Evaluation Result
You can see the detailed evaluation (in .json file) by clicking the title of algorithm. In the ".json" file file, total, type I,II,III are error rate, the successful rate are 1- error rate.| Algorithm | Avg. Rank |
target type | target size | movement | oclussion | motion type | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| human | animal | rigid | large | small | slow | fast | yes | no | passive | active | ||
| 3D-T[1] | 8 | 81.4(1) | 64.2(13) | 73.3(16) | 79.9(1) | 71.2(10) | 75.1(15) | 74.9(4) | 72.5(1) | 78.3(13) | 79.0(10) | 73.5(4) |
| ASKCF-OHT[2] | 18.73 | 51.7(19) | 49.8(22) | 72.2(18) | 58.7(18) | 59.0(18) | 67.1(19) | 55.6(17) | 52.1(18) | 68.1(21) | 71.9(18) | 54.0(18) |
| BBT[3] | 17.55 | 52.0(18) | 55.3(19) | 69.4(19) | 57.7(19) | 60.1(17) | 77.1(9) | 51.9(19) | 51.9(19) | 68.9(18) | 70.4(19) | 54.8(17) |
| CSR-rgbd++[4] | 7.45 | 76.6(5) | 65.2(9) | 75.9(12) | 75.4(7) | 73.0(7) | 79.6(5) | 71.8(7) | 70.1(5) | 79.4(10) | 79.1(9) | 72.1(6) |
| CT[5] | 34.09 | 31.1(34) | 46.7(30) | 36.9(37) | 39.0(32) | 34.4(36) | 48.6(34) | 31.5(35) | 23.3(38) | 54.3(30) | 42.1(35) | 34.2(34) |
| DCADCF_colornamejet[6] | 24.55 | 57.0(16) | 43.9(31) | 53.1(32) | 55.0(21) | 51.3(26) | 55.8(29) | 51.8(20) | 50.8(20) | 55.8(29) | 58.0(26) | 51.0(20) |
| DCADCF_fhog_concat[7] | 25.82 | 49.7(21) | 48.1(27) | 53.9(29) | 51.0(25) | 50.9(27) | 51.9(31) | 50.5(23) | 48.8(21) | 53.8(31) | 58.8(24) | 47.9(25) |
| DM-DCF[8] | 10.45 | 76.0(6) | 58.0(18) | 76.7(10) | 72.4(12) | 72.8(9) | 75.2(14) | 71.6(8) | 69.1(6) | 77.5(15) | 82.5(6) | 68.9(11) |
| DS-KCF[9] | 12.82 | 67.0(11) | 61.2(15) | 76.4(11) | 68.8(14) | 69.7(13) | 75.4(13) | 66.9(13) | 63.3(12) | 77.6(14) | 78.8(11) | 65.7(14) |
| DSKCF-CPP[10] | 12.91 | 64.5(13) | 64.3(12) | 74.3(14) | 66.3(15) | 69.4(15) | 76.5(10) | 64.7(15) | 60.1(14) | 79.0(11) | 79.6(8) | 63.7(15) |
| DSKCF_SHAPE[11] | 10.36 | 70.9(8) | 70.8(6) | 73.6(15) | 73.9(8) | 70.3(11) | 76.2(12) | 70.1(11) | 64.9(10) | 81.4(9) | 77.4(14) | 69.8(10) |
| Depth-CCF[12] | 8.18 | 69.7(10) | 64.5(11) | 81.4(3) | 73.1(9) | 72.9(8) | 78.4(8) | 70.8(10) | 65.2(9) | 83.7(8) | 84.4(2) | 68.7(12) |
| Dhog[13f] | 27.27 | 43.3(26) | 48.3(26) | 55.9(24) | 47.2(28) | 50.3(28) | 52.7(30) | 47.5(26) | 38.4(28) | 63.5(25) | 54.3(32) | 46.9(27) |
| ECO_TA[14] | 5.55 | 76.9(4) | 64.7(10) | 79.5(6) | 77.2(4) | 74.0(5) | 78.5(7) | 74.1(5) | 68.3(8) | 85.1(4) | 83.6(3) | 72.3(5) |
| ExampleResult2017-03-051488720222[15] | 33.64 | 32.9(32) | 36.3(35) | 45.2(33) | 33.8(35) | 41.4(33) | 45.8(36) | 35.1(33) | 34.1(31) | 43.7(35) | 47.4(34) | 34.6(33) |
| KCF[16] | 23.73 | 41.8(27) | 50.4(21) | 64.9(21) | 48.4(26) | 54.7(22) | 65.0(21) | 46.9(27) | 40.6(26) | 67.7(22) | 64.5(22) | 47.3(26) |
| KCFmatlab[17] | 26.82 | 39.7(29) | 49.4(24) | 54.6(27) | 40.1(31) | 52.5(23) | 57.8(24) | 42.9(29) | 35.2(29) | 63.6(24) | 56.4(27) | 43.7(28) |
| LDPSTRUCK[18] | 24.09 | 46.2(24) | 59.1(16) | 54.5(28) | 51.6(24) | 52.0(25) | 56.2(28) | 50.1(24) | 39.8(27) | 68.4(19) | 56.4(28) | 50.1(22) |
| LDP_SVT[19] | 22.82 | 46.8(23) | 58.8(17) | 55.8(25) | 52.9(22) | 52.3(24) | 56.3(27) | 51.1(22) | 41.0(25) | 68.4(20) | 58.2(25) | 50.4(21) |
| MIL[20] | 35.27 | 32.2(33) | 37.2(34) | 38.3(36) | 36.6(34) | 34.6(35) | 45.5(37) | 31.5(36) | 25.6(36) | 49.0(33) | 40.4(38) | 33.6(36) |
| OAPF[21] | 8.45 | 64.2(14) | 84.8(3) | 77.2(9) | 72.7(11) | 73.4(6) | 85.1(2) | 68.4(12) | 64.4(11) | 85.1(5) | 77.7(13) | 71.4(7) |
| OF[13g] | 39 | 17.9(39) | 11.4(39) | 23.4(39) | 20.1(39) | 17.5(39) | 18.1(39) | 18.8(39) | 15.9(39) | 22.3(39) | 23.4(39) | 16.8(39) |
| OTR[22] | 3.91 | 77.3(3) | 68.3(7) | 81.3(4) | 76.5(5) | 77.3(3) | 81.2(4) | 75.3(3) | 71.3(4) | 84.7(6) | 85.1(1) | 73.9(3) |
| PCdet[13i] | 26.36 | 40.6(28) | 42.1(32) | 61.7(23) | 55.4(20) | 43.6(32) | 58.5(22) | 44.8(28) | 46.3(23) | 52.0(32) | 64.9(21) | 42.6(29) |
| PCdet_flow[13h] | 18.27 | 50.5(20) | 51.6(20) | 72.7(17) | 63.4(16) | 55.5(20) | 73.9(16) | 53.0(18) | 55.0(16) | 64.4(23) | 75.5(16) | 52.7(19) |
| PCflow[13j] | 34.36 | 35.2(31) | 29.1(38) | 43.6(35) | 42.2(30) | 33.2(37) | 47.2(35) | 33.1(34) | 32.4(33) | 43.5(36) | 41.3(37) | 35.5(32) |
| RGB[13e] | 32.36 | 26.7(37) | 40.9(33) | 54.7(26) | 31.9(37) | 46.0(30) | 50.5(33) | 35.7(32) | 34.8(30) | 46.8(34) | 56.2(29) | 33.7(35) |
| RGBD+OF[13c] | 13.91 | 63.9(15) | 65.3(8) | 74.5(13) | 71.5(13) | 65.5(16) | 73.4(17) | 65.9(14) | 60.1(15) | 79.0(12) | 74.0(17) | 65.8(13) |
| RGBDOcc+OF[13a] | 8.64 | 74.0(7) | 62.6(14) | 78.4(7) | 78.1(2) | 69.7(14) | 76.3(11) | 72.2(6) | 72.0(2) | 75.2(16) | 82.3(7) | 70.0(9) |
| RGBOF[13d] | 23.73 | 47.1(22) | 47.0(28) | 63.6(22) | 47.4(27) | 57.5(19) | 56.7(26) | 51.8(21) | 46.9(22) | 61.9(28) | 63.4(23) | 49.3(23) |
| SAMF+Depth[23] | 22 | 44.8(25) | 49.6(23) | 67.0(20) | 52.4(23) | 55.2(21) | 65.2(20) | 49.5(25) | 41.1(24) | 71.6(17) | 66.3(20) | 49.3(24) |
| SemiB[24] | 37.64 | 22.5(38) | 33.0(37) | 32.7(38) | 24.0(38) | 31.6(38) | 38.2(38) | 24.4(38) | 25.1(37) | 32.7(38) | 41.9(36) | 23.2(38) |
| Struck[25] | 29.45 | 35.4(30) | 47.0(29) | 53.4(31) | 45.0(29) | 43.9(31) | 58.0(23) | 39.0(30) | 30.4(34) | 63.5(26) | 54.4(31) | 40.6(30) |
| TLD[26] | 34.91 | 29.0(36) | 35.1(36) | 44.4(34) | 32.5(36) | 38.5(34) | 51.6(32) | 29.7(37) | 33.8(32) | 38.7(37) | 50.2(33) | 30.5(37) |
| TSDM2019-12-221577069806[27] | 3.09 | 70.6(9) | 85.0(2) | 86.1(1) | 77.3(3) | 80.6(2) | 86.8(1) | 76.2(2) | 68.5(7) | 93.9(1) | 83.6(4) | 77.5(2) |
| VTD[28] | 30.09 | 30.9(35) | 48.8(25) | 53.9(30) | 38.6(33) | 46.2(29) | 57.3(25) | 37.2(31) | 28.3(35) | 63.1(27) | 54.9(30) | 38.5(31) |
| ca3dms+toh[29] | 6.91 | 66.3(12) | 74.3(4) | 82.0(2) | 73.0(10) | 74.2(4) | 79.6(6) | 71.4(9) | 63.2(13) | 88.1(3) | 82.8(5) | 70.3(8) |
| hiob_lc2[30] | 13.45 | 53.1(17) | 72.5(5) | 78.2(8) | 60.9(17) | 70.3(12) | 72.4(18) | 63.8(16) | 52.9(17) | 84.5(7) | 77.4(15) | 62.0(16) |
| zoom2track[31] | 3.36 | 78.0(2) | 85.8(1) | 81.0(5) | 76.4(6) | 83.9(1) | 82.8(3) | 79.8(1) | 71.8(3) | 92.9(2) | 78.3(12) | 81.5(1) |
References
| [1] | Adel Bibi, Tianzhu Zhang, and Bernard Ghanem, 3D Part-Based Sparse Tracker with Automatic Synchronization and Registration Conference on Computer Vision and Pattern Recognition (CVPR2016) |
| [2] | J.T. Pi and K.L. Hu, |
| [3] | Shaul Oron and Denis Suhanov and Shai Avidan, Best Buddies Tracking Arxiv |
| [4] | Ugur Kart, Joni-Kristian Kamarainen, Jiri Matas, How to Make an RGBD Tracker? ECCV VOT Workshop 2018 |
| [5] | K. Zhang, L. Zhang, and M.-H. Yang, Real-time compressive tracking. ECCV, 2012 |
| [6] | John Stynsberg, Masters Thesis |
| [7] | John Stynsberg, Masters Thesis |
| [8] | Ugur Kart, Joni-Kristian Kamarainen, Jiri Matas, Lixin Fan, Francesco Cricri, Depth Masked Discriminative Correlation Filter ICPR 2018 |
| [9] | M. Camplani, S. Hannuna, M. Mirmehdi, D. Damen, A. Paiement, L. Tao, T. Burghardt, Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling. BMVC 2015 |
| [10] | S. Hannuna, M. Camplani, J. Hall, M. Mirmehdi, D. Damen, T. Burghardt, A. Paiement, L. Tao, DS-KCF: A real-time tracker for RGB-D data Journal of Real-Time Image Processing |
| [11] | S. Hannuna, M. Camplani, J. Hall, M. Mirmehdi, D. Damen, T. Burghardt, A. Paiement, L. Tao, DS-KCF: A real-time tracker for RGB-D data Journal of Real-Time Image Processing |
| [12] | Guanqun Li, Depth information aided constrained correlation filter for visual tracking IOP Conference Series Earth and Environmental Science 234:012005 · March 2019 |
| [13] | S. Song and J. Xiao, Tracking Revisited using RGBD Camera: Baseline and Benchmark, |
| 13a. RGBD HoG detection+ optical flow + Occlusion handle. | |
| 13c. RGBD HoG detection+ optical flow. | |
| 13d. RGBD HoG detection. | |
| 13e. RGB HoG detection. | |
| 13f. D HoG detection. | |
| 13g. Optical flow. | |
| 13h. Point Cloud (detection+ flow). | |
| 13i. Point Cloud detection. | |
| 13j. Point Cloud flow. | |
| [14] | Yangliu Kuai, Gongjian Wen, Dongdong Li and Jingjing Xiao, Target-Aware Correlation Filter Tracking in RGBD Videos |
| [15] | Anonymous, |
| [16] | Test run by Massimo Camplani, authors are: J. F. Henriques, R. Caseiro, P. Martins, J. Batista, High-Speed Tracking with Kernelized Correlation Filters TPAMI 2015 |
| [17] | Submitted by Srishti Yadav (tested on MATLAB). Originally by: Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2014), High-Speed Tracking withKernelized Correlation Filters IEEE transactions on pattern analysis and machine intelligence |
| [18] | Awwad Sari, Fairouz Hussein, and Massimo Piccardi, Local Depth Patterns for Tracking in Depth Videos Proceedings of the 23rd Annual ACM Conference on Multimedia Conference. ACM, 2015 |
| [19] | Sari Awwad and Massimo Piccardi, Prototype-based budget maintenance for tracking in depth videos Multimedia Tools and Applications Journal (2016) |
| [20] | B. Babenko, M.-H. Yang, and S. Belongie, Visual Tracking with Online Multiple Instance Learning CVPR, 2009 |
| [21] | K. Meshgi, S. Maeda, S. Oba, H. Skibbe, Y. Li, and S. Ishii, Occlusion aware particle filter tracker to handle complex and persistent occlusions CVIU, 2015 |
| [22] | Ugur Kart, Alan Lukezic, Matej Kristan, Joni-Kristian Kamarainen, Jiri Matas, Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters CVPR 2019 |
| [23] | Yang Li and Jianke Zhu, A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration ECCV 2014 Workshop |
| [24] | H. Grabner, C. Leistner, and H. Bischof, Semi-supervised on-line boosting for robust tracking ECCV, 2008 |
| [25] | S. Hare, A. Saffari, and P. H. S. Torr., Struck: Structured output tracking with kernels. In ICCV, 2011. |
| [26] | Z. Kalal, K. Mikolajczyk, and J. Matas, Tracking-learning detection PAMI, 2012. |
| [27] | Pengyao Zhao, not yet published |
| [28] | J. Kwon and K. M. Lee, Visual tracking decomposition CVPR, 2010. |
| [29] | Ye Liu et al, Context-aware 3-D Mean-shift with Occlusion Handling for Robust Object Tracking in RGB-D Videos IEEE Trans. on Multimedia |
| [30] | Peer Springstübe, diploma thesis, tba none, diploma thesis |
| [31] | Anonymous, |