mlsanityData to 7 Oct 2026

Generalizable Multi-Camera 3D Pedestrian Detection

arXiv 2104.05813 ↗First posted 12 Apr 2021cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

We present a multi-camera 3D pedestrian detection method that does not need to train using data from the target scene. We estimate pedestrian location on the ground plane using a novel heuristic based on human body poses and person's bounding boxes from an off-the-shelf monocular detector. We then project these locations onto the world ground plane and fuse them with a new formulation of a clique cover problem. We also propose an optional step for exploiting pedestrian appearance during fusion by using a domain-generalizable person re-identification model. We evaluated the proposed approach on the challenging WILDTRACK dataset. It obtained a MODA of 0.569 and an F-score of 0.78, superior to state-of-the-art generalizable detection techniques.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

15 of 24 references.

References · 15

  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. 2018YOLOv3: An Incremental Improvementcited by 2,652
  5. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  6. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  7. 2019Learning Generalisable Omni-Scale Representations for Person Re-Identificationcited by 73
  8. 2020Multiview Detection with Feature Perspective Transformationcited by 70
  9. 2017Deep Occlusion Reasoning for Multi-Camera Multi-Target Detectioncited by 42
  10. 2019MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimationcited by 39
  11. 2020Real-time 3D Deep Multi-Camera Trackingcited by 23
  12. 2020Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometrycited by 18
3 more
  1. 2018Semantic Driven Multi-Camera Pedestrian Detectioncited by 6
  2. 2020Recognition and 3D Localization of Pedestrian Actions from Monocular Videocited by 4
  3. 2020Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 3; 2023: 1; 2024: 4; 2025: 2; 2026: 1.

14 papers.

Sort:

  1. 2021MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmarkcited by 28
  2. 2022Graph Neural Networks for Cross-Camera Data Associationcited by 13
  3. 2021Bringing Generalization to Deep Multi-View Pedestrian Detectioncited by 11
  4. 2021Voxelized 3D Feature Aggregation for Multiview Detectioncited by 6
  5. 2025DCHM: Depth-Consistent Human Modeling for Multiview Detectioncited by 5
  6. 2022Multiview Detection with Cardboard Human Modelingcited by 2
  7. 2022Graph-Based Multi-Camera Soccer Player Trackercited by 1
  8. 2023Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysiscited by 1
  9. 2024FCA-RAC: First Cycle Annotated Repetitive Action Countingcited by 1
  10. 2024IVAC-P2L: Leveraging Irregular Repetition Priors for Improving Video Action Countingcited by 0
  11. 2024Cross-Camera Data Association via GNN for Supervised Graph Clusteringcited by 0
  12. 2024The Streetscape Application Services Stack (SASS): Towards a Distributed Sensing Architecture for Urban Applicationscited by 0
2 more
  1. 2025Valeo Near-Field: a novel dataset for pedestrian intent detectioncited by 0
  2. 2026Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Trackingcited by 0