Collaborative Association Network for Multi-view Multi-Human Association and Tracking using Constraint Optimization and Object Search

Abstract

Multi-view multi-human association and tracking (MvMHAT) enhances scene perception using multiple cameras, crucial for applications such as surveillance and crowd analysis. Inherent feature disparities between views complicate similarity calculations. Recent works combine representation and motion information to address this issue. However, existing methods neglect parallax-induced angular issues and inconsistent object counts across views. To address these challenges, we introduce a collaborative association network combining temporal and spatial clues. Our method incorporates multi-scale adaptive alignment, cross-view and cross-frame feature fusion, to obtain comprehensive global feature representations for each object. We also formulate data association as a mixed-constraint optimization problem to enhance the scalability of our method. Additionally, we propose a novel object search loss to improve cross-view and cross-frame data association. Experiments on benchmarks demonstrate the efficiency of our method in MvMHAT task, significantly outperforming state-of-the-art methods.