Tracking Objects as Points

Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection. In this paper, we present a simultaneous detection and tracking algorithm that is simpler, faster, and more accurate than the state of the art. Our tracker, CenterTrack, applies a detection model to a pair of images and detections from the prior frame. Given this minimal input, CenterTrack localizes objects and predicts their associations with the previous frame. That's it. CenterTrack is simple, online (no peeking into the future), and real-time. It achieves 67.3% MOTA on the MOT17 challenge at 22 FPS and 89.4% MOTA on the KITTI tracking benchmark at 15 FPS, setting a new state of the art on both datasets. CenterTrack is easily extended to monocular 3D tracking by regressing additional 3D attributes. Using monocular video input, it achieves 28.3% AMOTA@0.2 on the newly released nuScenes 3D tracking benchmark, substantially outperforming the monocular baseline on this benchmark while running at 28 FPS.

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Multi-Object Tracking DanceTrack CenterTrack HOTA 41.8 # 21
DetA 78.1 # 13
AssA 22.6 # 21
MOTA 86.8 # 15
IDF1 35.7 # 22
Multiple Object Tracking KITTI Tracking test CenterTrack MOTA 89.44 # 4
Multiple Object Tracking SportsMOT CenterTrack HOTA 62.7 # 8
IDF1 60.0 # 9
AssA 48.0 # 8
MOTA 90.8 # 7
DetA 82.1 # 5
Multi-Object Tracking SportsMOT CenterTrack HOTA 62.7 # 9
IDF1 60.0 # 10
AssA 48.0 # 9
MOTA 90.8 # 8
DetA 82.1 # 6