MSight: An Edge-Cloud Infrastructure-based Perception System for Connected Automated Vehicles

TL;DR

MSight is a roadside perception system leveraging infrastructure sensors to improve real-time detection, localization, and trajectory prediction for connected automated vehicles, enhancing safety and efficiency with minimal latency.

Contribution

This paper introduces MSight, a novel infrastructure-based perception system that provides robust, lane-level vehicle detection and tracking for CAVs, outperforming onboard perception in occlusion and accuracy.

Findings

MSight achieves lane-level accuracy in vehicle detection.

The system operates with minimal latency in real-time scenarios.

MSight demonstrates potential to improve CAV safety and traffic efficiency.

Abstract

As vehicular communication and networking technologies continue to advance, infrastructure-based roadside perception emerges as a pivotal tool for connected automated vehicle (CAV) applications. Due to their elevated positioning, roadside sensors, including cameras and lidars, often enjoy unobstructed views with diminished object occlusion. This provides them a distinct advantage over onboard perception, enabling more robust and accurate detection of road objects. This paper presents MSight, a cutting-edge roadside perception system specifically designed for CAVs. MSight offers real-time vehicle detection, localization, tracking, and short-term trajectory prediction. Evaluations underscore the system's capability to uphold lane-level accuracy with minimal latency, revealing a range of potential applications to enhance CAV safety and efficiency. Presently, MSight operates 24/7 at a two-lane roundabout in the City of Ann Arbor, Michigan.