2020/03/30 by Zhichao Lu, Lu, Zhichao, Vivek Rathod +5 · 15 citations
Computer Science · Engineering · Environmental Science · #Algorithm #Artificial intelligence #Baseline (sea) #Computation #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Detector #Embedding #Engineering #FOS: Computer and information sciences #FOS: Electrical engineering #Fire Detection and Safety Systems #Focus (optics) #Image and Video Processing (eess.IV) #Impact of Light on Environment and Health #Joint (building) #Kalman filter #Machine Learning (cs.LG) #Object (grammar) #Object detection #Pattern recognition (psychology) #Simple (philosophy) #Tracking (education) #Tracking system #Video Surveillance and Tracking Methods #Video tracking #cs.CV #cs.LG #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2003.13870
published in arXiv (Cornell University) (Cornell University) · Accepted to CVPR 2020
arxiv created 2020/03/30 · openalex publication_date 2020/03/30 · arxiv updated 2020/04/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Traditionally multi-object tracking and object detection are performed using separate systems with most prior works focusing exclusively on one of these aspects over the other. Tracking systems clearly benefit from having access to accurate detections, however and there is ample evidence in literature that detectors can benefit from tracking which, for example, can help to smooth predictions over time. In this paper we focus on the tracking-by-detection paradigm for autonomous driving where both tasks are mission critical. We propose a conceptually simple and efficient joint model of detection and tracking, called RetinaTrack, which modifies the popular single stage RetinaNet approach such that it is amenable to instance-level embedding training. We show, via evaluations on the Waymo Open Dataset, that we outperform a recent state of the art tracking algorithm while requiring significantly less computation. We believe that our simple yet effective approach can serve as a strong baseline for future work in this area.