BoT-SORT
Robust multi-object tracking combining motion and appearance cues.
About
BoT-SORT is a multi-object tracking method that associates detections across video frames by combining motion and appearance cues. It adds camera-motion compensation, an improved Kalman filter state vector, and an optional re-identification branch (BoT-SORT-ReID) for appearance matching. It reached state-of-the-art results on the MOT17 and MOT20 benchmarks and is commonly paired with YOLO detectors for tracking pipelines.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Monocular depth estimation model producing detailed depth maps from single images.
End-to-end object detection with transformers by Meta, eliminating hand-designed components.
Self-supervised vision transformer by Meta producing universal visual features.
Unified vision foundation model by Microsoft for captioning, detection, and segmentation.
Monocular depth estimation model by Intel ISL supporting multiple backbones.
Simple and effective multi-object tracking using every detection box.