Graph Convolutional Network for Multi-Target Multi-Camera Vehicle Tracking
This addresses multi-camera vehicle tracking for surveillance applications, representing an incremental improvement over existing methods.
The paper tackles the problem of associating vehicle trajectories across multiple cameras by proposing a Graph Convolutional Network that processes all cameras globally, handling unsynchronizations and class imbalance, and it outperforms related work in generalization without manual annotations.
This letter focuses on the task of Multi-Target Multi-Camera vehicle tracking. We propose to associate single-camera trajectories into multi-camera global trajectories by training a Graph Convolutional Network. Our approach simultaneously processes all cameras providing a global solution, and it is also robust to large cameras unsynchronizations. Furthermore, we design a new loss function to deal with class imbalance. Our proposal outperforms the related work showing better generalization and without requiring ad-hoc manual annotations or thresholds, unlike compared approaches.