Research map / 3D vision / 3D generation
A Bayesian Filter for Multi-View 3D Multi-Object Tracking With Occlusion Handling
Jonah Ong, Ba-Tuong Vo, Ba‐Ngu Vo, Du Yong Kim, Sven Erik Nordholm
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · WILDTRACKS camera C1 | MODA: -17.1% -> 12.2% | Improved |
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · WILDTRACKS camera C2 | MODA: 28.4% -> 31.7% | Improved |
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · WILDTRACKS camera C4 | MODA: -300.0% -> -272.4% | Improved |
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · WILDTRACKS camera C5 | MODA: -113.0% -> -94.4% | Improved |
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · WILDTRACKS camera C7 | MODA: -100.3% -> -79.2% | Improved |
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · CMC1 Cam1 | MODA: 12.0% -> 20.6% | Improved |
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · CMC1 Cam4 | MODA: 11.1% -> 12.1% | Improved |
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · CMC2 Cam1 | MODA: 37.5% -> 51.2% | Improved |
| use YOLOv3 instead of Faster R-CNN (VGG16) | Monocular person detector · CMC2 Cam2 | MODA: 35.5% -> 45.3% | Improved |
| use multi-camera Deep-Occlusion detector instead of YOLOv3 on C1 | YOLOv3 monocular detections · WILDTRACKS | MODA: 12.2% -> 74.1% | Improved |
Closest papers by meaning
- Multi-View 3D Point Tracking (ICCV 2025 · similarity 0.88)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.87)
- S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking (ICML 2025 · similarity 0.86)
- MITracker: Multi-View Integration for Visual Object Tracking (CVPR 2025 · similarity 0.85)
- ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association (CVPR 2024 · similarity 0.85)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
