Advertisement

VisDrone-SOT2018: The Vision Meets Drone Single-Object Tracking Challenge Results

  • Longyin Wen
  • Pengfei ZhuEmail author
  • Dawei Du
  • Xiao Bian
  • Haibin Ling
  • Qinghua Hu
  • Chenfeng Liu
  • Hao Cheng
  • Xiaoyu Liu
  • Wenya Ma
  • Qinqin Nie
  • Haotian Wu
  • Lianjie Wang
  • Asanka G. Perera
  • Baochang Zhang
  • Byeongho Heo
  • Chunlei Liu
  • Dongdong Li
  • Emmanouil Michail
  • Hanlin Chen
  • Hao Liu
  • Haojie Li
  • Ioannis Kompatsiaris
  • Jian Cheng
  • Jiaqing Fan
  • Jie Zhang
  • Jin Young Choi
  • Jing Li
  • Jinyu Yang
  • Jongwon Choi
  • Juanping Zhao
  • Jungong Han
  • Kaihua Zhang
  • Kaiwen Duan
  • Ke Song
  • Konstantinos Avgerinakis
  • Kyuewang Lee
  • Lu Ding
  • Martin Lauer
  • Panagiotis Giannakeris
  • Peizhen Zhang
  • Qiang Wang
  • Qianqian Xu
  • Qingming Huang
  • Qingshan Liu
  • Robert Laganière
  • Ruixin Zhang
  • Sangdoo Yun
  • Shengyin Zhu
  • Sihang Wu
  • Stefanos Vrochidis
  • Wei Tian
  • Wei Zhang
  • Weidong Chen
  • Weiming Hu
  • Wenhao Wang
  • Wenhua Zhang
  • Wenrui Ding
  • Xiaohao He
  • Xiaotong Li
  • Xin Zhang
  • Xinbin Luo
  • Xixi Hu
  • Yang Meng
  • Yangliu Kuai
  • Yanyun Zhao
  • Yaxuan Li
  • Yifan Yang
  • Yifan Zhang
  • Yong Wang
  • Yuankai Qi
  • Zhipeng Deng
  • Zhiqun He
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11133)

Abstract

Single-object tracking, also known as visual tracking, on the drone platform attracts much attention recently with various applications in computer vision, such as filming and surveillance. However, the lack of commonly accepted annotated datasets and standard evaluation platform prevent the developments of algorithms. To address this issue, the Vision Meets Drone Single-Object Tracking (VisDrone-SOT2018) Challenge workshop was organized in conjunction with the 15th European Conference on Computer Vision (ECCV 2018) to track and advance the technologies in such field. Specifically, we collect a dataset, including 132 video sequences divided into three non-overlapping sets, i.e., training (86 sequences with 69, 941 frames), validation (11 sequences with 7, 046 frames), and testing (35 sequences with 29, 367 frames) sets. We provide fully annotated bounding boxes of the targets as well as several useful attributes, e.g., occlusion, background clutter, and camera motion. The tracking targets in these sequences include pedestrians, cars, buses, and animals. The dataset is extremely challenging due to various factors, such as occlusion, large scale, pose variation, and fast motion. We present the evaluation protocol of the VisDrone-SOT2018 challenge and the results of a comparison of 22 trackers on the benchmark dataset, which are publicly available on the challenge website: http://www.aiskyeye.com/. We hope this challenge largely boosts the research and development in single object tracking on drone platforms.

Keywords

Performance evaluation Drone Single-object tracking 

Notes

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China under Grant 61502332 and Grant 61732011, in part by Natural Science Foundation of Tianjin under Grant 17JCZDJC30800, in part by US National Science Foundation under Grant IIS-1407156 and Grant IIS-1350521, in part by Beijing Seetatech Technology Co., Ltd and GE Global Research.

References

  1. 1.
    Beauchemin, S.S., Barron, J.L.: The computation of optical flow. ACM Comput. Surv. 27(3), 433–467 (1995)CrossRefGoogle Scholar
  2. 2.
    Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.H.S.: Staple: complementary learners for real-time tracking. In: CVPR, pp. 1401–1409 (2016)Google Scholar
  3. 3.
    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
  4. 4.
    Cai, Z., Wen, L., Lei, Z., Vasconcelos, N., Li, S.Z.: Robust deformable and occluded object tracking with dynamic graph. TIP 23(12), 5497–5509 (2014)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. In: BMVC (2014)Google Scholar
  6. 6.
    Choi, J., et al.: Context-aware deep feature compression for high-speed visual tracking. In: CVPR (2018)Google Scholar
  7. 7.
    Choi, J., Chang, H.J., Jeong, J., Demiris, Y., Choi, J.Y.: Visual tracking using attention-modulated disintegration and integration. In: CVPR, pp. 4321–4330 (2016)Google Scholar
  8. 8.
    Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS, pp. 379–387 (2016)Google Scholar
  9. 9.
    Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ECO: efficient convolution operators for tracking. In: CVPR, pp. 6931–6939 (2017)Google Scholar
  10. 10.
    Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: BMVC (2014)Google Scholar
  11. 11.
    Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: ICCV, pp. 4310–4318 (2015)Google Scholar
  12. 12.
    Danelljan, M., Khan, F.S., Felsberg, M., van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR, pp. 1090–1097 (2014)Google Scholar
  13. 13.
    Danelljan, M., Robinson, A., Shahbaz Khan, F., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 472–488. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46454-1_29CrossRefGoogle Scholar
  14. 14.
    Dong, X., Shen, J., Wang, W., Liu, Y., Shao, L., Porikli, F.: Hyperparameter optimization for tracking with continuous deep q-learning. In: CVPR, pp. 518–527 (2018)Google Scholar
  15. 15.
    Du, D., Qi, H., Li, W., Wen, L., Huang, Q., Lyu, S.: Online deformable object tracking based on structure-aware hyper-graph. TIP 25(8), 3572–3584 (2016)MathSciNetGoogle Scholar
  16. 16.
    Du, D., et al.: The unmanned aerial vehicle benchmark: object detection and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 375–391. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01249-6_23CrossRefGoogle Scholar
  17. 17.
    Du, D., Wen, L., Qi, H., Huang, Q., Tian, Q., Lyu, S.: Iterative graph seeking for object tracking. TIP 27(4), 1809–1821 (2018)MathSciNetGoogle Scholar
  18. 18.
    Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. arXiv (2018)Google Scholar
  19. 19.
    Fan, H., Ling, H.: Parallel tracking and verifying: a framework for real-time and high accuracy visual tracking. In: ICCV, pp. 5487–5495 (2017)Google Scholar
  20. 20.
    Felsberg, M., et al.: The thermal infrared visual object tracking VOT-TIR2015 challenge results. In: ICCVWorkshops, pp. 639–651 (2015)Google Scholar
  21. 21.
    Galoogahi, H.K., Fagg, A., Huang, C., Ramanan, D., Lucey, S.: Need for speed: a benchmark for higher frame rate object tracking. In: ICCV, pp. 1134–1143 (2017)Google Scholar
  22. 22.
    Galoogahi, H.K., Fagg, A., Lucey, S.: Learning background-aware correlation filters for visual tracking. In: ICCV, pp. 1144–1152 (2017)Google Scholar
  23. 23.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  24. 24.
    He, Z., Fan, Y., Zhuang, J., Dong, Y., Bai, H.: Correlation filters with weighted convolution responses. In: ICCVWorkshops, pp. 1992–2000 (2017)Google Scholar
  25. 25.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. TPAMI 37(3), 583–596 (2015)CrossRefGoogle Scholar
  26. 26.
    Hsieh, M., Lin, Y., Hsu, W.H.: Drone-based object counting by spatially regularized regional proposal network. In: ICCV (2017)Google Scholar
  27. 27.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. CoRR abs/1709.01507 (2017). http://arxiv.org/abs/1709.01507
  28. 28.
    Hu, W., Li, X., Zhang, X., Shi, X., Maybank, S.J., Zhang, Z.: Incremental tensor subspace learning and its applications to foreground segmentation and tracking. IJCV 91(3), 303–327 (2011)CrossRefGoogle Scholar
  29. 29.
    Kristan, M., et al.: The visual object tracking VOT2016 challenge results. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 777–823. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_54CrossRefGoogle Scholar
  30. 30.
    Kristan, M., et al.: The visual object tracking VOT2017 challenge results. In: ICCVWorkshops, pp. 1949–1972 (2017)Google Scholar
  31. 31.
    Kristan, M., et al.: The visual object tracking VOT2015 challenge results. In: ICCVWorkshops, pp. 564–586 (2015)Google Scholar
  32. 32.
    Li, A., Li, M., Wu, Y., Yang, M.H., Yan, S.: NUS-PRO: a new visual tracking challenge. IEEE Trans. Pattern Anal. Mach. Intell., 1–15 (2015)Google Scholar
  33. 33.
    Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with Siamese region proposal network. In: CVPR, pp. 8971–8980 (2018)Google Scholar
  34. 34.
    Li, F., Tian, C., Zuo, W., Zhang, L., Yang, M.: Learning spatial-temporal regularized correlation filters for visual tracking. In: CVPR (2018)Google Scholar
  35. 35.
    Li, S., Du, D., Wen, L., Chang, M., Lyu, S.: Hybrid structure hypergraph for online deformable object tracking. In: ICPR, pp. 1127–1131 (2017)Google Scholar
  36. 36.
    Liang, P., Blasch, E., Ling, H.: Encoding color information for visual tracking: algorithms and benchmark. TIP 24(12), 5630–5644 (2015)MathSciNetGoogle Scholar
  37. 37.
    Liang, P., Wu, Y., Lu, H., Wang, L., Liao, C., Ling, H.: Planar object tracking in the wild: a benchmark. In: ICRA (2018)Google Scholar
  38. 38.
    Lin, T., Goyal, P., Girshick, R.B., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV, pp. 2999–3007 (2017)Google Scholar
  39. 39.
    Liu, B., Huang, J., Kulikowski, C.A., Yang, L.: Robust visual tracking using local sparse appearance model and k-selection. TPAMI 35(12), 2968–2981 (2013)CrossRefGoogle Scholar
  40. 40.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)MathSciNetCrossRefGoogle Scholar
  41. 41.
    Ma, C., Huang, J., Yang, X., Yang, M.: Hierarchical convolutional features for visual tracking. In: ICCV, pp. 3074–3082 (2015)Google Scholar
  42. 42.
    Mei, X., Ling, H.: Robust visual tracking using \(\ell 1\) minimization. In: ICCV, pp. 1436–1443 (2009)Google Scholar
  43. 43.
    Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445–461. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_27CrossRefGoogle Scholar
  44. 44.
    Mueller, M., Smith, N., Ghanem, B.: Context-aware correlation filter tracking. In: CVPR, pp. 1387–1395 (2017)Google Scholar
  45. 45.
    Müller, M., Bibi, A., Giancola, S., Alsubaihi, S., Ghanem, B.: TrackingNet: a large-scale dataset and benchmark for object tracking in the wild. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 310–327. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01246-5_19CrossRefGoogle Scholar
  46. 46.
    Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: CVPR, pp. 4293–4302 (2016)Google Scholar
  47. 47.
    Qi, Y., Qin, L., Zhang, J., Zhang, S., Huang, Q., Yang, M.: Structure-aware local sparse coding for visual tracking. TIP 27(8), 3857–3869 (2018)MathSciNetGoogle Scholar
  48. 48.
    Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. CoRR abs/1804.02767 (2018). http://arxiv.org/abs/1804.02767
  49. 49.
    Robicquet, A., Sadeghian, A., Alahi, A., Savarese, S.: Learning social etiquette: human trajectory understanding in crowded scenes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 549–565. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46484-8_33CrossRefGoogle Scholar
  50. 50.
    Ross, D.A., Lim, J., Lin, R., Yang, M.: Incremental learning for robust visual tracking. IJCV 77(1–3), 125–141 (2008)CrossRefGoogle Scholar
  51. 51.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  52. 52.
    Smeulders, A.W.M., Chu, D.M., Cucchiara, R., Calderara, S., Dehghan, A., Shah, M.: Visual tracking: an experimental survey. TPAMI 36(7), 1442–1468 (2014)CrossRefGoogle Scholar
  53. 53.
    Song, S., Xiao, J.: Tracking revisited using RGBD camera: unified benchmark and baselines. In: ICCV, pp. 233–240 (2013)Google Scholar
  54. 54.
    Song, Y., et al.: VITAL: visual tracking via adversarial learning. In: CVPR (2018)Google Scholar
  55. 55.
    Tao, R., Gavves, E., Smeulders, A.W.M.: Siamese instance search for tracking. In: CVPR, pp. 1420–1429 (2016)Google Scholar
  56. 56.
    Kristan, M., et al.: The visual object tracking VOT2014 challenge results. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8926, pp. 191–217. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-16181-5_14CrossRefGoogle Scholar
  57. 57.
    Felsberg, M., et al.: The thermal infrared visual object tracking VOT-TIR2016 challenge results. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 824–849. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_55CrossRefGoogle Scholar
  58. 58.
    Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: CVPR, pp. 4489–4497 (2015)Google Scholar
  59. 59.
    Valmadre, J., Bertinetto, L., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: End-to-end representation learning for correlation filter based tracking. In: CVPR, pp. 5000–5008 (2017)Google Scholar
  60. 60.
    Wang, N., Zhou, W., Tian, Q., Hong, R., Wang, M., Li, H.: Multi-cue correlation filters for robust visual tracking. In: CVPR, pp. 4844–4853 (2018)Google Scholar
  61. 61.
    Wang, Q., Gao, J., Xing, J., Zhang, M., Hu, W.: DCFNet: discriminant correlation filters network for visual tracking. CoRR abs/1704.04057 (2017). http://arxiv.org/abs/1704.04057
  62. 62.
    Wen, L., Cai, Z., Lei, Z., Yi, D., Li, S.Z.: Online spatio-temporal structural context learning for visual tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 716–729. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33765-9_51CrossRefGoogle Scholar
  63. 63.
    Wen, L., Cai, Z., Lei, Z., Yi, D., Li, S.Z.: Robust online learned spatio-temporal context model for visual tracking. TIP 23(2), 785–796 (2014)MathSciNetzbMATHGoogle Scholar
  64. 64.
    Wu, T., Lu, Y., Zhu, S.: Online object tracking, learning and parsing with and-or graphs. TPAMI 39(12), 2465–2480 (2017)CrossRefGoogle Scholar
  65. 65.
    Wu, Y., Lim, J., Yang, M.: Online object tracking: a benchmark. In: CVPR, pp. 2411–2418 (2013)Google Scholar
  66. 66.
    Wu, Y., Lim, J., Yang, M.: Object tracking benchmark. TPAMI 37(9), 1834–1848 (2015)CrossRefGoogle Scholar
  67. 67.
    Yun, S., Choi, J., Yoo, Y., Yun, K., Choi, J.Y.: Action-decision networks for visual tracking with deep reinforcement learning. In: CVPR (2017)Google Scholar
  68. 68.
    Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. In: CVPR (2018)Google Scholar
  69. 69.
    Zhong, W., Lu, H., Yang, M.: Robust object tracking via sparse collaborative appearance model. TIP 23(5), 2356–2368 (2014)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Longyin Wen
    • 1
  • Pengfei Zhu
    • 2
    Email author
  • Dawei Du
    • 3
  • Xiao Bian
    • 4
  • Haibin Ling
    • 5
  • Qinghua Hu
    • 2
  • Chenfeng Liu
    • 2
  • Hao Cheng
    • 2
  • Xiaoyu Liu
    • 2
  • Wenya Ma
    • 2
  • Qinqin Nie
    • 2
  • Haotian Wu
    • 2
  • Lianjie Wang
    • 2
  • Asanka G. Perera
    • 23
  • Baochang Zhang
    • 8
  • Byeongho Heo
    • 17
  • Chunlei Liu
    • 8
  • Dongdong Li
    • 22
  • Emmanouil Michail
    • 15
  • Hanlin Chen
    • 10
  • Hao Liu
    • 22
  • Haojie Li
    • 12
  • Ioannis Kompatsiaris
    • 15
  • Jian Cheng
    • 28
    • 29
  • Jiaqing Fan
    • 29
  • Jie Zhang
    • 21
  • Jin Young Choi
    • 17
  • Jing Li
    • 27
  • Jinyu Yang
    • 8
  • Jongwon Choi
    • 17
    • 19
  • Juanping Zhao
    • 6
  • Jungong Han
    • 9
  • Kaihua Zhang
    • 30
  • Kaiwen Duan
    • 14
  • Ke Song
    • 20
  • Konstantinos Avgerinakis
    • 15
  • Kyuewang Lee
    • 17
  • Lu Ding
    • 6
  • Martin Lauer
    • 16
  • Panagiotis Giannakeris
    • 15
  • Peizhen Zhang
    • 25
  • Qiang Wang
    • 28
  • Qianqian Xu
    • 31
  • Qingming Huang
    • 13
    • 14
  • Qingshan Liu
    • 30
  • Robert Laganière
    • 7
  • Ruixin Zhang
    • 24
  • Sangdoo Yun
    • 18
  • Shengyin Zhu
    • 11
  • Sihang Wu
    • 12
  • Stefanos Vrochidis
    • 15
  • Wei Tian
    • 16
  • Wei Zhang
    • 20
  • Weidong Chen
    • 14
  • Weiming Hu
    • 28
  • Wenhao Wang
    • 20
  • Wenhua Zhang
    • 21
  • Wenrui Ding
    • 8
  • Xiaohao He
    • 26
  • Xiaotong Li
    • 21
  • Xin Zhang
    • 21
  • Xinbin Luo
    • 6
  • Xixi Hu
    • 20
  • Yang Meng
    • 21
  • Yangliu Kuai
    • 22
  • Yanyun Zhao
    • 11
  • Yaxuan Li
    • 20
  • Yifan Yang
    • 14
  • Yifan Zhang
    • 28
    • 29
  • Yong Wang
    • 7
  • Yuankai Qi
    • 13
  • Zhipeng Deng
    • 22
  • Zhiqun He
    • 11
  1. 1.JD FinanceMountain ViewUSA
  2. 2.Tianjin UniversityTianjinChina
  3. 3.University at Albany, SUNYAlbanyUSA
  4. 4.GE Global ResearchNiskayunaUSA
  5. 5.Temple UniversityPhiladelphiaUSA
  6. 6.Shanghai Jiao Tong UniversityShanghaiChina
  7. 7.University of OttawaOttawaCanada
  8. 8.Beihang UniversityBeijingChina
  9. 9.Lancaster UniversityLancasterUK
  10. 10.Shenyang Aerospace UniversityShenyangChina
  11. 11.Beijing University of Posts and TelecommunicationsBeijingChina
  12. 12.South China University of TechnologyGuangzhouChina
  13. 13.Harbin Institute of TechnologyHarbinChina
  14. 14.University of Chinese Academy of SciencesBeijingChina
  15. 15.Centre for Research & Technology HellasThessalonikiGreece
  16. 16.Karlsruhe Institute of TechnologyKarlsruheGermany
  17. 17.Seoul National UniversitySeoulSouth Korea
  18. 18.NAVER CorpSeongnamSouth Korea
  19. 19.Samsung R&D CampusSeoulSouth Korea
  20. 20.Shandong UniversityJinanChina
  21. 21.Xidian UniversityXi’anChina
  22. 22.National University of Defense TechnologyChangshaChina
  23. 23.University of South AustraliaAdelaideAustralia
  24. 24.TencentShanghaiChina
  25. 25.Sun yat-sen universityGuangzhouChina
  26. 26.Tsinghua UniversityBeijingChina
  27. 27.Civil Aviation University of ChinaTianjinChina
  28. 28.Institute of Automation, Chinese Academy of SciencesBeijingChina
  29. 29.Nanjing Artificial Intelligence Chip ResearchInstitute of Automation, Chinese Academy of SciencesBeijingChina
  30. 30.Nanjing University of Information Science and TechnologyNanjingChina
  31. 31.Institute of Computing Technology, Chinese Academy of SciencesBeijingChina

Personalised recommendations