English

Real-time Object Detection for Streaming Perception

Computer Vision and Pattern Recognition 2022-03-30 v2

Abstract

Autonomous driving requires the model to perceive the environment and (re)act within a low latency for safety. While past works ignore the inevitable changes in the environment after processing, streaming perception is proposed to jointly evaluate the latency and accuracy into a single metric for video online perception. In this paper, instead of searching trade-offs between accuracy and speed like previous works, we point out that endowing real-time models with the ability to predict the future is the key to dealing with this problem. We build a simple and effective framework for streaming perception. It equips a novel DualFlow Perception module (DFP), which includes dynamic and static flows to capture the moving trend and basic detection feature for streaming prediction. Further, we introduce a Trend-Aware Loss (TAL) combined with a trend factor to generate adaptive weights for objects with different moving speeds. Our simple method achieves competitive performance on Argoverse-HD dataset and improves the AP by 4.9% compared to the strong baseline, validating its effectiveness. Our code will be made available at https://github.com/yancie-yjr/StreamYOLO.

Keywords

Cite

@article{arxiv.2203.12338,
  title  = {Real-time Object Detection for Streaming Perception},
  author = {Jinrong Yang and Songtao Liu and Zeming Li and Xiaoping Li and Jian Sun},
  journal= {arXiv preprint arXiv:2203.12338},
  year   = {2022}
}

Comments

CVPR 2022 Accepted Paper (Oral)

R2 v1 2026-06-24T10:23:11.759Z