Advertisement

TAO: A Large-Scale Benchmark for Tracking Any Object

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12350)

Abstract

For many years, multi-object tracking benchmarks have focused on a handful of categories. Motivated primarily by surveillance and self-driving applications, these datasets provide tracks for people, vehicles, and animals, ignoring the vast majority of objects in the world. By contrast, in the related field of object detection, the introduction of large-scale, diverse datasets (e.g., COCO) have fostered significant progress in developing highly robust solutions. To bridge this gap, we introduce a similarly diverse dataset for Tracking Any Object (TAO) (http://taodataset.org/). It consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. Importantly, we adopt a bottom-up approach for discovering a large vocabulary of 833 categories, an order of magnitude more than prior tracking benchmarks. To this end, we ask annotators to label objects that move at any point in the video, and give names to them post factum. Our vocabulary is both significantly larger and qualitatively different from existing tracking datasets. To ensure scalability of annotation, we employ a federated approach that focuses manual effort on labeling tracks for those relevant objects in a video (e.g., those that move). We perform an extensive evaluation of state-of-the-art trackers and make a number of important discoveries regarding large-vocabulary tracking in an open-world. In particular, we show that existing single- and multi-object trackers struggle when applied to this scenario in the wild, and that detection-based, multi-object trackers are in fact competitive with user-initialized ones. We hope that our dataset and analysis will boost further progress in the tracking community.

Keywords

Datasets Video object detection Tracking 

Notes

Acknowledgements

We thank Jonathon Luiten and Ross Girshick for detailed feedback, and Nadine Chang and Kenneth Marino for reviewing early drafts. Annotations for this dataset were provided by Scale.ai. This work was supported in part by the CMU Argo AI Center for Autonomous Vehicle Research, the Inria associate team GAYA, and by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/Interior Business Center (DOI/IBC) contract number D17PC00345. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes not withstanding any copyright annotation theron. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied of IARPA, DOI/IBC or the U.S. Government.

Supplementary material

504441_1_En_26_MOESM1_ESM.pdf (2 mb)
Supplementary material 1 (pdf 2018 KB)

References

  1. 1.
    Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces. In: CVPR (2016)Google Scholar
  2. 2.
    Barriuso, A., Torralba, A.: Notes on image annotation. arXiv preprint arXiv:1210.3448 (2012)
  3. 3.
    Berclaz, J., Fleuret, F., Fua, P.: Robust people tracking with global trajectory optimization. In: CVPR (2006)Google Scholar
  4. 4.
    Berclaz, J., Fleuret, F., Turetken, E., Fua, P.: Multiple object tracking using k-shortest paths optimization. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1806–1819 (2011)CrossRefGoogle Scholar
  5. 5.
    Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: ICCV (2019)Google Scholar
  6. 6.
    Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. J. Image Video Process. 2008, 1 (2008).  https://doi.org/10.1155/2008/246309CrossRefGoogle Scholar
  7. 7.
    Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850–865. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_56CrossRefGoogle Scholar
  8. 8.
    Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: ICIP (2016)Google Scholar
  9. 9.
    Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: CVPR (2019)Google Scholar
  10. 10.
    Breitenstein, M.D., Reichlin, F., Leibe, B., Koller-Meier, E., Van Gool, L.: Robust tracking-by-detection using a detector confidence particle filter. In: ICCV (2009)Google Scholar
  11. 11.
    Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., Shah, R.: Signature verification using a “siamese” time delay neural network. In: NIPS (1994)Google Scholar
  12. 12.
    Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taixé, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR (2017)Google Scholar
  13. 13.
    Caelles, S., Pont-Tuset, J., Perazzi, F., Montes, A., Maninis, K.K., Van Gool, L.: The 2019 DAVIS challenge on VOS: unsupervised multi-object segmentation. arXiv preprint arXiv:1905.00737 (2019)
  14. 14.
    Chang, M.F., et al.: Argoverse: 3D tracking and forecasting with rich maps. In: CVPR (2019)Google Scholar
  15. 15.
    Chen, B., Wang, D., Li, P., Wang, S., Lu, H.: Real-time ‘actor-critic’ tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 328–345. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01234-2_20CrossRefGoogle Scholar
  16. 16.
    Choi, W., Savarese, S.: Multiple target tracking in world coordinate with single, minimally calibrated camera. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 553–567. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15561-1_40CrossRefGoogle Scholar
  17. 17.
    Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ATOM: accurate tracking by overlap maximization. In: CVPR (2019)Google Scholar
  18. 18.
    Danelljan, M., Bhat, G., Shahbaz Khan, F., Felsberg, M.: ECO: efficient convolution operators for tracking. In: CVPR (2017)Google Scholar
  19. 19.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)Google Scholar
  20. 20.
    Ess, A., Leibe, B., Schindler, K., Van Gool, L.: A mobile vision system for robust multi-person tracking. In: CVPR (2008)Google Scholar
  21. 21.
    Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: CVPR (2019)Google Scholar
  22. 22.
    Feichtenhofer, C., Pinz, A., Zisserman, A.: Detect to track and track to detect. In: ICCV (2017)Google Scholar
  23. 23.
    Fisher, R., Santos-Victor, J., Crowley, J.: Context aware vision using image-based active recognition. EC’s Information Society Technology’s Programme Project IST2001-3754 (2001)Google Scholar
  24. 24.
    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)Google Scholar
  25. 25.
    Gkioxari, G., Malik, J.: Finding action tubes. In: CVPR (2015)Google Scholar
  26. 26.
    Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2018)Google Scholar
  27. 27.
    Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)Google Scholar
  28. 28.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)Google Scholar
  29. 29.
    Held, D., Thrun, S., Savarese, S.: Learning to track at 100 FPS with deep regression networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 749–765. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_45CrossRefGoogle Scholar
  30. 30.
    Huang, L., Zhao, X., Huang, K.: GOT-10k: a large high-diversity benchmark for generic object tracking in the wild. arXiv preprint arXiv:1810.11981 (2018)
  31. 31.
    Jiang, H., Fels, S., Little, J.J.: A linear programming approach for multiple object tracking. In: CVPR (2007)Google Scholar
  32. 32.
    Kang, K., et al.: Object detection in videos with tubelet proposal networks. In: CVPR (2017)Google Scholar
  33. 33.
    Khoreva, A., Benenson, R., Ilg, E., Brox, T., Schiele, B.: Lucid data dreaming for video object segmentation. Int. J. Comput. Vis. 127(9), 1175–1197 (2019).  https://doi.org/10.1007/s11263-019-01164-6CrossRefGoogle Scholar
  34. 34.
    Kristan, M., et al.: A novel performance evaluation methodology for single-target trackers. TPAMI 38(11), 2137–2155 (2016)CrossRefGoogle Scholar
  35. 35.
    Leal-Taixé, L., Fenzi, M., Kuznetsova, A., Rosenhahn, B., Savarese, S.: Learning an image-based motion context for multiple people tracking. In: CVPR (2014)Google Scholar
  36. 36.
    Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: SiamRPN++: evolution of siamese visual tracking with very deep networks. In: CVPR (2019)Google Scholar
  37. 37.
    Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: CVPR (2018)Google Scholar
  38. 38.
    Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10602-1_48CrossRefGoogle Scholar
  39. 39.
    Lokoč, J., Kovalčík, G., Souček, T., Moravec, J., Čech, P.: A framework for effective known-item search in video. In: ACMM (2019).  https://doi.org/10.1145/3343031.3351046
  40. 40.
    Milan, A., Leal-Taixé, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)
  41. 41.
    Milan, A., Rezatofighi, S.H., Dick, A., Reid, I., Schindler, K.: Online multi-target tracking using recurrent neural networks. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar
  42. 42.
    Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1187–1200 (2013)CrossRefGoogle Scholar
  43. 43.
    Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: CVPR (2016)Google Scholar
  44. 44.
    Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR (2011)Google Scholar
  45. 45.
    Ren, L., Lu, J., Wang, Z., Tian, Q., Zhou, J.: Collaborative deep reinforcement learning for multi-object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 605–621. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_36CrossRefGoogle Scholar
  46. 46.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)Google Scholar
  47. 47.
    Ristani, E., Tomasi, C.: Features for multi-target multi-camera tracking and re-identification. In: CVPR (2018)Google Scholar
  48. 48.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015).  https://doi.org/10.1007/s11263-015-0816-yMathSciNetCrossRefGoogle Scholar
  49. 49.
    Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: LabelMe: a database and web-based tool for image annotation. Int. J. Comput. Vis. 77(1–3), 157–173 (2008).  https://doi.org/10.1007/s11263-007-0090-8CrossRefGoogle Scholar
  50. 50.
    Scovanner, P., Tappen, M.F.: Learning pedestrian dynamics from the real world. In: ICCV (2009)Google Scholar
  51. 51.
    Shang, X., Di, D., Xiao, J., Cao, Y., Yang, X., Chua, T.S.: Annotating objects and relations in user-generated videos. In: ICMR (2019)Google Scholar
  52. 52.
    Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510–526. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_31CrossRefGoogle Scholar
  53. 53.
    Tao, R., Gavves, E., Smeulders, A.W.: Siamese instance search for tracking. In: CVPR (2016)Google Scholar
  54. 54.
    Thomee, B., et al.: YFCC100M: the new data in multimedia research. arXiv preprint arXiv:1503.01817 (2015)
  55. 55.
    Valmadre, J., et al.: Long-term tracking in the wild: a benchmark. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 692–707. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_41CrossRefGoogle Scholar
  56. 56.
    Voigtlaender, P., et al.: MOTS: multi-object tracking and segmentation. In: CPVR (2019)Google Scholar
  57. 57.
    Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. In: BMVC (2017)Google Scholar
  58. 58.
    Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: CVPR (2019)Google Scholar
  59. 59.
    Wang, W., et al.: Learning unsupervised video object segmentation through visual attention. In: CVPR (2019)Google Scholar
  60. 60.
    Wen, L., et al.: UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. arXiv preprint arXiv:1511.04136 (2015)
  61. 61.
    Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR (2013)Google Scholar
  62. 62.
    Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https://github.com/facebookresearch/detectron2
  63. 63.
    Xiao, F., Lee, Y.J.: Video object detection with an aligned spatial-temporal memory. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 494–510. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01237-3_30CrossRefGoogle Scholar
  64. 64.
    Xu, N., et al.: YouTube-VOS: a large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)
  65. 65.
    Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: ICCV (2019)Google Scholar
  66. 66.
    Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: CVPR, June 2020Google Scholar
  67. 67.
    Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: CVPR (2008)Google Scholar
  68. 68.
    Zhao, H., Torralba, A., Torresani, L., Yan, Z.: HACS: human action clips and segments dataset for recognition and temporal localization. In: ICCV (2019)Google Scholar
  69. 69.
    Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR (2017)Google Scholar
  70. 70.
    Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 408–417 (2017)Google Scholar
  71. 71.
    Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware siamese networks for visual object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 103–119. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01240-3_7CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Carnegie Mellon UniversityPittsburghUSA
  2. 2.InriaMontbonnotFrance
  3. 3.Argo AIPittsburghUSA

Personalised recommendations