A Gray Relational Analysis-Based Motion Detection Algorithm for Real-World Surveillance Sensor Deployment

The automated detection of moving objects is an essential task for any intelligent transportation system. To achieve reliable and accurate motion detection in video streams acquired from either jitter or static cameras in real-world scenarios, a novel motion detection approach based on gray relational analysis is proposed in this paper, which integrates a multi-sample background generation module and a moving object detection module. As our experimental results demonstrate, the proposed approach attains superior motion detection performance compared to other state-of-the-art techniques based on qualitative and quantitative evaluations. In addition, the processing speed of the proposed approach makes it suitable for real-time applications.