STCo: A Communication-Efficient Spatiotemporal Context-Aware Framework for V2V Collaborative Perception

Multi-vehicle collaborative perception is fundamental to realizing Level 4+ autonomous driving by enabling connected vehicles to share and integrate sensor data for enhanced situational awareness. Under emerging Internet of Things (IoT) architectures, fleets of vehicles form dynamic, decentralized networks. In practice, however, deployment is hampered by three core challenges: (1) transmission latency in vehicle-to-vehicle (V2V) links, (2) data transmission constrained by limited communication bandwidth, and (3) the complexity of fusing asynchronous, multi-source data streams. To overcome these obstacles, this paper presents STCo, a spatio-temporal context-aware and communication-efficient framework for multi-vehicle collaborative perception. First, a spatio-temporal context modeling mechanism is devised to enhance perceptual continuity and mitigate communication asynchrony in IoT environments. Second, a cross-vehicle sensor perspective disparity mining algorithm leverages distributed observations to extract high-value complementary information. Third, a multi-source data fusion paradigm unifies diverse perception inputs into a unified representation from the ego vehicle’s perspective, thereby strengthening feature correlations. This paper validates STCo on both the real-world V2V4Real dataset and the large-scale simulated OPV2V benchmark. Experimental results demonstrate that STCo outperforms state-of-the-art methods in detection accuracy while substantially reducing communication overhead, highlighting its efficacy and practicality for IoT-enabled autonomous driving systems.