Rethinking the Role of Infrastructure in Collaborative Perception

TL;DR

This paper evaluates the significance of infrastructure data in collaborative perception, showing that infrastructure-enhanced systems significantly improve detection accuracy and robustness over vehicle-centric approaches.

Contribution

It provides the first extensive quantitative analysis comparing vehicle-centric and infra-centric collaborative perception, highlighting the benefits of infrastructure data.

Findings

Infrastructure data improves 3D detection accuracy by up to 10.30%.

Infra-centric CP enhances noise robustness and increases accuracy by up to 46.47%.

Quantitative comparison between vehicle-centric and infra-centric CP approaches.

Abstract

Collaborative Perception (CP) is a process in which an ego agent receives and fuses sensor information from surrounding vehicles and infrastructure to enhance its perception capability. To evaluate the need for infrastructure equipped with sensors, extensive and quantitative analysis of the role of infrastructure data in CP is crucial, yet remains underexplored. To address this gap, we first quantitatively assess the importance of infrastructure data in existing vehicle-centric CP, where the ego agent is a vehicle. Furthermore, we compare vehicle-centric CP with infra-centric CP, where the ego agent is now the infrastructure, to evaluate the effectiveness of each approach. Our results demonstrate that incorporating infrastructure data improves 3D detection accuracy by up to 10.30%, and infra-centric CP shows enhanced noise robustness and increases accuracy by up to 46.47% compared with vehicle-centric CP.