BoT-SORT: Robust Associations Multi-Pedestrian Tracking

Abstract

The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene, while keeping a unique identifier for each object. In this paper, we present a new robust state-of-the-art tracker, which can combine the advantages of motion and appearance information, along with camera-motion compensation, and a more accurate Kalman filter state vector. Our new trackers BoT-SORT, and BoT-SORT-ReID rank first in the datasets of MOTChallenge [29, 11] on both MOT17 and MOT20 test sets, in terms of all the main MOT metrics: MOTA, IDF1, and HOTA. For MOT17: 80.5 MOTA, 80.2 IDF1, and 65.0 HOTA are achieved. The source code and the pre-trained models are available at https://github.com/NirAharon/BOT-SORT

Cited by in corpus (14)

• Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery
• Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions
• Learning Data Association for Multi-Object Tracking using Only Coordinates
• Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking
• SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos
• Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory
• Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration
• Towards pedestrian head tracking: A benchmark dataset and a multi-source data fusion network
• Multiple Object Tracking in Video SAR: A Benchmark and Tracking Baseline
• YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID
• Motion State: A New Benchmark Multiple Object Tracking
• The 6th AI City Challenge
• Evaluating the Significance of Outdoor Advertising from Driver's Perspective Using Computer Vision
• A Multilevel Strategy to Improve People Tracking in a Real-World Scenario