mlsanityData to 7 Oct 2026

Efficient Online 3D Multi-Camera Multi-Object Tracking and Pose Estimation

arXiv 2604.16522 ↗First posted 16 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper proposes a fast and online method for jointly performing 3D multi-object tracking and pose estimation using multiple monocular cameras. Our algorithm requires only 2D bounding box and pose detections, eliminating the need for costly 3D training data or computationally expensive deep learning models. Our solution is an efficient implementation of a Bayes-optimal multi-object tracking filter, enhancing computational efficiency while maintaining accuracy. We demonstrate that our algorithm is significantly faster than state-of-the-art methods without compromising accuracy, using only publicly available pre-trained 2D detection models. We also illustrate the robust performance of our algorithm in scenarios where multiple cameras are intermittently disconnected or reconnected during operation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 64 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

35 of 64 references.

References · 35

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Mask R-CNNcited by 7,259
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2015Fast R-CNNcited by 2,930
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  7. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  10. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  11. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  12. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
23 more
  1. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  2. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  3. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  4. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  5. 2019Fast and Robust Multi-Person 3D Pose Estimation from Multiple Viewscited by 83
  6. 2020Multiview Detection with Feature Perspective Transformationcited by 70
  7. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  8. 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
  9. 2017Deep Occlusion Reasoning for Multi-Camera Multi-Target Detectioncited by 42
  10. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  11. 2021Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereocited by 38
  12. 2021Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Imagescited by 38
  13. 2017Deep Multi-camera People Detectioncited by 37
  14. 2021LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Trackingcited by 34
  15. 2023EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye Viewcited by 33
  16. 20223D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localizationcited by 22
  17. 2024SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimationcited by 21
  18. 2023Multiple View Geometry Transformers for 3D Human Pose Estimationcited by 19
  19. 2020Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometrycited by 18
  20. 2022Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimationcited by 9
  21. 2014Parsing Occluded People by Flexible Compositionscited by 8
  22. 2024Track Initialization and Re-Identification for~3D Multi-View Multi-Object Trackingcited by 7
  23. 2021Urban Traffic Surveillance (UTS): A fully probabilistic 3D tracking approach based on 2D detectionscited by 3

Built on by

Not cited yet.