The Scheme of the Cooperative Gun-Dome Face Image Acquisition in Surveillance Sensors

How to automatically realize acquisition, refining and fast retrieval of the pedestrian face image in surveillance video is of great importance in public security visual surveillance field. This paper proposes a new gun-dome camera cooperative system which solves the above problem partly. The system adopts static panorama-variable view dual-camera cooperative video-monitoring system. As respect to the face detection, the deep learning architecture is exploited and proves it effectiveness. The experimental results show the effectiveness and efficiency of the dual-camera system in close-up face image acquisition.