# Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection

arXiv: https://arxiv.org/abs/1704.05775 · HTML: https://mlsanity.com/paper/1704.05775/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2017.

## Built on by (most cited first, 30 of 42)

- [Waymo Open Dataset: Panoramic Video Panoptic Segmentation](https://mlsanity.com/paper/2206.07704/) (2022)
- [Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)](https://mlsanity.com/paper/2108.05888/) (2021)
- [VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild](https://mlsanity.com/paper/2108.02452/) (2021)
- [EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View](https://mlsanity.com/paper/2310.13350/) (2023)
- [MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark](https://mlsanity.com/paper/2111.15157/) (2021)
- [Cross-View Cross-Scene Multi-View Crowd Counting](https://mlsanity.com/paper/2205.01551/) (2022)
- [Lifting Multi-View Detection and Tracking to the Bird's Eye View](https://mlsanity.com/paper/2403.12573/) (2024)
- [3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization](https://mlsanity.com/paper/2207.10895/) (2022)
- [Generalizable Multi-Camera 3D Pedestrian Detection](https://mlsanity.com/paper/2104.05813/) (2021)
- [Two-level Data Augmentation for Calibrated Multi-view Detection](https://mlsanity.com/paper/2210.10756/) (2022)
- [Bringing Generalization to Deep Multi-View Pedestrian Detection](https://mlsanity.com/paper/2109.12227/) (2021)
- [Multi-view Tracking Using Weakly Supervised Human Motion Prediction](https://mlsanity.com/paper/2210.10771/) (2022)
- [MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos](https://mlsanity.com/paper/2412.00692/) (2024)
- [Unsupervised Multi-view Pedestrian Detection](https://mlsanity.com/paper/2305.12457/) (2023)
- [Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking](https://mlsanity.com/paper/2405.18606/) (2024)
- [Voxelized 3D Feature Aggregation for Multiview Detection](https://mlsanity.com/paper/2112.03471/) (2021)
- [Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume](https://mlsanity.com/paper/2503.10982/) (2025)
- [Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention](https://mlsanity.com/paper/2208.09211/) (2022)
- [From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration](https://mlsanity.com/paper/2212.09298/) (2022)
- [DCHM: Depth-Consistent Human Modeling for Multiview Detection](https://mlsanity.com/paper/2507.14505/) (2025)
- [MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost](https://mlsanity.com/paper/2509.01157/) (2025)
- [MVM3Det: A Novel Method for Multi-view Monocular 3D Detection](https://mlsanity.com/paper/2109.10473/) (2021)
- [Learning to Select Camera Views: Efficient Multiview Understanding at Few Glances](https://mlsanity.com/paper/2303.06145/) (2023)
- [Optimizing Camera Configurations for Multi-View Pedestrian Detection](https://mlsanity.com/paper/2312.02144/) (2023)
- [Multiview Detection with Cardboard Human Modeling](https://mlsanity.com/paper/2207.02013/) (2022)
- [3D Multi-Object Tracking Employing MS-GLMB Filter for Autonomous Driving](https://mlsanity.com/paper/2410.14977/) (2024)
- [MVUDA: Unsupervised Domain Adaptation for Multi-view Pedestrian Detection](https://mlsanity.com/paper/2412.04117/) (2024)
- [MC-BEVRO: Multi-Camera Bird Eye View Road Occupancy Detection for Traffic Monitoring](https://mlsanity.com/paper/2502.11287/) (2025)
- [One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking](https://mlsanity.com/paper/2507.08494/) (2025)
- [Custom Object Detection via Multi-Camera Self-Supervised Learning](https://mlsanity.com/paper/2102.03442/) (2021)

## Abstract (arXiv)

People detection in single 2D images has improved greatly in recent years. However, comparatively little of this progress has percolated into multi-camera multi-people tracking algorithms, whose performance still degrades severely when scenes become very crowded. In this work, we introduce a new architecture that combines Convolutional Neural Nets and Conditional Random Fields to explicitly model those ambiguities. One of its key ingredients are high-order CRF terms that model potential occlusions and give our approach its robustness even when many people are present. Our model is trained end-to-end and we show that it outperforms several state-of-art algorithms on challenging scenes.