ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold... The objects with low detection scores, e.g. occluded objects, are simply thrown away, which brings non-negligible true object missing and fragmented trajectories. To solve this problem, we present a simple, effective and generic association method, called BYTE, tracking BY associaTing Every detection box instead of only the high score ones. For the low score detection boxes, we utilize their similarities with tracklets to recover true objects and filter out the background detections. We apply BYTE to 9 different state-of-the-art trackers and achieve consistent improvement on IDF1 score ranging from 1 to 10 points. To put forwards the state-of-the-art performance of MOT, we design a simple and strong tracker, named ByteTrack. For the first time, we achieve 80.3 MOTA, 77.3 IDF1 and 63.1 HOTA on the test set of MOT17 with 30 FPS running speed on a single V100 GPU. The source code, pre-trained models with deploy versions and tutorials of applying to other trackers are released at https://github.com/ifzhang/ByteTrack. read more

PDF Abstract arXiv 2021 PDF arXiv 2021 Abstract

Results from the Paper


 Ranked #1 on Multi-Object Tracking on MOT17 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Multi-Object Tracking MOT17 ByteTrack MOTA 80.3 # 1
IDF1 77.3 # 1
Multi-Object Tracking MOT20 ByteTrack MOTA 77.8 # 1
IDF1 75.2 # 1

Methods


No methods listed for this paper. Add relevant methods here