Papers
Topics
Authors
Recent
Search
2000 character limit reached

Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker

Published 2 May 2022 in cs.CV | (2205.00968v3)

Abstract: In existing joint detection and tracking methods, pairwise relational features are used to match previous tracklets to current detections. However, the features may not be discriminative enough for a tracker to identify a target from a large number of detections. Selecting only high-scored detections for tracking may lead to missed detections whose confidence score is low. Consequently, in the online setting, this results in disconnections of tracklets which cannot be recovered. In this regard, we present Sparse Graph Tracker (SGT), a novel online graph tracker using higher-order relational features which are more discriminative by aggregating the features of neighboring detections and their relations. SGT converts video data into a graph where detections, their connections, and the relational features of two connected nodes are represented by nodes, edges, and edge features, respectively. The strong edge features allow SGT to track targets with tracking candidates selected by top-K scored detections with large K. As a result, even low-scored detections can be tracked, and the missed detections are also recovered. The robustness of K value is shown through the extensive experiments. In the MOT16/17/20 and HiEve Challenge, SGT outperforms the state-of-the-art trackers with real-time inference speed. Especially, a large improvement in MOTA is shown in the MOT20 and HiEve Challenge. Code is available at https://github.com/HYUNJS/SGT.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Layer normalization. arXiv preprint arXiv:1607.06450, 2016.
  2. Evaluating multiple object tracking performance: the clear mot metrics. EURASIP Journal on Image and Video Processing, 2008:1–10, 2008.
  3. An introduction to the kalman filter. SIGGRAPH, Course, 8(27599-23175):41, 2001.
  4. High-speed tracking-by-detection without using image information. In AVSS, pages 1–6. IEEE, 2017.
  5. Learning a neural solver for multiple object tracking. In CVPR, pages 6247–6257, 2020.
  6. A unified multi-scale deep convolutional neural network for fast object detection. In ECCV, pages 354–370. Springer, 2016.
  7. Virtual to real adaptation of pedestrian detectors. Sensors, 20(18):5250, 2020.
  8. R-fcn: Object detection via region-based fully convolutional networks. NeurIPS, 29, 2016.
  9. Learning a proposal classifier for multiple object tracking. In CVPR, pages 2443–2452, 2021.
  10. Mot20: A benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003, 2020.
  11. Pedestrian detection: A benchmark. In CVPR, pages 304–311. IEEE, 2009.
  12. A mobile vision system for robust multi-person tracking. In CVPR, pages 1–8, 2008.
  13. Detect to track and track to detect. In ICCV, pages 3038–3046, 2017.
  14. Neural message passing for quantum chemistry. In ICML, pages 1263–1272. PMLR, 2017.
  15. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
  16. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  17. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  18. Harold W Kuhn. The hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1-2):83–97, 1955.
  19. Cornernet: Detecting objects as paired keypoints. In ECCV, pages 734–750, 2018.
  20. Learning to associate: Hybridboosted multi-target tracker for crowded scene. In CVPR, pages 2953–2960. IEEE, 2009.
  21. One more check: Making “fake background” be tracked again. In AAAI, volume 36, pages 1546–1554, 2022.
  22. Rethinking the competition between detection and reid in multiobject tracking. TIP, 31:3182–3196, 2022.
  23. Focal loss for dense object detection. In ICCV, pages 2980–2988, 2017.
  24. Microsoft coco: Common objects in context. In ECCV, pages 740–755. Springer, 2014.
  25. Human in events: A large-scale benchmark for human-centric video analysis in complex events. arXiv preprint arXiv:2005.04490, 2020.
  26. Retinatrack: Online single stage joint detection and tracking. In CVPR, pages 14668–14678, 2020.
  27. Mot16: A benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831, 2016.
  28. Stacked hourglass networks for human pose estimation. In ECCV, pages 483–499. Springer, 2016.
  29. Graph neural networks exponentially lose expressive power for node classification. arXiv preprint arXiv:1905.10947, 2019.
  30. Quasi-dense similarity learning for multiple object tracking. In CVPR, June 2021.
  31. Chained-tracker: Chaining paired attentive regression results for end-to-end joint multiple-object detection and tracking. In ECCV, pages 145–161. Springer, 2020.
  32. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.
  33. Faster r-cnn: Towards real-time object detection with region proposal networks. NeurIPS, 28, 2015.
  34. Performance measures and a data set for multi-target, multi-camera tracking. In ECCV, pages 17–35. Springer, 2016.
  35. Crowdhuman: A benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123, 2018.
  36. Application of multi-object tracking with siamese track-rcnn to the human in events dataset. In ACM Multimedia, pages 4625–4629, 2020.
  37. Transtrack: Multiple-object tracking with transformer. arXiv preprint arXiv:2012.15460, 2020.
  38. Multiple object tracking with correlation learning. In CVPR, pages 3876–3886, 2021.
  39. Joint object detection and multi-object tracking with graph neural networks. In ICRA, pages 13708–13715, 2021.
  40. Towards real-time multi-object tracking. In ECCV, pages 107–122. Springer, 2020.
  41. Gnn3dmot: Graph neural network for 3d multi-object tracking with 2d-3d multi-feature learning. In CVPR, pages 6499–6508, 2020.
  42. Simple online and realtime tracking with a deep association metric. In ICIP, pages 3645–3649. IEEE, 2017.
  43. Track to detect and segment: An online multi-object tracker. In CVPR, pages 12352–12361, 2021.
  44. Joint detection and identification feature learning for person search. In CVPR, pages 3415–3424, 2017.
  45. Spatial-temporal relation networks for multi-object tracking. In ICCV, pages 3988–3998, 2019.
  46. Relationtrack: Relation-aware multiple object tracking with decoupled representation. arXiv preprint arXiv:2105.04322, 2021.
  47. Deep layer aggregation. In CVPR, pages 2403–2412, 2018.
  48. Citypersons: A diverse dataset for pedestrian detection. In CVPR, pages 3213–3221, 2017.
  49. Bytetrack: Multi-object tracking by associating every detection box. arXiv preprint arXiv:2110.06864, 2021.
  50. Fairmot: On the fairness of detection and re-identification in multiple object tracking. IJCV, 129(11):3069–3087, 2021.
  51. Improving multiple object tracking with single object tracking. In CVPR, pages 2453–2462, 2021.
  52. Person re-identification in the wild. In CVPR, pages 1367–1376, 2017.
  53. Tracking objects as points. In ECCV, pages 474–490. Springer, 2020.
  54. Objects as points. arXiv preprint arXiv:1904.07850, 2019.
  55. Global tracking transformers. In CVPR, pages 8771–8780, 2022.
Citations (33)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up