Optimizing Camera Configurations for Multi-View Pedestrian Detection
This work addresses the challenge of optimizing camera layouts for pedestrian detection systems, which is incremental as it builds on existing multi-view detection methods by automating configuration design.
The paper tackles the problem of designing camera configurations for multi-view pedestrian detection by introducing a transformer-based generator that uses reinforcement learning to optimize camera placements, directions, and fields-of-view, resulting in configurations that outperform random search, heuristic-based methods, and human expert designs in simulation scenarios.
Jointly considering multiple camera views (multi-view) is very effective for pedestrian detection under occlusion. For such multi-view systems, it is critical to have well-designed camera configurations, including camera locations, directions, and fields-of-view (FoVs). Usually, these configurations are crafted based on human experience or heuristics. In this work, we present a novel solution that features a transformer-based camera configuration generator. Using reinforcement learning, this generator autonomously explores vast combinations within the action space and searches for configurations that give the highest detection accuracy according to the training dataset. The generator learns advanced techniques like maximizing coverage, minimizing occlusion, and promoting collaboration. Across multiple simulation scenarios, the configurations generated by our transformer-based model consistently outperform random search, heuristic-based methods, and configurations designed by human experts, shedding light on future camera layout optimization.