RetinaTrack: Online Single Stage Joint Detection and Tracking
arXiv:2003.13870
Abstract
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.
arXiv commentAccepted to CVPR 2020
References in corpus (14)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- In Defense of the Triplet Loss for Person Re-Identification
- SGDR: Stochastic Gradient Descent with Warm Restarts
- MOT16: A Benchmark for Multi-Object Tracking
- FCOS: Fully Convolutional One-Stage Object Detection
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
- CornerNet-Lite: Efficient Keypoint Based Object Detection
- Seq-NMS for Video Object Detection
- MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
- Generating Multi-Agent Trajectories using Programmatic Weak Supervision
- Mobile Video Object Detection with Temporally-Aware Feature Maps
- Scale MLPerf-0.6 models on Google TPU-v3 Pods