Systematic Literature Review on Vehicular Collaborative Perception - A Computer Vision Perspective

The systematic literature review on vehicular collaborative perception, published on November 12, 2025, addresses the pressing need for reliable perception capabilities in autonomous vehicles. Despite advancements in artificial intelligence and sensor technologies, single-vehicle systems face significant challenges, such as visual occlusions and limited long-range detection. Collaborative perception, facilitated by vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, emerges as a promising solution to these limitations. This review, adhering to PRISMA 2020 guidelines, synthesizes findings from 106 peer-reviewed articles, revealing common trends and research gaps. By systematically analyzing existing literature, the study not only highlights the importance of collaborative approaches in computer vision but also sets a foundation for future research directions, ultimately aiming to enhance the effectiveness and safety of autonomous vehicles.