作者:Xingyi ZhouVladlen KoltunPhilipp Krähenbühl

作者单位:UT Austin,Intel Labs

发布时间:2020

发布期刊/会议:ECCV

论文全称:Tracking Objects as Points

论文地址:https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123490460.pdf

论文代码:https://github.com/xingyizhou/CenterTrack

地位:

个人理解

一、摘要

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. 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*.8% 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.