mlsanityData to 7 Oct 2026

Depth Perspective-aware Multiple Object Tracking

arXiv 2207.04551 ↗First posted 10 Jul 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper aims to tackle Multiple Object Tracking (MOT), an important problem in computer vision but remains challenging due to many practical issues, especially occlusions. Indeed, we propose a new real-time Depth Perspective-aware Multiple Object Tracking (DP-MOT) approach to tackle the occlusion problem in MOT. A simple yet efficient Subject-Ordered Depth Estimation (SODE) is first proposed to automatically order the depth positions of detected subjects in a 2D scene in an unsupervised manner. Using the output from SODE, a new Active pseudo-3D Kalman filter, a simple but effective extension of Kalman filter with dynamic control variables, is then proposed to dynamically update the movement of objects. In addition, a new high-order association approach is presented in the data association step to incorporate first-order and second-order relationships between the detected objects. The proposed approach consistently achieves state-of-the-art performance compared to recent MOT methods on standard MOT benchmarks.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 36 of its 60 references that are in the map. First posted on arXiv 10 Jul 2022.

Builds on

36 of 60 references.

References · 36

  1. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2018YOLOv3: An Incremental Improvementcited by 2,652
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  6. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  7. 2020Tracking Objects as Pointscited by 483
  8. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  9. 2019Tracking without bells and whistlescited by 382
  10. 2019Towards Real-Time Multi-Object Trackingcited by 311
  11. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  12. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
24 more
  1. 2016Person Re-identification in the Wildcited by 157
  2. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  3. 2015MOTChallenge 2015: Towards a Benchmark for Multi-Target Trackingcited by 133
  4. 2020Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Trackingcited by 115
  5. 2020GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learningcited by 113
  6. 2018Deep Affinity Network for Multiple Object Trackingcited by 82
  7. 2021Monocular Quasi-Dense 3D Object Trackingcited by 80
  8. 2018Joint Monocular 3D Vehicle Detection and Trackingcited by 77
  9. 2019Online Multi-Object Tracking with Dual Matching Attention Networkscited by 77
  10. 2019Spatial-Temporal Relation Networks for Multi-Object Trackingcited by 74
  11. 2019How To Train Your Deep Multi-Object Trackercited by 71
  12. 2016Fast Optical Flow using Dense Inverse Searchcited by 70
  13. 2019FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Trackingcited by 65
  14. 2021DEFT: Detection Embeddings for Trackingcited by 56
  15. 2020Lifted Disjoint Paths with Application in Multiple Object Trackingcited by 55
  16. 20193D Multi-Object Tracking: A Baseline and New Evaluation Metricscited by 47
  17. 2021Learning a Proposal Classifier for Multiple Object Trackingcited by 42
  18. 2020A Unified Object Motion and Affinity Model for Online Multi-Object Trackingcited by 33
  19. 2018Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filteringcited by 32
  20. 2021DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Trackingcited by 31
  21. 2020Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Trackingcited by 25
  22. 2022Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehiclescited by 19
  23. 2019Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshmentcited by 18
  24. 2018Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Trackingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 0; 2025: 3; 2026: 1.

8 papers.

  1. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  2. 2023Type-to-Track: Retrieve Any Object via Prompt-based Trackingcited by 24
  3. 2023SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognitioncited by 14
  4. 20233D Multiple Object Tracking on Autonomous Driving: A Literature Reviewcited by 4
  5. 2025Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Trackingcited by 1
  6. 2025DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Trackingcited by 1
  7. 2026Occlusion-Aware SORT: Observing Occlusion for Robust Multi-Object Trackingcited by 1
  8. 2025Fast Self-Supervised depth and mask aware Association for Multi-Object Trackingcited by 0