# Generalizable Multi-Camera 3D Pedestrian Detection

arXiv: https://arxiv.org/abs/2104.05813 · HTML: https://mlsanity.com/paper/2104.05813/

## Key facts

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

## Builds on (most cited first, 15 of 15)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships](https://mlsanity.com/paper/2003.00504/) (2020)
- [Learning Generalisable Omni-Scale Representations for Person Re-Identification](https://mlsanity.com/paper/1910.06827/) (2019)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection](https://mlsanity.com/paper/1704.05775/) (2017)
- [MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation](https://mlsanity.com/paper/1906.06059/) (2019)
- [Real-time 3D Deep Multi-Camera Tracking](https://mlsanity.com/paper/2003.11753/) (2020)
- [Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry](https://mlsanity.com/paper/2007.10986/) (2020)
- [Semantic Driven Multi-Camera Pedestrian Detection](https://mlsanity.com/paper/1812.10779/) (2018)
- [Recognition and 3D Localization of Pedestrian Actions from Monocular Video](https://mlsanity.com/paper/2008.01162/) (2020)
- [Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning](https://mlsanity.com/paper/2003.07618/) (2020)

## Built on by (most cited first, 14 of 14)

- [MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark](https://mlsanity.com/paper/2111.15157/) (2021)
- [Graph Neural Networks for Cross-Camera Data Association](https://mlsanity.com/paper/2201.06311/) (2022)
- [Bringing Generalization to Deep Multi-View Pedestrian Detection](https://mlsanity.com/paper/2109.12227/) (2021)
- [Voxelized 3D Feature Aggregation for Multiview Detection](https://mlsanity.com/paper/2112.03471/) (2021)
- [DCHM: Depth-Consistent Human Modeling for Multiview Detection](https://mlsanity.com/paper/2507.14505/) (2025)
- [Multiview Detection with Cardboard Human Modeling](https://mlsanity.com/paper/2207.02013/) (2022)
- [Graph-Based Multi-Camera Soccer Player Tracker](https://mlsanity.com/paper/2211.02125/) (2022)
- [Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysis](https://mlsanity.com/paper/2308.04515/) (2023)
- [FCA-RAC: First Cycle Annotated Repetitive Action Counting](https://mlsanity.com/paper/2406.12178/) (2024)
- [IVAC-P2L: Leveraging Irregular Repetition Priors for Improving Video Action Counting](https://mlsanity.com/paper/2403.11959/) (2024)
- [Cross-Camera Data Association via GNN for Supervised Graph Clustering](https://mlsanity.com/paper/2410.00643/) (2024)
- [The Streetscape Application Services Stack (SASS): Towards a Distributed Sensing Architecture for Urban Applications](https://mlsanity.com/paper/2411.19714/) (2024)
- [Valeo Near-Field: a novel dataset for pedestrian intent detection](https://mlsanity.com/paper/2510.15673/) (2025)
- [Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking](https://mlsanity.com/paper/2608.24130/) (2026)

## 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.