Leveraging Temporal Contexts to Enhance Vehicle-Infrastructure Cooperative Perception

TL;DR

This paper introduces CTCE, a framework that enhances vehicle-infrastructure cooperative perception by leveraging temporal contexts and fusion modules, improving detection accuracy and robustness under communication constraints.

Contribution

The paper proposes a novel CTCE framework with temporal query enhancement and fusion modules, addressing communication limitations and improving cooperative perception performance.

Findings

CTCE outperforms QUEST with 3.8% and 1.3% mAP improvements.

The framework maintains robustness under communication interruptions.

Temporal contexts significantly boost perception accuracy.

Abstract

Infrastructure sensors installed at elevated positions offer a broader perception range and encounter fewer occlusions. Integrating both infrastructure and ego-vehicle data through V2X communication, known as vehicle-infrastructure cooperation, has shown considerable advantages in enhancing perception capabilities and addressing corner cases encountered in single-vehicle autonomous driving. However, cooperative perception still faces numerous challenges, including limited communication bandwidth and practical communication interruptions. In this paper, we propose CTCE, a novel framework for cooperative 3D object detection. This framework transmits queries with temporal contexts enhancement, effectively balancing transmission efficiency and performance to accommodate real-world communication conditions. Additionally, we propose a temporal-guided fusion module to further improve performance. The roadside temporal enhancement and vehicle-side spatial-temporal fusion together constitute a multi-level temporal contexts integration mechanism, fully leveraging temporal information to enhance performance. Furthermore, a motion-aware reconstruction module is introduced to recover lost roadside queries due to communication interruptions. Experimental results on V2X-Seq and V2X-Sim datasets demonstrate that CTCE outperforms the baseline QUEST, achieving improvements of 3.8% and 1.3% in mAP, respectively. Experiments under communication interruption conditions validate CTCE's robustness to communication interruptions.