Edge-centric Video Surveillance System Based on Event-driven Rate Adaptation for 24-hour Monitoring

In this paper, to sustain a high-quality 24-hour video surveillance (i.e., high reliability) and reduce redundant video traffic volume (i.e., network friendliness), we propose an edge-centric video surveillance system that provides flexible adaptive control of the image enhancement process and video quality based on an event-driven adaptation. In the proposed system, the video bitrate is adaptively controlled according to the contrast of captured videos and conditions in a monitored area (e.g., "normal", "caution", and "alert"). To confirm the system performance, we evaluate objective image quality, accuracy of human detection and video traffic volume generated by the proposed system. Evaluations conclude that the system can reduce the video traffic while sustaining high-quality visibility.