Spatiotemporal Feature Alignment and Weighted Fusion in Collaborative Perception Enabled by Network Synchronization and Age of Information

Abstract

Collaborative perception in Internet of Vehicles (IoV) aggregates multi-vehicle observations for broader scene coverage and improved decision-making. However, fusion quality degrades under spatiotemporal heterogeneity from unsynchronized clocks, communication delays, and motion variations across vehicles. Prior work mitigates these through spatial transformations or fixed time-offset corrections, overlooking time-varying clock drifts and delays that cause persistent feature misalignment. To address these challenges, we propose a spatiotemporal feature alignment and weighted fusion framework. Specifically, network synchronization is introduced to estimate inter-vehicle clock states and establish a common temporal reference, onto which local feature timestamps can be mapped. Based on this, we define delivery-time Age of Information (AoI) to measure the expected age of a shared feature when it becomes available for fusion, by accounting for its generation time and the Vehicle-to-Everything (V2X) communication delay. The proposed spatiotemporal feature alignment then compensates asynchronous neighbor features toward the fusion time, rather than directly aggregating delayed features. Since different spatial regions contribute unequally to perception, we further perform Region-of-Interest (RoI)-level weighted fusion, where the fusion weights are determined by delivery-time AoI, synchronization reliability, and content complementarity. As a result, timely, reliable, and complementary regions are emphasized, while stale, uncertain, or redundant regions are down-weighted. Simulation results further demonstrate consistent accuracy improvements over representative baselines under clock drift, varying communication conditions, temporal misalignment levels, and vehicle numbers.

Accepted by IEEE Transactions on Cognitive Communications and Networking