Tracking Objects as Points

Abstract

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% [email protected] on the newly released nuScenes 3D tracking benchmark, substantially outperforming the monocular baseline on this benchmark while running at 28 FPS.

arXiv commentECCV 2020 Camera-ready version. Updated track rebirth results. Code available at https://github.com/xingyizhou/CenterTrack

References in corpus (11)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Simple Online and Realtime Tracking
• MOT16: A Benchmark for Multi-Object Tracking
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• CrowdHuman: A Benchmark for Detecting Human in a Crowd
• Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
• Track to Reconstruct and Reconstruct to Track
• Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
• Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
• Integrated Object Detection and Tracking with Tracklet-Conditioned Detection
• 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics

Cited by in corpus (7)

• MAT: Motion-Aware Multi-Object Tracking
• Local Metrics for Multi-Object Tracking
• Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation
• Simple online and real-time tracking with occlusion handling
• Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking
• MOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videos
• Relation3DMOT: Exploiting Deep Affinity for 3D Multi-Object Tracking from View Aggregation