Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras

TL;DR

This paper introduces a real-time, full-stack traffic scene perception framework using roadside cameras, featuring modular design and landmark-based 3D localization, suitable for various camera types and deployed in real-world settings.

Contribution

It presents a modular roadside perception system with landmark-based 3D localization that simplifies training and supports diverse camera configurations for autonomous driving infrastructure.

Findings

Operates in real-time with less than 20ms delay

Provides high-precision vehicle trajectories

Works with optical and thermal cameras

Abstract

We propose a novel and pragmatic framework for traffic scene perception with roadside cameras. The proposed framework covers a full-stack of roadside perception pipeline for infrastructure-assisted autonomous driving, including object detection, object localization, object tracking, and multi-camera information fusion. Unlike previous vision-based perception frameworks rely upon depth offset or 3D annotation at training, we adopt a modular decoupling design and introduce a landmark-based 3D localization method, where the detection and localization can be well decoupled so that the model can be easily trained based on only 2D annotations. The proposed framework applies to either optical or thermal cameras with pinhole or fish-eye lenses. Our framework is deployed at a two-lane roundabout located at Ellsworth Rd. and State St., Ann Arbor, MI, USA, providing 7x24 real-time traffic flow monitoring and high-precision vehicle trajectory extraction. The whole system runs efficiently on a low-power edge computing device with all-component end-to-end delay of less than 20ms.