBS V0) [17] 42.71 0.8211 0.9936 0.0064 0.1789 0.9449 0.7730 0.7571
Multimode Background Subtraction [18] 37.00 0.8341 0.9953 0.0047 0.1659 0.7634 0.7980 0.7828
M4CD Version 2.0 [30] 27.86 0.7391 0.9990 0.0010 0.2609 0.5037 0.8136 0.9067
GraphCutDiff [19] 21.43 0.8701 0.9979 0.0021 0.1299 0.4085 0.8787 0.8906
Sample based background subtractor (SBBS) [31] 45.86 0.7057 0.9958 0.0042 0.2943 0.8953 0.7403 0.8064
Fast BSUV-Net 2.0 [56] 11.71 0.8237 0.9997 0.0003 0.1763 0.2732 0.8909 0.9754
EFIC [20] 38.14 0.7647 0.9962 0.0038 0.2353 0.7164 0.7786 0.8373
BSUV-net + SemanticBGS (supervised method) [51] 20.00 0.8219 0.9989 0.0011 0.1781 0.4112 0.8730 0.9381
RT-SBS-v1 [52] 27.71 0.6892 0.9994 0.0006 0.3108 0.5829 0.7888 0.9513
IUTIS-1 [21] 52.57 0.6557 0.9906 0.0094 0.3443 1.4403 0.6705 0.7486
IUTIS-2 [22] 31.57 0.6226 0.9994 0.0006 0.3774 0.6450 0.7401 0.9415
IUTIS-3 [23] 30.14 0.7479 0.9987 0.0013 0.2521 0.5534 0.8032 0.8960
CVABS [47] 28.00 0.8591 0.9972 0.0028 0.1409 0.5376 0.8570 0.8573
BMN-BSN (supervised method) [48] 32.43 0.7802 0.9977 0.0023 0.2198 0.5355 0.8124 0.8531
SWCD [43] 34.00 0.8250 0.9960 0.0040 0.1750 0.6468 0.8233 0.8269
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 5.43 0.9793 0.9998 0.0002 0.0207 0.0544 0.9845 0.9898
CL-VID [46] 46.14 0.7189 0.9950 0.0050 0.2811 0.9044 0.7390 0.8007
FgSegNet_v2_CO (Supervised learning) [54] 2.00 0.9869 0.9999 0.0001 0.0131 0.0294 0.9905 0.9940
SharedModel [28] 25.86 0.8430 0.9978 0.0022 0.1570 0.5138 0.8480 0.8568
C-EFIC [24] 36.29 0.7352 0.9977 0.0023 0.2648 0.6600 0.7867 0.8719
WeSamBE [33] 22.86 0.8168 0.9989 0.0011 0.1832 0.4891 0.8608 0.9134
DeepBS (supervised method) [34] 17.71 0.7517 0.9996 0.0004 0.2483 0.3784 0.8301 0.9677
BMOG [35] 36.71 0.7635 0.9976 0.0024 0.2365 0.6243 0.7836 0.8152
FgSegNet_v2_GOP (supervised learning) [49] 2.00 0.9869 0.9999 0.0001 0.0131 0.0294 0.9905 0.9940
PAWCS [25] 24.43 0.7181 0.9994 0.0006 0.2819 0.5319 0.8152 0.9474
MU-Net1 (Supervised Method) [55] 13.00 0.9075 0.9991 0.0009 0.0925 0.2103 0.9319 0.9599
Cascade CNN(supervised method) [29] 11.57 0.9312 0.9993 0.0007 0.0688 0.1911 0.9431 0.9555
Euclidean distance [1] 42.86 0.5567 0.9987 0.0013 0.4433 0.7824 0.6701 0.8846
KDE - ElGammal [2] 41.71 0.6941 0.9975 0.0025 0.3059 0.7192 0.7571 0.8486
SemanticBGS [38] 21.57 0.7420 0.9994 0.0006 0.2580 0.5112 0.8260 0.9518
GMM | Stauffer & Grimson [3] 44.71 0.7181 0.9971 0.0029 0.2819 0.7905 0.7380 0.7704
GMM | Zivkovic [4] 42.57 0.6863 0.9978 0.0022 0.3137 0.7707 0.7406 0.8138
Mahalanobis distance [5] 32.57 0.1749 1.0000 0.0000 0.8251 1.2575 0.2212 0.9975
CwisarDRP [26] 31.71 0.7531 0.9984 0.0016 0.2469 0.5760 0.8015 0.8718
IUTIS-5 [27] 22.86 0.7493 0.9993 0.0007 0.2507 0.5002 0.8248 0.9311
BSGAN (supervised method) [40] 10.00 0.9335 0.9993 0.0007 0.0665 0.1827 0.9465 0.9599
MU-Net2 (Supervised Method) [58] 12.57 0.9164 0.9992 0.0008 0.0836 0.1939 0.9343 0.9544
BSUV-Net (supervised method) [50] 20.57 0.8267 0.9988 0.0012 0.1733 0.4142 0.8713 0.9278
BSUV-Net 2.0 [57] 13.86 0.8166 0.9997 0.0003 0.1834 0.3639 0.8844 0.9761
CwisarDH [6] 40.43 0.6288 0.9986 0.0014 0.3712 0.7475 0.6837 0.8762
Spectral-360 [7] 41.00 0.7032 0.9977 0.0023 0.2968 0.6804 0.7569 0.8211
DCB [32] 47.86 0.2588 0.9984 0.0016 0.7412 1.5795 0.3835 0.8261
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 25.86 0.7457 0.9991 0.0009 0.2543 0.5109 0.8228 0.9231
SC_SOBS [9] 47.14 0.5676 0.9976 0.0024 0.4324 0.8606 0.6620 0.8434
AMBER [10] 33.29 0.6661 0.9990 0.0010 0.3339 0.6164 0.7673 0.9169
CP3-online [11] 41.29 0.8365 0.9934 0.0066 0.1635 0.9364 0.7485 0.7001
Simplified Self-Organized Background Subtraction [37] 44.86 0.5815 0.9978 0.0022 0.4185 0.9448 0.6846 0.8502

Results, for the low framerate category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 7.00 0.8628 0.9998 0.0002 0.1372 0.0679 0.8508 0.8427
RT-SBS-v2 [53] 22.29 0.8207 0.9959 0.0041 0.1793 0.5913 0.7341 0.6921
Multiscale Spatio-Temporal BG Model [12] 52.71 0.6057 0.9608 0.0392 0.3943 4.7581 0.3365 0.2917
SuBSENSE [13] 30.71 0.8537 0.9938 0.0062 0.1463 0.9968 0.6445 0.6035
WisenetMD [42] 31.00 0.8461 0.9942 0.0058 0.1539 0.9943 0.6404 0.6092
SOBS_CF [14] 45.14 0.8046 0.9173 0.0827 0.1954 8.7531 0.5148 0.4613
RMoG (Region-based Mixture of Gaussians) [15] 48.71 0.5805 0.9922 0.0078 0.4195 1.6809 0.5312 0.5916
FgSegNet_S (FPM) (Supervised Method) [44] 4.43 0.9791 0.9998 0.0002 0.0209 0.0291 0.8972 0.8585
FgSegNet_v2 (Supervised Method) [45] 2.86 0.9868 0.9999 0.0001 0.0132 0.0247 0.9336 0.9005
AAPSA [16] 46.86 0.5799 0.9943 0.0057 0.4201 1.6158 0.4942 0.5675
Multimode Background Subtraction Version 0 (MBS V0) [17] 37.14 0.6656 0.9942 0.0058 0.3344 0.8610 0.6279 0.6604
Multimode Background Subtraction [18] 38.57 0.6773 0.9942 0.0058 0.3227 0.8651 0.6350 0.6000
M4CD Version 2.0 [30] 31.57 0.7911 0.9949 0.0051 0.2089 0.8394 0.6275 0.6315
GraphCutDiff [19] 39.86 0.4713 0.9966 0.0034 0.5287 1.2794 0.5127 0.6814
Sample based background subtractor (SBBS) [31] 44.29 0.6997 0.9927 0.0073 0.3003 1.3551 0.5534 0.5461
Fast BSUV-Net 2.0 [56] 16.71 0.7765 0.9991 0.0009 0.2235 0.2488 0.7824 0.7887
EFIC [20] 21.43 0.7694 0.9982 0.0018 0.2306 0.5666 0.6632 0.7232
BSUV-net + SemanticBGS (supervised method) [51] 32.29 0.7978 0.9926 0.0074 0.2022 1.1025 0.6788 0.7069
RT-SBS-v1 [52] 23.29 0.7206 0.9977 0.0023 0.2794 0.7316 0.6943 0.7326
IUTIS-1 [21] 35.71 0.7316 0.9955 0.0045 0.2684 1.0088 0.5694 0.6260
IUTIS-2 [22] 34.29 0.7513 0.9951 0.0049 0.2487 0.9678 0.6034 0.6690
IUTIS-3 [23] 21.43 0.8213 0.9963 0.0037 0.1787 0.7267 0.7327 0.6995
CVABS [47] 16.43 0.8187 0.9975 0.0025 0.1813 0.5343 0.7856 0.7671
BMN-BSN (supervised method) [48] 28.57 0.6538 0.9982 0.0018 0.3462 0.9209 0.6426 0.7045
SWCD [43] 26.29 0.7981 0.9951 0.0049 0.2019 0.9016 0.7374 0.7000
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 5.57 0.9740 0.9998 0.0002 0.0260 0.0359 0.8786 0.8411
CL-VID [46] 39.57 0.8409 0.9814 0.0186 0.1591 2.1424 0.5849 0.5484
FgSegNet_v2_CO (Supervised learning) [54] 1.71 0.9868 0.9999 0.0001 0.0132 0.0245 0.9342 0.9012
SharedModel [28] 22.71 0.8430 0.9958 0.0042 0.1570 0.7450 0.7286 0.6839
C-EFIC [24] 18.43 0.8077 0.9976 0.0024 0.1923 0.5532 0.6806 0.7135
WeSamBE [33] 26.14 0.8842 0.9944 0.0056 0.1158 0.8216 0.6602 0.6134
DeepBS (supervised method) [34] 34.43 0.5924 0.9975 0.0025 0.4076 1.3564 0.6002 0.7018
BMOG [35] 32.43 0.6385 0.9971 0.0029 0.3615 0.8967 0.6102 0.6956
FgSegNet_v2_GOP (supervised learning) [49] 1.71 0.9868 0.9999 0.0001 0.0132 0.0245 0.9342 0.9012
PAWCS [25] 28.29 0.7732 0.9963 0.0037 0.2268 0.7258 0.6588 0.6405
MU-Net1 (Supervised Method) [55] 17.86 0.7187 0.9992 0.0008 0.2813 0.1659 0.7237 0.9767
Cascade CNN(supervised method) [29] 9.86 0.8489 0.9993 0.0007 0.1511 0.1317 0.8370 0.8285
Euclidean distance [1] 49.14 0.5914 0.9868 0.0132 0.4086 2.2419 0.5015 0.6152
KDE - ElGammal [2] 41.71 0.7000 0.9931 0.0069 0.3000 1.3124 0.5478 0.6245
SemanticBGS [38] 15.57 0.8357 0.9976 0.0024 0.1643 0.6031 0.7888 0.7675
GMM | Stauffer & Grimson [3] 38.71 0.5823 0.9961 0.0039 0.4177 1.2951 0.5373 0.6894
GMM | Zivkovic [4] 39.86 0.5300 0.9970 0.0030 0.4700 1.3620 0.5065 0.6686
Mahalanobis distance [5] 34.43 0.0538 0.9999 0.0001 0.9462 2.5114 0.0797 0.7612
CwisarDRP [26] 23.43 0.7718 0.9972 0.0028 0.2282 0.6774 0.6858 0.7045
IUTIS-5 [27] 18.00 0.8398 0.9968 0.0032 0.1602 0.6766 0.7743 0.7424
BSGAN (supervised method) [40] 8.43 0.8601 0.9995 0.0005 0.1399 0.1097 0.8472 0.8382
MU-Net2 (Supervised Method) [58] 9.00 0.9309 0.9987 0.0013 0.0691 0.2152 0.8706 0.8344
BSUV-Net (supervised method) [50] 31.00 0.8012 0.9928 0.0072 0.1988 1.0727 0.6797 0.7058
BSUV-Net 2.0 [57] 14.57 0.7867 0.9997 0.0003 0.2133 0.2160 0.7902 0.8047
CwisarDH [6] 36.43 0.6738 0.9951 0.0049 0.3262 1.0435 0.6406 0.6399
Spectral-360 [7] 36.71 0.7515 0.9941 0.0059 0.2485 0.8964 0.6437 0.5946
DCB [32] 49.00 0.1570 0.9948 0.0052 0.8430 2.9401 0.1412 0.5957
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 32.57 0.7517 0.9963 0.0037 0.2483 1.1823 0.6259 0.6550
SC_SOBS [9] 45.43 0.7874 0.9577 0.0423 0.2126 4.7727 0.5463 0.5272
AMBER [10] 51.86 0.5226 0.9911 0.0089 0.4774 2.2069 0.4689 0.5937
CP3-online [11] 49.00 0.6810 0.9854 0.0146 0.3190 2.1756 0.4742 0.5263
Simplified Self-Organized Background Subtraction [37] 48.86 0.5314 0.9918 0.0082 0.4686 2.0183 0.4644 0.6435

Results, for the night videos category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 7.14 0.9155 0.9966 0.0034 0.0845 0.5979 0.9001 0.8863
RT-SBS-v2 [53] 30.00 0.5719 0.9831 0.0169 0.4281 3.3343 0.5629 0.5786
Multiscale Spatio-Temporal BG Model [12] 47.71 0.5773 0.9574 0.0426 0.4227 5.8859 0.4164 0.4270
SuBSENSE [13] 29.86 0.6570 0.9766 0.0234 0.3430 3.7718 0.5599 0.5359
WisenetMD [42] 28.14 0.6467 0.9789 0.0211 0.3533 3.5363 0.5701 0.5488
SOBS_CF [14] 42.14 0.6808 0.9463 0.0537 0.3192 6.5308 0.4482 0.4056
RMoG (Region-based Mixture of Gaussians) [15] 47.29 0.5524 0.9668 0.0332 0.4476 5.1606 0.4265 0.4345
FgSegNet_S (FPM) (Supervised Method) [44] 3.57 0.9708 0.9992 0.0008 0.0292 0.1661 0.9713 0.9719
FgSegNet_v2 (Supervised Method) [45] 2.71 0.9651 0.9994 0.0006 0.0349 0.1471 0.9739 0.9831
AAPSA [16] 40.00 0.3908 0.9871 0.0129 0.6092 3.7971 0.4161 0.5056
Multimode Background Subtraction Version 0 (MBS V0) [17] 36.86 0.5535 0.9773 0.0227 0.4465 3.6592 0.5158 0.4899
Multimode Background Subtraction [18] 36.86 0.5535 0.9773 0.0227 0.4465 3.6592 0.5158 0.4899
M4CD Version 2.0 [30] 36.71 0.6525 0.9696 0.0304 0.3475 4.6115 0.4946 0.4891
GraphCutDiff [19] 40.29 0.6435 0.9687 0.0313 0.3565 4.7439 0.4688 0.4292
Sample based background subtractor (SBBS) [31] 37.71 0.5186 0.9818 0.0182 0.4814 3.6968 0.5055 0.5343
Fast BSUV-Net 2.0 [56] 18.00 0.6302 0.9943 0.0057 0.3698 2.5024 0.6551 0.7942
EFIC [20] 17.00 0.6704 0.9893 0.0107 0.3296 2.5739 0.6548 0.6869
BSUV-net + SemanticBGS (supervised method) [51] 18.43 0.5984 0.9960 0.0040 0.4016 2.2167 0.6815 0.8205
RT-SBS-v1 [52] 34.71 0.4229 0.9876 0.0124 0.5771 3.5667 0.4569 0.5890
IUTIS-1 [21] 39.86 0.6056 0.9717 0.0283 0.3944 4.5767 0.4770 0.4709
IUTIS-2 [22] 34.00 0.5594 0.9825 0.0175 0.4406 3.6933 0.5154 0.5348
IUTIS-3 [23] 36.00 0.5664 0.9819 0.0181 0.4336 3.7085 0.4948 0.5130
CVABS [47] 21.14 0.6552 0.9858 0.0142 0.3448 2.8346 0.6418 0.6444
BMN-BSN (supervised method) [48] 19.57 0.6705 0.9869 0.0131 0.3295 2.5853 0.6125 0.6113
SWCD [43] 28.00 0.6188 0.9822 0.0178 0.3812 3.2662 0.5807 0.5598
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 4.57 0.9539 0.9993 0.0007 0.0461 0.2108 0.9655 0.9775
CL-VID [46] 38.71 0.6938 0.9587 0.0413 0.3062 5.5070 0.4715 0.4420
FgSegNet_v2_CO (Supervised learning) [54] 1.57 0.9650 0.9994 0.0006 0.0350 0.1468 0.9740 0.9834
SharedModel [28] 32.43 0.5995 0.9799 0.0201 0.4005 3.5758 0.5419 0.5250
C-EFIC [24] 18.00 0.7223 0.9866 0.0134 0.2777 2.5899 0.6677 0.6636
WeSamBE [33] 24.43 0.6370 0.9840 0.0160 0.3630 3.1305 0.5929 0.5827
DeepBS (supervised method) [34] 24.00 0.5315 0.9959 0.0041 0.4685 2.5754 0.5835 0.8366
BMOG [35] 37.00 0.6495 0.9694 0.0306 0.3505 4.4376 0.4982 0.4611
COLBMOG [36] 14.00 0.8047 0.9889 0.0111 0.1953 1.8269 0.7564 0.7287
FgSegNet_v2_GOP (supervised learning) [49] 1.57 0.9650 0.9994 0.0006 0.0350 0.1468 0.9740 0.9834
PAWCS [25] 34.71 0.3608 0.9932 0.0068 0.6392 3.3386 0.4152 0.6539
MU-Net1 (Supervised Method) [55] 8.00 0.8021 0.9979 0.0021 0.1979 0.8568 0.8575 0.9367
Cascade CNN(supervised method) [29] 8.14 0.9139 0.9964 0.0036 0.0861 0.6116 0.8965 0.8805
Euclidean distance [1] 51.43 0.4913 0.9653 0.0347 0.5087 5.5378 0.3859 0.4168
KDE - ElGammal [2] 46.43 0.5914 0.9640 0.0360 0.4086 5.2735 0.4365 0.4036
SemanticBGS [38] 31.29 0.4661 0.9892 0.0108 0.5339 3.2519 0.5014 0.6294
GMM | Stauffer & Grimson [3] 48.29 0.5261 0.9701 0.0299 0.4739 4.9179 0.4097 0.4128
GMM | Zivkovic [4] 48.43 0.4797 0.9739 0.0261 0.5203 4.7227 0.3960 0.4231
Mahalanobis distance [5] 34.43 0.0825 0.9978 0.0022 0.9175 3.7362 0.1374 0.6914
CwisarDRP [26] 38.43 0.5067 0.9819 0.0181 0.4933 3.8484 0.4970 0.5447
IUTIS-5 [27] 31.29 0.5852 0.9828 0.0172 0.4148 3.5684 0.5290 0.5438
BSGAN (supervised method) [40] 8.14 0.9139 0.9964 0.0036 0.0861 0.6116 0.8965 0.8805
MU-Net2 (Supervised Method) [58] 9.29 0.7734 0.9977 0.0023 0.2266 1.3310 0.8362 0.9240
BSUV-Net (supervised method) [50] 16.57 0.6299 0.9959 0.0041 0.3701 2.1761 0.6987 0.8221
BSUV-Net 2.0 [57] 23.57 0.5321 0.9960 0.0040 0.4679 2.5849 0.5857 0.8189
CwisarDH [6] 42.71 0.4076 0.9852 0.0148 0.5924 3.9853 0.3735 0.5021
Spectral-360 [7] 38.14 0.6237 0.9739 0.0261 0.3763 4.4642 0.4832 0.4610
DCB [32] 41.57 0.1714 0.9939 0.0061 0.8286 3.8662 0.2305 0.4481
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 36.57 0.6107 0.9759 0.0241 0.3893 4.0052 0.5130 0.4904
SC_SOBS [9] 42.71 0.6496 0.9515 0.0485 0.3504 6.1567 0.4503 0.4241
AMBER [10] 50.86 0.5890 0.9375 0.0625 0.4110 7.8383 0.3802 0.3818
CP3-online [11] 48.29 0.6221 0.9381 0.0619 0.3779 7.6963 0.3919 0.3410
Simplified Self-Organized Background Subtraction [37] 38.71 0.4468 0.9862 0.0138 0.5532 3.7281 0.4462 0.5149

Results, for the ptz category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 6.00 0.9789 0.9994 0.0006 0.0211 0.0763 0.9486 0.9212
RT-SBS-v2 [53] 21.71 0.7570 0.9934 0.0066 0.2430 0.8274 0.5808 0.4862
Multiscale Spatio-Temporal BG Model [12] 44.86 0.7953 0.7282 0.2718 0.2047 27.1630 0.0364 0.0188
SuBSENSE [13] 29.86 0.8306 0.9629 0.0371 0.1694 3.8159 0.3476 0.2840
WisenetMD [42] 29.29 0.8582 0.9576 0.0424 0.1418 4.3288 0.3367 0.2745
SOBS_CF [14] 42.43 0.8558 0.6796 0.3204 0.1442 31.9430 0.0368 0.0190
RMoG (Region-based Mixture of Gaussians) [15] 39.43 0.6409 0.9278 0.0722 0.3591 7.4757 0.2470 0.2212
FgSegNet_S (FPM) (Supervised Method) [44] 1.86 0.9910 0.9999 0.0001 0.0090 0.0172 0.9879 0.9849
FgSegNet_v2 (Supervised Method) [45] 3.57 0.9919 0.9999 0.0001 0.0081 0.0190 0.9862 0.9808
AAPSA [16] 37.43 0.5128 0.9638 0.0362 0.4872 3.9676 0.3302 0.3772
Multimode Background Subtraction Version 0 (MBS V0) [17] 25.14 0.5770 0.9945 0.0055 0.4230 0.7821 0.5118 0.4988
Multimode Background Subtraction [18] 22.57 0.5973 0.9963 0.0037 0.4027 0.5850 0.5520 0.5400
M4CD Version 2.0 [30] 35.43 0.8538 0.8984 0.1016 0.1462 10.2247 0.2322 0.1791
GraphCutDiff [19] 32.57 0.5798 0.9868 0.0132 0.4202 1.6312 0.3723 0.3325
Sample based background subtractor (SBBS) [31] 39.71 0.6567 0.9243 0.0757 0.3433 7.8369 0.2400 0.2239
Fast BSUV-Net 2.0 [56] 23.00 0.8056 0.9878 0.0122 0.1944 1.3516 0.5014 0.4236
EFIC [20] 25.71 0.9177 0.9217 0.0783 0.0823 7.8707 0.5842 0.5282
BSUV-net + SemanticBGS (supervised method) [51] 18.71 0.8039 0.9928 0.0072 0.1961 0.8751 0.6562 0.6205
RT-SBS-v1 [52] 30.43 0.7517 0.9825 0.0175 0.2483 1.9393 0.3763 0.2944
IUTIS-1 [21] 40.14 0.8803 0.6844 0.3156 0.1197 31.4561 0.0453 0.0237
IUTIS-2 [22] 37.29 0.8488 0.8881 0.1119 0.1512 11.2503 0.2198 0.1704
IUTIS-3 [23] 29.43 0.6644 0.9868 0.0132 0.3356 1.5649 0.3921 0.3474
CVABS [47] 27.00 0.5510 0.9943 0.0057 0.4490 0.8210 0.4699 0.4629
SWCD [43] 27.86 0.5653 0.9939 0.0061 0.4347 0.8292 0.4545 0.3976
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 3.71 0.9837 0.9999 0.0001 0.0163 0.0240 0.9843 0.9848
CL-VID [46] 43.14 0.9200 0.5548 0.4452 0.0800 44.2873 0.0300 0.0153
FgSegNet_v2_CO (Supervised learning) [54] 2.43 0.9919 0.9999 0.0001 0.0081 0.0188 0.9864 0.9812
SharedModel [28] 28.29 0.7969 0.9791 0.0209 0.2031 2.2166 0.3860 0.3121
C-EFIC [24] 26.71 0.8686 0.8947 0.1053 0.1314 10.5973 0.6207 0.6144
WeSamBE [33] 27.71 0.8145 0.9754 0.0246 0.1855 2.5692 0.3844 0.3121
DeepBS (supervised method) [34] 37.00 0.7459 0.9248 0.0752 0.2541 7.7228 0.3133 0.2855
BMOG [35] 39.43 0.7667 0.8891 0.1109 0.2333 11.2335 0.2350 0.2094
FgSegNet_v2_GOP (supervised learning) [49] 2.43 0.9919 0.9999 0.0001 0.0081 0.0188 0.9864 0.9812
PAWCS [25] 25.14 0.6976 0.9912 0.0088 0.3024 1.1162 0.4615 0.4725
MU-Net1 (Supervised Method) [55] 9.71 0.9529 0.9978 0.0022 0.0471 0.2506 0.7946 0.7598
Cascade CNN(supervised method) [29] 8.00 0.9663 0.9990 0.0010 0.0337 0.1221 0.9168 0.8730
Euclidean distance [1] 46.57 0.7808 0.6614 0.3386 0.2192 33.8518 0.0395 0.0206
KDE - ElGammal [2] 44.86 0.8121 0.6761 0.3239 0.1879 32.3132 0.0365 0.0188
SemanticBGS [38] 19.57 0.7570 0.9950 0.0050 0.2430 0.6820 0.5673 0.5016
GMM | Stauffer & Grimson [3] 45.14 0.6475 0.8570 0.1430 0.3525 14.5321 0.1522 0.1185
GMM | Zivkovic [4] 47.00 0.6111 0.8330 0.1670 0.3889 16.9493 0.1046 0.0683
Mahalanobis distance [5] 45.29 0.0398 0.9574 0.0426 0.9602 4.9260 0.0374 0.1311
CwisarDRP [26] 27.00 0.7539 0.9883 0.0117 0.2461 1.2984 0.4292 0.3200
IUTIS-5 [27] 27.14 0.6749 0.9902 0.0098 0.3251 1.2166 0.4282 0.3833
BSGAN (supervised method) [40] 7.00 0.9678 0.9991 0.0009 0.0322 0.1188 0.9194 0.8764
MU-Net2 (Supervised Method) [58] 9.29 0.9372 0.9986 0.0014 0.0628 0.1745 0.8185 0.7792
BSUV-Net (supervised method) [50] 19.57 0.8045 0.9909 0.0091 0.1955 1.0716 0.6282 0.5897
BSUV-Net 2.0 [57] 16.57 0.7932 0.9957 0.0043 0.2068 0.5892 0.7037 0.6829
CwisarDH [6] 28.57 0.3363 0.9977 0.0023 0.6637 0.6847 0.3218 0.4824
Spectral-360 [7] 39.29 0.5047 0.9416 0.0584 0.4953 6.0771 0.3653 0.3265
DCB [32] 41.00 0.2259 0.9867 0.0133 0.7741 1.9676 0.0804 0.1150
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 33.57 0.6730 0.9770 0.0230 0.3270 2.5519 0.3241 0.2861
SC_SOBS [9] 41.71 0.8403 0.7126 0.2874 0.1597 28.6809 0.0409 0.0212
AMBER [10] 47.00 0.5161 0.8880 0.1120 0.4839 11.5906 0.1348 0.1895
CP3-online [11] 37.57 0.6061 0.9711 0.0289 0.3939 3.1516 0.2660 0.1992
Simplified Self-Organized Background Subtraction [37] 46.14 0.4688 0.9241 0.0759 0.5312 7.9206 0.1384 0.1022

Results, for the turbulence category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 8.43 0.9335 0.9998 0.0002 0.0665 0.0513 0.9310 0.9288
RT-SBS-v2 [53] 29.57 0.6959 0.9995 0.0005 0.3041 0.1914 0.7315 0.7946
Multiscale Spatio-Temporal BG Model [12] 41.71 0.6796 0.9972 0.0028 0.3204 0.4151 0.5291 0.4926
SuBSENSE [13] 21.57 0.8050 0.9994 0.0006 0.1950 0.1527 0.7792 0.7814
WisenetMD [42] 16.29 0.7751 0.9998 0.0002 0.2249 0.1303 0.8304 0.9035
SOBS_CF [14] 44.43 0.7391 0.9763 0.0237 0.2609 2.4806 0.4702 0.4685
RMoG (Region-based Mixture of Gaussians) [15] 46.29 0.5780 0.9952 0.0048 0.4220 0.7314 0.4578 0.5701
FgSegNet_S (FPM) (Supervised Method) [44] 5.29 0.9795 0.9998 0.0002 0.0205 0.0291 0.9681 0.9571
FgSegNet_v2 (Supervised Method) [45] 3.29 0.9727 0.9999 0.0001 0.0273 0.0247 0.9727 0.9727
AAPSA [16] 41.86 0.7401 0.9933 0.0067 0.2599 0.7735 0.4643 0.4289
Multimode Background Subtraction Version 0 (MBS V0) [17] 42.14 0.5571 0.9981 0.0019 0.4429 0.3086 0.5698 0.6804
Multimode Background Subtraction [18] 41.86 0.6037 0.9979 0.0021 0.3963 0.3180 0.5858 0.6198
M4CD Version 2.0 [30] 21.57 0.7248 0.9997 0.0003 0.2752 0.1639 0.7978 0.8941
GraphCutDiff [19] 38.86 0.7562 0.9945 0.0055 0.2438 0.6509 0.5143 0.4929
Sample based background subtractor (SBBS) [31] 28.86 0.6962 0.9996 0.0004 0.3038 0.1969 0.7362 0.8055
Fast BSUV-Net 2.0 [56] 18.00 0.7045 0.9999 0.0001 0.2955 0.1580 0.7998 0.9292
EFIC [20] 36.29 0.6667 0.9991 0.0009 0.3333 0.2502 0.6713 0.7270
BSUV-net + SemanticBGS (supervised method) [51] 25.57 0.6781 0.9997 0.0003 0.3219 0.1345 0.7631 0.8830
RT-SBS-v1 [52] 37.14 0.7573 0.9941 0.0059 0.2427 0.7118 0.6070 0.6296
IUTIS-1 [21] 32.14 0.8533 0.9954 0.0046 0.1467 0.5339 0.5829 0.5506
IUTIS-2 [22] 29.71 0.7827 0.9987 0.0013 0.2173 0.2259 0.7145 0.6923
IUTIS-3 [23] 21.00 0.6860 0.9998 0.0002 0.3140 0.1638 0.7857 0.9261
CVABS [47] 28.14 0.6894 0.9995 0.0005 0.3106 0.1825 0.7665 0.8675
BMN-BSN (supervised method) [48] 42.14 0.7776 0.9682 0.0318 0.2224 3.2476 0.5544 0.5503
SWCD [43] 26.57 0.7218 0.9994 0.0006 0.2782 0.1763 0.7735 0.8382
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 3.71 0.9614 0.9999 0.0001 0.0386 0.0331 0.9648 0.9684
CL-VID [46] 40.86 0.8350 0.9759 0.0241 0.1650 2.4943 0.4734 0.4186
FgSegNet_v2_CO (Supervised learning) [54] 2.14 0.9727 0.9999 0.0001 0.0273 0.0246 0.9730 0.9733
SharedModel [28] 27.29 0.7904 0.9990 0.0010 0.2096 0.1936 0.7339 0.7566
C-EFIC [24] 37.71 0.6494 0.9990 0.0010 0.3506 0.2542 0.6275 0.7047
WeSamBE [33] 24.29 0.7382 0.9996 0.0004 0.2618 0.1748 0.7737 0.8371
DeepBS (supervised method) [34] 13.71 0.7979 0.9998 0.0002 0.2021 0.0838 0.8455 0.9082
BMOG [35] 33.29 0.6879 0.9993 0.0007 0.3121 0.2043 0.6932 0.7685
FgSegNet_v2_GOP (supervised learning) [49] 2.14 0.9727 0.9999 0.0001 0.0273 0.0246 0.9730 0.9733
PAWCS [25] 32.57 0.8117 0.9950 0.0050 0.1883 0.6378 0.6450 0.6809
MU-Net1 (Supervised Method) [55] 16.71 0.8994 0.9994 0.0006 0.1006 0.0849 0.8499 0.8388
Cascade CNN(supervised method) [29] 13.29 0.9303 0.9997 0.0003 0.0697 0.0584 0.9108 0.8935
Euclidean distance [1] 43.57 0.8340 0.9661 0.0339 0.1660 3.4759 0.4135 0.3565
KDE - ElGammal [2] 39.86 0.8492 0.9857 0.0143 0.1508 1.5119 0.4478 0.3908
SemanticBGS [38] 37.00 0.6597 0.9988 0.0012 0.3403 0.2705 0.6921 0.7790
GMM | Stauffer & Grimson [3] 39.86 0.7913 0.9882 0.0118 0.2087 1.2760 0.4663 0.4293
GMM | Zivkovic [4] 41.71 0.7786 0.9886 0.0114 0.2214 1.2460 0.4169 0.3494
Mahalanobis distance [5] 45.71 0.3521 0.9972 0.0028 0.6479 0.5272 0.3359 0.6578
CwisarDRP [26] 24.14 0.6221 0.9998 0.0002 0.3779 0.1572 0.7397 0.9273
IUTIS-5 [27] 20.71 0.6777 0.9999 0.0001 0.3223 0.1589 0.7836 0.9414
BSGAN (supervised method) [40] 12.00 0.9306 0.9997 0.0003 0.0694 0.0579 0.9118 0.8952
MU-Net2 (Supervised Method) [58] 9.57 0.9122 0.9998 0.0002 0.0878 0.0488 0.9272 0.9450
BSUV-Net (supervised method) [50] 30.57 0.7068 0.9993 0.0007 0.2932 0.1718 0.7051 0.7295
BSUV-Net 2.0 [57] 14.29 0.7320 0.9999 0.0001 0.2680 0.1445 0.8174 0.9437
CwisarDH [6] 29.57 0.6068 0.9997 0.0003 0.3932 0.1853 0.7227 0.8942
Spectral-360 [7] 36.43 0.8815 0.9859 0.0141 0.1185 1.4375 0.5429 0.4982
DCB [32] 54.86 0.2257 0.9765 0.0235 0.7743 2.7228 0.1582 0.3337
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 27.57 0.6109 0.9998 0.0002 0.3891 0.1987 0.7127 0.9035
SC_SOBS [9] 43.86 0.7277 0.9839 0.0161 0.2723 1.7286 0.4880 0.4955
AMBER [10] 26.71 0.6997 0.9997 0.0003 0.3003 0.1793 0.7545 0.8374
CP3-online [11] 49.14 0.5732 0.9946 0.0054 0.4268 0.6797 0.3743 0.3711
Simplified Self-Organized Background Subtraction [37] 48.43 0.7440 0.9452 0.0548 0.2560 5.6018 0.1515 0.0985

Results, for the baseline category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 8.00 0.9907 0.9993 0.0007 0.0093 0.0956 0.9837 0.9768
RT-SBS-v2 [53] 21.57 0.9653 0.9980 0.0020 0.0347 0.3258 0.9535 0.9423
Multiscale Spatio-Temporal BG Model [12] 49.14 0.8137 0.9970 0.0030 0.1863 1.1478 0.8450 0.8870
SuBSENSE [13] 21.00 0.9520 0.9982 0.0018 0.0480 0.3574 0.9503 0.9495
WisenetMD [42] 22.86 0.9507 0.9982 0.0018 0.0493 0.3674 0.9487 0.9477
SOBS_CF [14] 32.86 0.9347 0.9978 0.0022 0.0653 0.3912 0.9299 0.9254
RMoG (Region-based Mixture of Gaussians) [15] 42.86 0.7082 0.9981 0.0019 0.2918 1.5935 0.7848 0.9125
FgSegNet_S (FPM) (Supervised Method) [44] 3.00 0.9974 0.9999 0.0001 0.0026 0.0170 0.9977 0.9979
FgSegNet_v2 (Supervised Method) [45] 2.86 0.9977 0.9999 0.0001 0.0023 0.0145 0.9978 0.9978
AAPSA [16] 36.29 0.9092 0.9979 0.0021 0.0908 0.5826 0.9183 0.9286
Multimode Background Subtraction Version 0 (MBS V0) [17] 32.00 0.9158 0.9979 0.0021 0.0842 0.4361 0.9287 0.9431
Multimode Background Subtraction [18] 32.00 0.9158 0.9979 0.0021 0.0842 0.4361 0.9287 0.9431
M4CD Version 2.0 [30] 31.43 0.9540 0.9976 0.0024 0.0460 0.3927 0.9322 0.9123
GraphCutDiff [19] 54.14 0.7028 0.9960 0.0040 0.2972 1.9757 0.7147 0.8093
Sample based background subtractor (SBBS) [31] 38.57 0.9417 0.9973 0.0027 0.0583 0.4947 0.9192 0.8994
Fast BSUV-Net 2.0 [56] 14.00 0.9761 0.9983 0.0017 0.0239 0.2500 0.9694 0.9630
EFIC [20] 40.57 0.9349 0.9971 0.0029 0.0651 0.5223 0.9172 0.9023
BSUV-net + SemanticBGS (supervised method) [51] 19.57 0.9782 0.9978 0.0022 0.0218 0.2564 0.9640 0.9505
RT-SBS-v1 [52] 37.29 0.9639 0.9957 0.0043 0.0361 0.4955 0.9303 0.8992
IUTIS-1 [21] 32.43 0.9214 0.9979 0.0021 0.0786 0.4538 0.9298 0.9391
IUTIS-2 [22] 45.43 0.7452 0.9978 0.0022 0.2548 1.5115 0.7913 0.9100
IUTIS-3 [23] 19.14 0.9712 0.9981 0.0019 0.0288 0.3002 0.9546 0.9393
CVABS [47] 44.14 0.9437 0.9947 0.0053 0.0563 0.7089 0.9147 0.8877
BMN-BSN (supervised method) [48] 26.00 0.9677 0.9973 0.0027 0.0323 0.3253 0.9521 0.9371
SWCD [43] 40.57 0.9610 0.9952 0.0048 0.0390 0.6003 0.9214 0.8851
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 5.00 0.9971 0.9999 0.0001 0.0029 0.0196 0.9973 0.9976
CL-VID [46] 32.00 0.9666 0.9971 0.0029 0.0334 0.4094 0.9370 0.9098
FgSegNet_v2_CO (Supervised learning) [54] 1.57 0.9977 0.9999 0.0001 0.0023 0.0142 0.9978 0.9979
SharedModel [28] 20.71 0.9545 0.9982 0.0018 0.0455 0.3344 0.9522 0.9502
C-EFIC [24] 37.14 0.9455 0.9970 0.0030 0.0545 0.5201 0.9309 0.9170
WeSamBE [33] 27.43 0.9422 0.9981 0.0019 0.0578 0.4678 0.9413 0.9422
DeepBS (supervised method) [34] 17.29 0.9517 0.9987 0.0013 0.0483 0.2424 0.9580 0.9660
BMOG [35] 51.86 0.8553 0.9939 0.0061 0.1447 1.4545 0.8301 0.8196
FgSegNet_v2_GOP (supervised learning) [49] 1.57 0.9977 0.9999 0.0001 0.0023 0.0142 0.9978 0.9979
PAWCS [25] 29.00 0.9408 0.9980 0.0020 0.0592 0.4491 0.9397 0.9394
MU-Net1 (Supervised Method) [55] 6.71 0.9912 0.9995 0.0005 0.0088 0.0694 0.9875 0.9840
Cascade CNN(supervised method) [29] 10.43 0.9898 0.9989 0.0011 0.0102 0.1405 0.9786 0.9678
Euclidean distance [1] 48.14 0.8385 0.9955 0.0045 0.1615 1.0260 0.8720 0.9114
KDE - ElGammal [2] 39.43 0.8969 0.9977 0.0023 0.1031 0.5499 0.9092 0.9223
SemanticBGS [38] 22.00 0.9796 0.9976 0.0024 0.0204 0.3027 0.9604 0.9421
GMM | Stauffer & Grimson [3] 52.29 0.8180 0.9948 0.0052 0.1820 1.5325 0.8245 0.8461
GMM | Zivkovic [4] 48.00 0.8085 0.9972 0.0028 0.1915 1.3298 0.8382 0.8993
Mahalanobis distance [5] 39.86 0.3154 0.9991 0.0009 0.6846 2.8698 0.4642 0.9270
CwisarDRP [26] 35.71 0.8580 0.9981 0.0019 0.1420 0.8778 0.8880 0.9347
IUTIS-5 [27] 16.57 0.9680 0.9983 0.0017 0.0320 0.3053 0.9567 0.9464
BSGAN (supervised method) [40] 9.29 0.9905 0.9991 0.0009 0.0095 0.1202 0.9814 0.9725
MU-Net2 (Supervised Method) [58] 6.29 0.9907 0.9996 0.0004 0.0093 0.0550 0.9900 0.9894
BSUV-Net (supervised method) [50] 13.14 0.9776 0.9983 0.0017 0.0224 0.2157 0.9693 0.9614
BSUV-Net 2.0 [57] 15.00 0.9549 0.9987 0.0013 0.0451 0.1924 0.9620 0.9713
CwisarDH [6] 36.14 0.8972 0.9980 0.0020 0.1028 0.5679 0.9145 0.9337
Spectral-360 [7] 34.57 0.9616 0.9968 0.0032 0.0384 0.4265 0.9330 0.9065
DCB [32] 41.43 0.7123 0.9982 0.0018 0.2877 1.3771 0.7695 0.9070
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 33.29 0.9513 0.9975 0.0025 0.0487 0.4766 0.9330 0.9170
SC_SOBS [9] 29.29 0.9327 0.9980 0.0020 0.0673 0.3747 0.9333 0.9341
AMBER [10] 44.57 0.8784 0.9973 0.0027 0.1216 0.9233 0.8813 0.8980
CP3-online [11] 43.43 0.8501 0.9972 0.0028 0.1499 0.7725 0.8856 0.9252
Simplified Self-Organized Background Subtraction [37] 54.14 0.4894 0.9965 0.0035 0.5106 2.6366 0.6085 0.8419

Results, for the dynamic background category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 6.43 0.9927 1.0000 0.0000 0.0073 0.0097 0.9849 0.9778
RT-SBS-v2 [53] 15.86 0.9209 0.9992 0.0008 0.0791 0.1301 0.9217 0.9241
Multiscale Spatio-Temporal BG Model [12] 47.43 0.7392 0.9905 0.0095 0.2608 1.1365 0.5953 0.5515
SuBSENSE [13] 28.14 0.7768 0.9994 0.0006 0.2232 0.4042 0.8177 0.8915
WisenetMD [42] 25.57 0.8062 0.9994 0.0006 0.1938 0.3285 0.8376 0.8932
SOBS_CF [14] 39.71 0.9014 0.9820 0.0180 0.0986 1.8391 0.6519 0.5953
RMoG (Region-based Mixture of Gaussians) [15] 36.86 0.7892 0.9978 0.0022 0.2108 0.4238 0.7352 0.7288
FgSegNet_S (FPM) (Supervised Method) [44] 2.71 0.9983 1.0000 0.0000 0.0017 0.0055 0.9958 0.9934
FgSegNet_v2 (Supervised Method) [45] 4.14 0.9976 1.0000 0.0000 0.0024 0.0066 0.9951 0.9927
AAPSA [16] 40.71 0.7083 0.9983 0.0017 0.2917 0.4992 0.6706 0.7336
Multimode Background Subtraction Version 0 (MBS V0) [17] 38.29 0.7637 0.9972 0.0028 0.2363 0.4848 0.7904 0.8606
Multimode Background Subtraction [18] 37.14 0.7641 0.9972 0.0028 0.2359 0.4845 0.7915 0.8651
M4CD Version 2.0 [30] 38.57 0.8518 0.9930 0.0070 0.1482 0.8043 0.6857 0.6841
GraphCutDiff [19] 52.43 0.7693 0.9063 0.0937 0.2307 9.2106 0.5391 0.5357
Sample based background subtractor (SBBS) [31] 26.57 0.7772 0.9994 0.0006 0.2228 0.2682 0.8128 0.9037
Fast BSUV-Net 2.0 [56] 36.71 0.7719 0.9984 0.0016 0.2281 0.4620 0.7320 0.7949
EFIC [20] 45.29 0.6667 0.9967 0.0033 0.3333 0.9154 0.5779 0.6849
BSUV-net + SemanticBGS (supervised method) [51] 23.57 0.9403 0.9985 0.0015 0.0597 0.1902 0.8176 0.7733
RT-SBS-v1 [52] 20.86 0.8900 0.9991 0.0009 0.1100 0.1550 0.8811 0.8756
IUTIS-1 [21] 45.71 0.8811 0.9487 0.0513 0.1189 5.1263 0.4189 0.3305
IUTIS-2 [22] 46.43 0.8027 0.9828 0.0172 0.1973 2.0051 0.5741 0.5564
IUTIS-3 [23] 19.14 0.8778 0.9993 0.0007 0.1222 0.1985 0.8960 0.9239
CVABS [47] 27.14 0.8517 0.9988 0.0012 0.1483 0.3037 0.8618 0.8768
BMN-BSN (supervised method) [48] 42.57 0.8676 0.9821 0.0179 0.1324 1.8297 0.6371 0.5662
SWCD [43] 26.43 0.8692 0.9984 0.0016 0.1308 0.2809 0.8645 0.8633
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 2.86 0.9966 1.0000 0.0000 0.0034 0.0065 0.9958 0.9950
CL-VID [46] 42.43 0.9151 0.9735 0.0265 0.0849 2.6936 0.5524 0.5060
FgSegNet_v2_CO (Supervised learning) [54] 2.14 0.9976 1.0000 0.0000 0.0024 0.0062 0.9959 0.9942
SharedModel [28] 28.00 0.7597 0.9995 0.0005 0.2403 0.3304 0.8222 0.9198
C-EFIC [24] 47.00 0.6556 0.9952 0.0048 0.3444 1.0825 0.5627 0.6993
WeSamBE [33] 32.43 0.6796 0.9995 0.0005 0.3204 0.6012 0.7440 0.8933
DeepBS (supervised method) [34] 24.14 0.8543 0.9988 0.0012 0.1457 0.2067 0.8761 0.9083
BMOG [35] 30.43 0.9006 0.9966 0.0034 0.0994 0.4040 0.7928 0.7582
FgSegNet_v2_GOP (supervised learning) [49] 2.14 0.9976 1.0000 0.0000 0.0024 0.0062 0.9959 0.9942
PAWCS [25] 20.86 0.8868 0.9989 0.0011 0.1132 0.1917 0.8938 0.9038
MU-Net1 (Supervised Method) [55] 8.86 0.9872 0.9997 0.0003 0.0128 0.0418 0.9836 0.9802
Cascade CNN(supervised method) [29] 10.29 0.9798 0.9997 0.0003 0.0202 0.0522 0.9658 0.9528
Euclidean distance [1] 51.00 0.7757 0.9714 0.0286 0.2243 3.0095 0.5081 0.4487
KDE - ElGammal [2] 45.14 0.8012 0.9856 0.0144 0.1988 1.6393 0.5961 0.5732
SemanticBGS [38] 11.71 0.9467 0.9996 0.0004 0.0533 0.0925 0.9489 0.9512
GMM | Stauffer & Grimson [3] 42.14 0.8344 0.9896 0.0104 0.1656 1.2083 0.6330 0.5989
GMM | Zivkovic [4] 42.86 0.8019 0.9903 0.0097 0.1981 1.1725 0.6328 0.6213
Mahalanobis distance [5] 44.29 0.1237 0.9988 0.0012 0.8763 1.1753 0.1798 0.7451
CwisarDRP [26] 25.71 0.8291 0.9992 0.0008 0.1709 0.2892 0.8487 0.8723
IUTIS-5 [27] 17.71 0.8636 0.9996 0.0004 0.1364 0.1808 0.8902 0.9324
BSGAN (supervised method) [40] 8.00 0.9878 0.9998 0.0002 0.0122 0.0408 0.9763 0.9656
MU-Net2 (Supervised Method) [58] 7.00 0.9878 0.9999 0.0001 0.0122 0.0223 0.9892 0.9906
BSUV-Net (supervised method) [50] 26.43 0.9294 0.9981 0.0019 0.0706 0.2703 0.7967 0.7484
BSUV-Net 2.0 [57] 14.29 0.8782 0.9997 0.0003 0.1218 0.0840 0.9057 0.9396
CwisarDH [6] 29.86 0.8144 0.9985 0.0015 0.1856 0.3270 0.8274 0.8499
Spectral-360 [7] 31.43 0.7819 0.9992 0.0008 0.2181 0.3513 0.7766 0.8456
DCB [32] 39.43 0.5803 0.9991 0.0009 0.4197 0.5921 0.6149 0.7632
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 20.43 0.8691 0.9993 0.0007 0.1309 0.1887 0.8792 0.9129
SC_SOBS [9] 38.43 0.8918 0.9836 0.0164 0.1082 1.6899 0.6686 0.6283
AMBER [10] 29.00 0.9177 0.9956 0.0044 0.0823 0.4837 0.8436 0.7990
CP3-online [11] 44.86 0.7260 0.9963 0.0037 0.2740 0.6613 0.6111 0.6122
Simplified Self-Organized Background Subtraction [37] 56.29 0.5234 0.9252 0.0748 0.4766 7.8981 0.1613 0.1013

Results, for the camera jitter category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 6.29 0.9905 0.9993 0.0007 0.0095 0.1099 0.9893 0.9882
RT-SBS-v2 [53] 26.43 0.8724 0.9884 0.0116 0.1276 1.6602 0.8233 0.7816
Multiscale Spatio-Temporal BG Model [12] 50.57 0.7171 0.9477 0.0523 0.2829 6.0218 0.5073 0.3979
SuBSENSE [13] 26.86 0.8243 0.9908 0.0092 0.1757 1.6469 0.8152 0.8115
WisenetMD [42] 25.14 0.8235 0.9918 0.0082 0.1765 1.5393 0.8228 0.8278
SOBS_CF [14] 38.86 0.8218 0.9768 0.0232 0.1782 2.8437 0.7150 0.6405
RMoG (Region-based Mixture of Gaussians) [15] 44.00 0.6669 0.9864 0.0136 0.3331 2.6794 0.7010 0.7605
FgSegNet_S (FPM) (Supervised Method) [44] 4.43 0.9955 0.9998 0.0002 0.0045 0.0417 0.9957 0.9959
FgSegNet_v2 (Supervised Method) [45] 2.43 0.9962 0.9999 0.0001 0.0038 0.0262 0.9971 0.9979
AAPSA [16] 38.86 0.6637 0.9916 0.0084 0.3363 2.1753 0.7207 0.8021
Multimode Background Subtraction Version 0 (MBS V0) [17] 20.29 0.8321 0.9929 0.0071 0.1679 1.5408 0.8367 0.8443
Multimode Background Subtraction [18] 20.29 0.8321 0.9929 0.0071 0.1679 1.5408 0.8367 0.8443
M4CD Version 2.0 [30] 24.29 0.8159 0.9921 0.0079 0.1841 1.4478 0.8231 0.8403
GraphCutDiff [19] 52.14 0.6938 0.9222 0.0778 0.3062 8.4121 0.5489 0.5918
Sample based background subtractor (SBBS) [31] 37.86 0.7322 0.9874 0.0126 0.2678 2.1608 0.7347 0.7950
Fast BSUV-Net 2.0 [56] 19.71 0.9355 0.9886 0.0114 0.0645 1.3187 0.8828 0.8492
EFIC [20] 38.57 0.8201 0.9789 0.0211 0.1799 2.7134 0.7125 0.6389
BSUV-net + SemanticBGS (supervised method) [51] 31.14 0.8465 0.9864 0.0136 0.1535 1.9372 0.7788 0.7474
RT-SBS-v1 [52] 32.71 0.7964 0.9884 0.0116 0.2036 1.9651 0.7806 0.7864
IUTIS-1 [21] 45.14 0.7936 0.9480 0.0520 0.2064 5.8053 0.5997 0.5299
IUTIS-2 [22] 40.29 0.7209 0.9867 0.0133 0.2791 2.4236 0.7165 0.7184
IUTIS-3 [23] 25.14 0.7923 0.9924 0.0076 0.2077 1.5231 0.8139 0.8520
CVABS [47] 27.57 0.7432 0.9933 0.0067 0.2568 1.5892 0.7837 0.8359
BMN-BSN (supervised method) [48] 38.14 0.9099 0.9517 0.0483 0.0901 4.9312 0.6962 0.6069
SWCD [43] 35.86 0.7085 0.9917 0.0083 0.2915 1.8873 0.7411 0.7827
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 4.57 0.9934 0.9999 0.0001 0.0066 0.0439 0.9954 0.9974
CL-VID [46] 43.00 0.8792 0.9306 0.0694 0.1208 7.0993 0.5214 0.3809
FgSegNet_v2_CO (Supervised learning) [54] 1.29 0.9962 0.9999 0.0001 0.0038 0.0262 0.9971 0.9979
SharedModel [28] 27.43 0.7960 0.9920 0.0080 0.2040 1.6061 0.8141 0.8377
C-EFIC [24] 25.57 0.8458 0.9890 0.0110 0.1542 1.6653 0.8248 0.8157
WeSamBE [33] 29.14 0.7777 0.9921 0.0079 0.2223 1.7091 0.7976 0.8395
DeepBS (supervised method) [34] 13.29 0.8788 0.9957 0.0043 0.1212 0.8994 0.8990 0.9313
BMOG [35] 34.71 0.8363 0.9777 0.0223 0.1637 2.6753 0.7493 0.7293
FgSegNet_v2_GOP (supervised learning) [49] 1.29 0.9962 0.9999 0.0001 0.0038 0.0262 0.9971 0.9979
PAWCS [25] 22.71 0.7840 0.9935 0.0065 0.2160 1.4220 0.8137 0.8660
MU-Net1 (Supervised Method) [55] 9.29 0.9869 0.9989 0.0011 0.0131 0.1562 0.9802 0.9740
Cascade CNN(supervised method) [29] 9.43 0.9885 0.9984 0.0016 0.0115 0.2105 0.9758 0.9635
Euclidean distance [1] 51.71 0.7115 0.9456 0.0544 0.2885 6.2957 0.4874 0.3753
KDE - ElGammal [2] 46.86 0.7375 0.9562 0.0438 0.2625 5.1349 0.5720 0.4862
SemanticBGS [38] 18.57 0.8282 0.9930 0.0070 0.1718 1.3826 0.8388 0.8623
GMM | Stauffer & Grimson [3] 45.71 0.7334 0.9666 0.0334 0.2666 4.2269 0.5969 0.5126
GMM | Zivkovic [4] 48.86 0.6900 0.9665 0.0335 0.3100 4.4057 0.5670 0.4872
Mahalanobis distance [5] 36.57 0.2157 0.9976 0.0024 0.7843 3.4663 0.3358 0.8564
CwisarDRP [26] 28.71 0.7049 0.9936 0.0064 0.2951 1.8416 0.7656 0.8713
IUTIS-5 [27] 21.57 0.8220 0.9925 0.0075 0.1780 1.4389 0.8332 0.8511
BSGAN (supervised method) [40] 7.29 0.9912 0.9989 0.0011 0.0088 0.1479 0.9828 0.9746
MU-Net2 (Supervised Method) [58] 7.71 0.9881 0.9990 0.0010 0.0119 0.1411 0.9824 0.9770
BSUV-Net (supervised method) [50] 32.14 0.8635 0.9844 0.0156 0.1365 2.0539 0.7743 0.7224
BSUV-Net 2.0 [57] 12.29 0.8804 0.9961 0.0039 0.1196 0.8499 0.9004 0.9271
CwisarDH [6] 26.71 0.7437 0.9931 0.0069 0.2563 1.7058 0.7886 0.8516
Spectral-360 [7] 38.14 0.6696 0.9906 0.0094 0.3304 2.0855 0.7142 0.8387
DCB [32] 35.71 0.2796 0.9969 0.0031 0.7204 3.3105 0.3669 0.9107
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 36.86 0.7717 0.9866 0.0134 0.2283 2.0787 0.7513 0.7645
SC_SOBS [9] 40.43 0.8113 0.9768 0.0232 0.1887 2.8794 0.7051 0.6286
AMBER [10] 33.14 0.6505 0.9938 0.0062 0.3495 1.9125 0.7107 0.8493
CP3-online [11] 51.86 0.6629 0.9519 0.0481 0.3371 5.9333 0.5207 0.4562
Simplified Self-Organized Background Subtraction [37] 55.43 0.5808 0.9373 0.0627 0.4192 7.7124 0.4147 0.3411

Results, for the intermittent object motion category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 9.86 0.9136 0.9977 0.0023 0.0864 1.0124 0.9366 0.9653
RT-SBS-v2 [53] 17.43 0.9093 0.9898 0.0102 0.0907 1.2485 0.8946 0.8913
Multiscale Spatio-Temporal BG Model [12] 46.57 0.5661 0.9448 0.0552 0.4339 7.1430 0.4497 0.6016
SuBSENSE [13] 31.00 0.6578 0.9915 0.0085 0.3422 3.8349 0.6569 0.7957
WisenetMD [42] 27.00 0.7398 0.9903 0.0097 0.2602 3.1606 0.7264 0.7881
SOBS_CF [14] 38.57 0.7641 0.9381 0.0619 0.2359 6.7454 0.5810 0.5464
RMoG (Region-based Mixture of Gaussians) [15] 35.86 0.4488 0.9950 0.0050 0.5512 4.6882 0.5431 0.8026
FgSegNet_S (FPM) (Supervised Method) [44] 4.57 0.9970 0.9994 0.0006 0.0030 0.0709 0.9940 0.9911
FgSegNet_v2 (Supervised Method) [45] 3.14 0.9968 0.9996 0.0004 0.0032 0.0567 0.9961 0.9955
AAPSA [16] 41.43 0.4912 0.9890 0.0110 0.5088 4.9776 0.5098 0.7139
Multimode Background Subtraction Version 0 (MBS V0) [17] 28.86 0.6386 0.9931 0.0069 0.3614 3.1858 0.7092 0.8201
Multimode Background Subtraction [18] 27.14 0.7418 0.9862 0.0138 0.2582 2.3008 0.7568 0.7827
M4CD Version 2.0 [30] 28.00 0.7153 0.9909 0.0091 0.2847 3.1601 0.6939 0.8055
GraphCutDiff [19] 35.57 0.2923 0.9977 0.0023 0.7077 5.1143 0.4019 0.8315
Sample based background subtractor (SBBS) [31] 35.86 0.7616 0.9399 0.0601 0.2384 6.3180 0.6795 0.6772
Fast BSUV-Net 2.0 [56] 12.43 0.8567 0.9977 0.0023 0.1433 1.0897 0.9016 0.9572
EFIC [20] 43.29 0.7416 0.8942 0.1058 0.2584 11.5448 0.5783 0.5634
BSUV-net + SemanticBGS (supervised method) [51] 19.29 0.6896 0.9982 0.0018 0.3104 2.6042 0.7601 0.9165
RT-SBS-v1 [52] 25.57 0.6084 0.9967 0.0033 0.3916 3.5062 0.7126 0.9006
IUTIS-1 [21] 48.00 0.6050 0.9280 0.0720 0.3950 9.5356 0.5073 0.5485
IUTIS-2 [22] 35.43 0.3735 0.9973 0.0027 0.6265 4.7669 0.4836 0.8374
IUTIS-3 [23] 26.86 0.6987 0.9946 0.0054 0.3013 3.2481 0.7136 0.8146
CVABS [47] 36.43 0.6941 0.9832 0.0168 0.3059 4.1728 0.6586 0.6773
BMN-BSN (supervised method) [48] 39.29 0.9018 0.8671 0.1329 0.0982 11.8077 0.6369 0.5714
SWCD [43] 28.86 0.7606 0.9881 0.0119 0.2394 3.6639 0.7092 0.7372
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 4.86 0.9960 0.9996 0.0004 0.0040 0.0732 0.9951 0.9941
CL-VID [46] 43.86 0.7794 0.8725 0.1275 0.2206 11.9905 0.5177 0.4596
FgSegNet_v2_CO (Supervised learning) [54] 1.86 0.9967 0.9997 0.0003 0.0033 0.0523 0.9964 0.9961
SharedModel [28] 32.14 0.7182 0.9867 0.0133 0.2818 4.0264 0.6727 0.7587
C-EFIC [24] 37.86 0.8107 0.9172 0.0828 0.1893 8.4615 0.6229 0.5823
WeSamBE [33] 26.43 0.7472 0.9891 0.0109 0.2528 3.2798 0.7392 0.7888
DeepBS (supervised method) [34] 31.71 0.5735 0.9949 0.0051 0.4265 4.1292 0.6098 0.8251
BMOG [35] 41.00 0.5095 0.9871 0.0129 0.4905 4.8434 0.5291 0.6818
FgSegNet_v2_GOP (supervised learning) [49] 1.86 0.9967 0.9997 0.0003 0.0033 0.0523 0.9964 0.9961
PAWCS [25] 20.86 0.7487 0.9945 0.0055 0.2513 2.3536 0.7764 0.8392
MU-Net1 (Supervised Method) [55] 6.86 0.9816 0.9995 0.0005 0.0184 0.1746 0.9872 0.9931
Cascade CNN(supervised method) [29] 20.86 0.9840 0.9843 0.0157 0.0160 1.5416 0.8505 0.7821
Euclidean distance [1] 48.29 0.5919 0.9336 0.0664 0.4081 8.9975 0.4892 0.4995
KDE - ElGammal [2] 51.71 0.5035 0.9309 0.0691 0.4965 10.0695 0.4088 0.4609
SemanticBGS [38] 18.29 0.7231 0.9978 0.0022 0.2769 2.7695 0.7878 0.9149
GMM | Stauffer & Grimson [3] 43.43 0.5142 0.9835 0.0165 0.4858 5.1955 0.5207 0.6688
GMM | Zivkovic [4] 44.43 0.5467 0.9712 0.0288 0.4533 5.4986 0.5325 0.6458
Mahalanobis distance [5] 51.43 0.1607 0.9780 0.0220 0.8393 8.0275 0.2290 0.5098
CwisarDRP [26] 33.00 0.4614 0.9957 0.0043 0.5386 4.2319 0.5626 0.8543
IUTIS-5 [27] 23.00 0.7047 0.9963 0.0037 0.2953 3.0420 0.7296 0.8501
BSGAN (supervised method) [40] 9.86 0.9136 0.9977 0.0023 0.0864 1.0124 0.9366 0.9653
MU-Net2 (Supervised Method) [58] 4.43 0.9832 0.9998 0.0002 0.0168 0.1280 0.9894 0.9956
BSUV-Net (supervised method) [50] 20.14 0.6806 0.9981 0.0019 0.3194 2.6454 0.7499 0.9401
BSUV-Net 2.0 [57] 14.14 0.7428 0.9992 0.0008 0.2572 1.7176 0.8263 0.9693
CwisarDH [6] 36.43 0.5549 0.9911 0.0089 0.4451 4.6560 0.5753 0.7417
Spectral-360 [7] 40.57 0.5878 0.9835 0.0165 0.4122 5.3734 0.5609 0.7374
DCB [32] 50.29 0.4415 0.9695 0.0305 0.5585 7.5659 0.3710 0.5291
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 17.29 0.7813 0.9950 0.0050 0.2187 1.6329 0.7891 0.8512
SC_SOBS [9] 38.86 0.7237 0.9613 0.0387 0.2763 5.2207 0.5918 0.5896
AMBER [10] 27.00 0.7617 0.9866 0.0134 0.2383 2.7784 0.7211 0.7530
CP3-online [11] 39.86 0.7826 0.8746 0.1254 0.2174 11.5284 0.6177 0.5631
Simplified Self-Organized Background Subtraction [37] 42.14 0.2161 0.9951 0.0049 0.7839 5.8185 0.3021 0.6538

Results, for the shadow category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision  Average   FPR-S 
BSPVGAN (supervised method) [41] 6.57 0.9873 0.9992 0.0008 0.0127 0.1368 0.9849 0.9825 0.0229
RT-SBS-v2 [53] 13.86 0.9669 0.9963 0.0037 0.0331 0.4977 0.9497 0.9340 0.1717
Multiscale Spatio-Temporal BG Model [12] 42.71 0.7824 0.9910 0.0090 0.2176 1.6933 0.7918 0.8130 0.5282
SuBSENSE [13] 24.14 0.9419 0.9920 0.0080 0.0581 1.0120 0.8986 0.8646 0.5996
WisenetMD [42] 24.43 0.9424 0.9920 0.0080 0.0576 1.0118 0.8984 0.8637 0.5966
SOBS_CF [14] 47.71 0.8699 0.9828 0.0172 0.1301 2.2579 0.7721 0.7045 0.5899
RMoG (Region-based Mixture of Gaussians) [15] 40.57 0.6680 0.9936 0.0064 0.3320 2.1720 0.7212 0.8073 0.3097
FgSegNet_S (FPM) (Supervised Method) [44] 3.86 0.9962 0.9997 0.0003 0.0038 0.0466 0.9927 0.9893 0.0057
FgSegNet_v2 (Supervised Method) [45] 2.71 0.9958 0.9998 0.0002 0.0042 0.0352 0.9955 0.9952 0.0062
AAPSA [16] 45.29 0.8589 0.9855 0.0145 0.1411 1.9218 0.7953 0.7452 0.5877
Multimode Background Subtraction Version 0 (MBS V0) [17] 41.71 0.7762 0.9918 0.0082 0.2238 1.5794 0.7784 0.8063 0.3481
Multimode Background Subtraction [18] 36.71 0.7920 0.9924 0.0076 0.2080 1.4940 0.7968 0.8262 0.3481
M4CD Version 2.0 [30] 25.43 0.9324 0.9922 0.0078 0.0676 1.0796 0.8969 0.8707 0.5749
GraphCutDiff [19] 41.71 0.6578 0.9936 0.0064 0.3422 2.3516 0.7228 0.8271 0.4260
Sample based background subtractor (SBBS) [31] 35.71 0.5981 0.9970 0.0030 0.4019 1.8693 0.7105 0.8934 0.1228
Fast BSUV-Net 2.0 [56] 25.43 0.9222 0.9928 0.0072 0.0778 1.0989 0.8890 0.8741 0.4219
EFIC [20] 41.00 0.8543 0.9908 0.0092 0.1457 1.7066 0.8202 0.8056 0.4846
BSUV-net + SemanticBGS (supervised method) [51] 11.00 0.9661 0.9986 0.0014 0.0339 0.3263 0.9664 0.9676 0.0501
RT-SBS-v1 [52] 16.57 0.9573 0.9950 0.0050 0.0427 0.6507 0.9363 0.9189 0.2507
IUTIS-1 [21] 35.43 0.8748 0.9912 0.0088 0.1252 1.3512 0.8494 0.8291 0.6032
IUTIS-2 [22] 37.86 0.6636 0.9946 0.0054 0.3364 2.2199 0.7393 0.8621 0.4480
IUTIS-3 [23] 26.00 0.9478 0.9914 0.0086 0.0522 1.0410 0.8984 0.8585 0.6031
CVABS [47] 34.43 0.9237 0.9898 0.0102 0.0763 1.2986 0.8755 0.8361 0.5043
BMN-BSN (supervised method) [48] 32.29 0.9670 0.9887 0.0113 0.0330 1.2111 0.8588 0.7893 0.5280
SWCD [43] 33.14 0.9348 0.9898 0.0102 0.0652 1.2363 0.8779 0.8302 0.5507
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 4.29 0.9930 0.9998 0.0002 0.0070 0.0465 0.9937 0.9944 0.0042
CL-VID [46] 38.14 0.9324 0.9884 0.0116 0.0676 1.3860 0.8409 0.7703 0.6229
FgSegNet_v2_CO (Supervised learning) [54] 1.57 0.9957 0.9998 0.0002 0.0043 0.0337 0.9958 0.9959 0.0061
SharedModel [28] 28.86 0.9445 0.9910 0.0090 0.0555 1.0876 0.8898 0.8455 0.5937
C-EFIC [24] 30.86 0.9191 0.9920 0.0080 0.0809 1.1933 0.8778 0.8453 0.4791
WeSamBE [33] 23.43 0.9401 0.9923 0.0077 0.0599 1.0187 0.8999 0.8686 0.5532
DeepBS (supervised method) [34] 17.29 0.9584 0.9942 0.0058 0.0416 0.7403 0.9304 0.9092 0.4844
BMOG [35] 37.57 0.8590 0.9909 0.0091 0.1410 1.5975 0.8414 0.8396 0.5372
FgSegNet_v2_GOP (supervised learning) [49] 1.57 0.9957 0.9998 0.0002 0.0043 0.0337 0.9958 0.9959 0.0061
PAWCS [25] 25.43 0.9172 0.9932 0.0068 0.0828 1.0230 0.8913 0.8710 0.4815
MU-Net1 (Supervised Method) [55] 7.71 0.9924 0.9986 0.0014 0.0076 0.1576 0.9825 0.9729 0.0213
Cascade CNN(supervised method) [29] 11.14 0.9781 0.9973 0.0027 0.0219 0.3500 0.9593 0.9414 0.1566
Euclidean distance [1] 52.43 0.8006 0.9783 0.0217 0.1994 2.8949 0.6786 0.6112 0.5763
KDE - ElGammal [2] 43.43 0.8541 0.9885 0.0115 0.1459 1.6844 0.8030 0.7660 0.6217
SemanticBGS [38] 14.00 0.9748 0.9954 0.0046 0.0252 0.5383 0.9478 0.9244 0.3018
GMM | Stauffer & Grimson [3] 48.71 0.7960 0.9871 0.0129 0.2040 2.1951 0.7370 0.7156 0.5352
GMM | Zivkovic [4] 49.29 0.7774 0.9878 0.0122 0.2226 2.1908 0.7322 0.7232 0.5428
Mahalanobis distance [5] 38.71 0.2109 0.9980 0.0020 0.7891 3.6861 0.3353 0.8726 0.0644
CwisarDRP [26] 35.00 0.8298 0.9922 0.0078 0.1702 1.6625 0.8249 0.8551 0.5773
IUTIS-5 [27] 20.43 0.9492 0.9923 0.0077 0.0508 0.9484 0.9084 0.8766 0.5792
BSGAN (supervised method) [40] 9.43 0.9808 0.9980 0.0020 0.0192 0.2670 0.9680 0.9556 0.1046
MU-Net2 (Supervised Method) [58] 6.71 0.9929 0.9987 0.0013 0.0071 0.1443 0.9845 0.9763 0.0327
BSUV-Net (supervised method) [50] 19.29 0.9294 0.9960 0.0040 0.0706 0.7449 0.9233 0.9222 0.1879
BSUV-Net 2.0 [57] 12.43 0.9732 0.9963 0.0037 0.0268 0.4668 0.9562 0.9427 0.2506
CwisarDH [6] 34.00 0.8786 0.9910 0.0090 0.1214 1.2770 0.8581 0.8476 0.5547
Spectral-360 [7] 38.14 0.8898 0.9893 0.0107 0.1102 1.5682 0.8519 0.8187 0.5815
DCB [32] 54.00 0.6635 0.9838 0.0162 0.3365 3.2273 0.6307 0.6612 0.3706
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 30.29 0.9214 0.9918 0.0082 0.0786 1.1305 0.8832 0.8535 0.5005
SC_SOBS [9] 48.14 0.8502 0.9834 0.0166 0.1498 2.3000 0.7786 0.7230 0.6035
AMBER [10] 40.00 0.8297 0.9914 0.0086 0.1703 1.7537 0.8128 0.8098 0.4658
CP3-online [11] 52.29 0.7840 0.9832 0.0168 0.2160 2.5175 0.7037 0.6539 0.5914
Simplified Self-Organized Background Subtraction [37] 51.14 0.5020 0.9904 0.0096 0.4980 3.0726 0.5935 0.7521 0.3694

Results, for the thermal category.

Click on method name for more details.

Method Average ranking Average     Re  Average     Sp  Average   FPR  Average   FNR  Average   PWC     Average     F-Measure  Average   Precision 
BSPVGAN (supervised method) [41] 8.71 0.9763 0.9989 0.0011 0.0237 0.2406 0.9764 0.9770
RT-SBS-v2 [53] 19.71 0.8733 0.9947 0.0053 0.1267 1.0218 0.8697 0.8679
Multiscale Spatio-Temporal BG Model [12] 49.00 0.4102 0.9929 0.0071 0.5898 3.9622 0.5103 0.8403
SuBSENSE [13] 36.29 0.8161 0.9908 0.0092 0.1839 2.0125 0.8171 0.8328
WisenetMD [42] 33.00 0.7867 0.9931 0.0069 0.2133 1.8993 0.8152 0.8696
SOBS_CF [14] 33.86 0.6347 0.9953 0.0047 0.3653 1.8021 0.7140 0.8715
RMoG (Region-based Mixture of Gaussians) [15] 35.29 0.3441 0.9991 0.0009 0.6559 5.1222 0.4788 0.9365
FgSegNet_S (FPM) (Supervised Method) [44] 2.14 0.9926 0.9998 0.0002 0.0074 0.0517 0.9937 0.9949
FgSegNet_v2 (Supervised Method) [45] 3.14 0.9924 0.9997 0.0003 0.0076 0.0574 0.9938 0.9952
AAPSA [16] 33.14 0.6186 0.9957 0.0043 0.3814 1.8316 0.7030 0.8795
Multimode Background Subtraction Version 0 (MBS V0) [17] 36.00 0.8101 0.9908 0.0092 0.1899 1.5315 0.8115 0.8174
Multimode Background Subtraction [18] 33.14 0.8162 0.9920 0.0080 0.1838 1.4289 0.8194 0.8268
M4CD Version 2.0 [30] 27.86 0.6432 0.9981 0.0019 0.3568 2.0839 0.7448 0.9517
GraphCutDiff [19] 36.57 0.4899 0.9976 0.0024 0.5101 4.6735 0.5786 0.9111
Sample based background subtractor (SBBS) [31] 34.71 0.6929 0.9941 0.0059 0.3071 1.6545 0.7499 0.8579
Fast BSUV-Net 2.0 [56] 21.71 0.7957 0.9951 0.0049 0.2043 1.2058 0.8379 0.9178
EFIC [20] 25.43 0.8335 0.9944 0.0056 0.1665 1.3553 0.8388 0.8490
BSUV-net + SemanticBGS (supervised method) [51] 35.43 0.8764 0.9790 0.0210 0.1236 2.4043 0.8455 0.8267
RT-SBS-v1 [52] 39.43 0.5892 0.9920 0.0080 0.4108 2.3025 0.7041 0.9401
IUTIS-1 [21] 30.14 0.6171 0.9972 0.0028 0.3829 1.9653 0.7174 0.9245
IUTIS-2 [22] 35.29 0.4125 0.9987 0.0013 0.5875 4.9923 0.5306 0.9395
IUTIS-3 [23] 25.71 0.7832 0.9945 0.0055 0.2168 1.2552 0.8210 0.8922
CVABS [47] 27.57 0.8706 0.9930 0.0070 0.1294 1.4160 0.8567 0.8470
BMN-BSN (supervised method) [48] 39.14 0.7534 0.9899 0.0101 0.2466 1.6661 0.7849 0.8421
SWCD [43] 25.14 0.8602 0.9932 0.0068 0.1398 1.2664 0.8581 0.8585
FgSegNet (Foreground Segmentation Network) (Supervised Method) [39] 5.29 0.9907 0.9997 0.0003 0.0093 0.0672 0.9921 0.9935
CL-VID [46] 45.14 0.6667 0.9903 0.0097 0.3333 3.3354 0.7260 0.8301
FgSegNet_v2_CO (Supervised learning) [54] 2.43 0.9922 0.9997 0.0003 0.0078 0.0572 0.9938 0.9954
SharedModel [28] 36.14 0.8618 0.9845 0.0155 0.1382 1.8656 0.8319 0.8072
C-EFIC [24] 25.86 0.8131 0.9943 0.0057 0.1869 1.3706 0.8349 0.8690
WeSamBE [33] 36.57 0.7727 0.9928 0.0072 0.2273 2.3538 0.7962 0.8554
DeepBS (supervised method) [34] 31.29 0.6637 0.9956 0.0044 0.3363 3.5773 0.7583 0.9257
BMOG [35] 36.57 0.5244 0.9960 0.0040 0.4756 4.3614 0.6348 0.9005
FgSegNet_v2_GOP (supervised learning) [49] 2.43 0.9922 0.9997 0.0003 0.0078 0.0572 0.9938 0.9954
PAWCS [25] 31.71 0.8504 0.9910 0.0090 0.1496 1.4018 0.8324 0.8280
MU-Net1 (Supervised Method) [55] 7.71 0.9852 0.9990 0.0010 0.0148 0.1389 0.9825 0.9799
Cascade CNN(supervised method) [29] 22.71 0.9461 0.9931 0.0069 0.0539 1.0478 0.8958 0.8577
Euclidean distance [1] 46.71 0.5111 0.9907 0.0093 0.4889 3.8516 0.6313 0.8877
KDE - ElGammal [2] 30.29 0.6725 0.9955 0.0045 0.3275 1.6795 0.7423 0.8974
SemanticBGS [38] 27.86 0.7664 0.9932 0.0068 0.2336 1.3897 0.8219 0.9118
GMM | Stauffer & Grimson [3] 40.57 0.5691 0.9946 0.0054 0.4309 4.2642 0.6621 0.8652
GMM | Zivkovic [4] 42.00 0.5542 0.9942 0.0058 0.4458 4.3002 0.6548 0.8706
Mahalanobis distance [5] 33.57 0.0786 0.9999 0.0001 0.9214 6.0413 0.1383 0.9932
CwisarDRP [26] 29.14 0.6778 0.9969 0.0031 0.3222 3.4564 0.7619 0.9116
IUTIS-5 [27] 22.43 0.7990 0.9952 0.0048 0.2010 1.1484 0.8303 0.8969
BSGAN (supervised method) [40] 20.00 0.9531 0.9937 0.0063 0.0469 0.9406 0.9064 0.8715
MU-Net2 (Supervised Method) [58] 6.71 0.9862 0.9991 0.0009 0.0138 0.1283 0.9842 0.9823
BSUV-Net (supervised method) [50] 31.71 0.8739 0.9880 0.0120 0.1261 1.7058 0.8581 0.8551
BSUV-Net 2.0 [57] 16.57 0.8594 0.9954 0.0046 0.1406 1.1659 0.8932 0.9359
CwisarDH [6] 29.14 0.7268 0.9949 0.0051 0.2732 1.6199 0.7866 0.8786
Spectral-360 [7] 31.00 0.7238 0.9939 0.0061 0.2762 1.6337 0.7764 0.9114
DCB [32] 49.00 0.5653 0.9882 0.0118 0.4347 2.5188 0.6258 0.8502
FTSG (Flux Tensor with Split Gaussian mdoels)) [8] 23.86 0.7357 0.9960 0.0040 0.2643 1.1823 0.7768 0.9088
SC_SOBS [9] 34.00 0.6003 0.9957 0.0043 0.3997 1.9841 0.6923 0.8857
AMBER [10] 35.00 0.7071 0.9939 0.0061 0.2929 1.6264 0.7597 0.8514
CP3-online [11] 37.57 0.8229 0.9894 0.0106 0.1771 1.6974 0.7917 0.7663
Simplified Self-Organized Background Subtraction [37] 53.43 0.3005 0.9910 0.0090 0.6995 6.1421 0.4094 0.7283

Results for methods [3, 5] have been obtained by the organizing committee using authors' original code. Results for methods [1, 2, 6] have been obtained by the organizing committee using their own implementation or OpenCV. A 5x5 median filter has been applied in a post-processing step.

Metrics:

  • Average ranking across categories : (rank:Bad Weather + rank:Low Framerate + rank:Night Videos + rank:PTZ + rank:Turbulence + rank:Baseline + rank:Dynamic Background + rank:Camera Jitter + rank:Intermittent Object Motion + rank:Shadow + rank:Thermal) / 11
  • Average ranking : (rank:Recall + rank:Spec + rank:FPR + rank:FNR + rank:PWC + rank:FMeasure + rank:Precision) / 7
  • TP : True Positive
  • FP : False Positive
  • FN : False Negative
  • TN : True Negative
  • Re (Recall) : TP / (TP + FN)
  • Sp (Specificity) : TN / (TN + FP)
  • FPR (False Positive Rate) : FP / (FP + TN)
  • FNR (False Negative Rate) : FN / (TP + FN)
  • PWC (Percentage of Wrong Classifications) : 100 * (FN + FP) / (TP + FN + FP + TN)
  • F-Measure : (2 * Precision * Recall) / (Precision + Recall)
  • Precision : TP / (TP + FP)
  • FPR-S : Average False positive rate in hard shadow areas


References:

  • 1. Y. Benezeth, P.-M. Jodoin, B. Emile, H. Laurent, and C. Rosenberger. Comparative study of background subtraction algorithms.J. of Elec. Imaging, 19(3):1–12, 2010.
  • 2. A. Elgammal, D. Harwood, and L. Davis, "Non-parametric model for background subtraction," in Proc. Eur. Conf. on Computer Vision, Lect. Notes Comput. Sci. 1843, 751-767 2000.
  • 3. C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," inProc. Int. Conf. on Computer Vi-sion and Pattern Recognition, Vol. 2, IEEE, Piscataway, NJ (1999)
  • 4. Z. Zivkovic, "Improved adaptive Gaussian mixture model for back-ground subtraction," in Proc. Int. Conf. Pattern Recognition, pp. 28-31, IEEE, Piscataway, NJ 2004
  • 5. Y. Benezeth, P.-M. Jodoin, B. Emile, H. Laurent, and C. Rosenberger. Comparative study of background subtraction algorithms.J. of Elec. Imaging, 19(3):1–12, 2010.
  • 6. M. De Gregorio and M. Giordano "Change Detection with Weightless Neural Networks", in proc of IEEE Workshop on Change Detection, 2014
  • 7. M.Sedky, M.Moniri and C. C. Chibelushi "Spectral-360: A physical-based technique for change detection", in proc of IEEE Workshop on Change Detection, 2014
  • 8. R. Wang, F. Bunyak, G. Seetharaman and K. Palaniappan "Static and Moving Object Detection Using Flux Tensor with Split Gaussian Models", in proc of IEEE Workshop on Change Detection, 2014
  • 9. L. Maddalena, A. Petrosino, "The SOBS algorithm: what are the limits?", in proc of IEEE Workshop on Change Detection, CVPR 2012
  • 10. B. Wang and P. Dudek "A Fast Self-tuning Background Subtraction Algorithm", in proc of IEEE Workshop on Change Detection, 2014
  • 11. Dong Liang, Shun'ichi Kaneko, Manabu Hashimoto, Kenji Iwata, Xinyue Zhao, Co-occurrence probability-based pixel pairs background model for robust object detection in dynamic scenes, Pattern Recognition, Volume 48, Issue 4, April 2015, Pages 1374-1390.
  • 12. Xiqun Lu "A multiscale spatio-temporal background model for motion detection", ICIP 2014
  • 13. St-Charles, P.-L., Bilodeau, G.-A., Bergevin, R., "SuBSENSE : A Universal Change Detection Method with Local Adaptive Sensitivity". Accepted for IEEE Transactions on Image Processing, Nov. 2014
  • 14. L. Maddalena, A. Petrosino "A Fuzzy Spatial Coherence-based Approach to Background/ Foreground Separation for Moving Object Detection". Neural Computing and Applications, Springer London, Vol. 19, pp. 179–186, 2010
  • 15. Varadarajan, S.; Miller, P.; Huiyu Zhou, "Spatial mixture of Gaussians for dynamic background modelling," Advanced Video and Signal Based Surveillance (AVSS), 2013 10th IEEE International Conference on , pp.63,68, 27-30 Aug. 2013
  • 16. G. Ramirez-Alonso y M. Chacon-Murguia, Auto-Adaptive Parallel SOM Architecture with a modular analysis for dynamic object segmentation in videos, Neurocomputing, vol. 175, p. 990–1000. DOI:10.1016/j.neucom.2015.04.118, 2016
  • 17. Sajid, Hasan, and Sen-Ching Samson Cheung. "Background subtraction for static & moving camera." In Image Processing (ICIP), 2015 IEEE International Conference on, pp. 4530-4534. IEEE, 2015.
  • 18. Sajid, Hasan, and Sen-Ching Samson Cheung. "Universal multimode background subtraction." IEEE Transactions on Image Processing 26, no. 7 (2017): 3249-3260
  • 19. “Change detection based on graph cuts”, Alina Miron, Atta Badii, IWSSIP 2015
  • 20. G. Allebosch, F. Deboeverie, P. Veelaert, W. Philips, "EFIC: Edge based Foreground background segmentation and Interior Classification for dynamic camera viewpoints", In Advanced Concepts for Intelligent Vision Systems (ACIVS), Catania, Italy, pp. Accepted, 2015
  • 21. S. Bianco, G. Ciocca, R. Schettini, "How Far Can You Get by Combining Change Detection Algorithms?" ICIAP 2017, volume 10484 of LNCS, pp. 96-107, 2017.
  • 22. S. Bianco, G. Ciocca, R. Schettini, "How Far Can You Get by Combining Change Detection Algorithms?" ICIAP 2017, volume 10484 of LNCS, pp. 96-107, 2017.
  • 23. S. Bianco, G. Ciocca and R. Schettini, "Combination of Video Change Detection Algorithms by Genetic Programming," in IEEE Transactions on Evolutionary Computation, vol. 21, no. 6, pp. 914-928, 2017.
  • 24. Allebosch G., Van Hamme D., Deboeverie F., Veelaert P., Philips W. (2016) C-EFIC: Color and Edge Based Foreground Background Segmentation with Interior Classification. In: Braz J. et al. (eds) Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2015. Communications in Computer and Information Science, vol 598. Springer
  • 25. P.-L. St-Charles, G.-A. Bilodeau, R. Bergevin, "A Self-Adjusting Approach to Change Detection Based on Background Word Consensus" in IEEE Winter Conference on Applications of Computer Vision (WACV). Big Island, Hawaii, USA, Jan. 6-9, 2015.
  • 26. M. De Gregorio and M. Giordano, "WiSARDRP for change detection in video sequences", 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 26-28 April 2017, Bruges, Belgium, pp. 453--458.
  • 27. S. Bianco, G. Ciocca and R. Schettini, "Combination of Video Change Detection Algorithms by Genetic Programming," in IEEE Transactions on Evolutionary Computation, vol. 21, no. 6, pp. 914-928, 2017.
  • 28. Yingying Chen; Jinqiao Wang; Hanqing Lu, "Learning sharable models for robust background subtraction," in Multimedia and Expo (ICME), 2015 IEEE International Conference on, pp.1-6, 2015
  • 29. Wang Y., Luo Z. M., and Jodoin P. M. “Interactive Deep Learning Method for Segmenting Moving Objects”, Pattern Recognition Letters, 2016.
  • 30. Kunfeng Wang, Chao Gou, and Fei-Yue Wang. M4CD: A Robust Change Detection Method for Intelligent Visual Surveillance. arXiv:1802.04979, 2018.
  • 31. Varghese, Arun, and G. Sreelekha. "Sample-based integrated background subtraction and shadow detection." IPSJ Transactions on Computer Vision and Applications 9.1 (2017): 25. (https://doi.org/10.1186/s41074-017-0036-1)
  • 32. Rawitas Krungkaew, Worapan Kusakunniran "Foreground segmentation in a video by using a novel dynamic codebook", 13th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), 2016
  • 33. Jiang S, Lu X. WeSamBE: A Weight-Sample-Based Method for Background Subtraction[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017. (DOI: 10.1109/TCSVT.2017.2711659)
  • 34. Babaee, Mohammadreza, Duc Tung Dinh, and Gerhard Rigoll. "A Deep Convolutional Neural Network for Video Sequence Background Subtraction." Pattern Recognition (2017)
  • 35. Martins, I., Carvalho, P., Corte-Real, L., Alba-Castro, J.L. (2017) "BMOG: Boosted Gaussian Mixture Model with Controlled Complexity", accepted at IbPRIA 2017, to be published in Pattern Recognition and Image Analysis. IbPRIA 2017. LNCS, Springer
  • 36. I. Martins, P. Carvalho, L. Corte-Real, and J. L. Alba-Castro Texture collinearity foreground segmentation for night videos Computer Vision and Image Understanding, 200:103032, Nov. 2020.
  • 37. Kamal Sehairi, Fatima Chouireb, Jean Meunier, “Comparative study of motion detection methods for video surveillance systems,” J. Electron. Imaging 26(2), 023025 (2017), doi: 10.1117/1.JEI.26.2.023025
  • 38. M. Braham, S. Piérard and M. Van Droogenbroeck, "Semantic Background Subtraction". In IEEE International Conference on Image Processing (ICIP), September 2017.
  • 39. Long Ang, L., & Hacer, Y. K. (2018). Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding. arXiv preprint arXiv:1801.02225.
  • 40. Wenbo Zheng, Kunfeng Wang, Fei-Yue Wang. "Background Subtraction Algorithm Based on Bayesian Generative Adversarial Networks". Acta Automatica Sinica, under review.
  • 41. Wenbo Zheng, Kunfeng Wang, Fei-Yue Wang. "A Novel Background Subtraction Algorithm Based on Parallel Vision and Bayesian GANs".Neurocomputing, to be submitted.
  • 42. https://arxiv.org/ftp/arxiv/papers/1805/1805.09277.pdf
  • 43. Işık, Şahin, Kemal Özkan, Serkan Günal, and Ömer Nezih Gerek. "SWCD: a sliding window and self-regulated learning-based background updating method for change detection in videos." Journal of Electronic Imaging 27, no. 2 (2018): 023002.
  • 44. Lim, Long Ang, and Hacer Yalim Keles. "Foreground Segmentation Using Convolutional Neural Networks for Multiscale Feature Encoding." Pattern Recognition Letters (2018).
  • 45. Lim, Long Ang, and Hacer Yalim Keles. "Learning Multi-scale Features for Foreground Segmentation." arXiv preprint arXiv:1808.01477 (2018)
  • 46. Ezequiel López-Rubio, Miguel A. Molina-Cabello, Rafael Marcos Luque Baena, Enrique Domínguez. Foreground Detection by Competitive Learning for Varying Input Distributions. International Journal of Neural Systems 28(5): 1-16 (2018)
  • 47. Işık, Ş., Özkan, K., & Gerek, Ö. N. "CVABS: Moving object segmentation with common vector approach for videos", will be submitted.
  • 48. V. Mondéjar-Guerra, J.Rouco, J. Novo, M. Ortega. "An end-to-end deep learning approach for simultaneous background modeling and subtraction". In British Machine Vision Conference 2019
  • 49. F. Gao, Y. Li and S. Lu, "Extracting moving objects more accurately: a CDA contour optimizer," in IEEE Transactions on Circuits and Systems for Video Technology. doi: 10.1109/TCSVT.2021.3055539
  • 50. M. O. Tezcan, P. Ishwar and J. Konrad. "BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos." arXiv preprint arXiv:1907.11371 (2019).
  • 51. M. O. Tezcan, P. Ishwar and J. Konrad. "BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos." arXiv preprint arXiv:1907.11371 (2019).
  • 52. Anthony Cioppa, Marc Van Droogenbroeck, Marc Braham "Real-Time Semantic Background Subtraction". arXiv preprint, 2020. Submitted to ICIP 2020.
  • 53. Anthony Cioppa, Marc Van Droogenbroeck, Marc Braham "Real-Time Semantic Background Subtraction". arXiv preprint, 2020. Submitted to ICIP 2020.
  • 54. F. Gao, Y. Li and S. Lu, "Extracting moving objects more accurately: a CDA contour optimizer," in IEEE Transactions on Circuits and Systems for Video Technology. doi: 10.1109/TCSVT.2021.3055539
  • 55. G. Rahmon, F. Bunyak, G. Seetharaman and K. Palaniappan, "Motion U-Net: Multi-cue Encoder-Decoder Network for Motion Segmentation,” Proceedings of the 25th International Conference on Pattern Recognition, 2020
  • 56. M. O. Tezcan, P. Ishwar and J. Konrad, "BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtraction," in IEEE Access, vol. 9, pp. 53849-53860, 2021, doi: 10.1109/ACCESS.2021.3071163.
  • 57. M. O. Tezcan, P. Ishwar and J. Konrad, "BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtraction," in IEEE Access, vol. 9, pp. 53849-53860, 2021, doi: 10.1109/ACCESS.2021.3071163.
  • 58. G. Rahmon, F. Bunyak, G. Seetharaman and K. Palaniappan, "Motion U-Net: Multi-cue Encoder-Decoder Network for Motion Segmentation,” Proceedings of the 25th International Conference on Pattern Recognition, 2020