A Lightweight Pedestrian Intrusion Detection Algorithm Based on On-Board Video

In order to enhance the real-time perception of the environment of the train and ensure safety, it is necessary to detect intrusion. Most of the intrusion detection algorithms have large parameters and slow speed, so they cannot be well applied in high-speed trains. Therefore, this paper proposes a lightweight pedestrian intrusion detection algorithm with on-board video. First, the lightweight object detection algorithm is used to realize pedestrian detection in the whole scene. Second, the railway track area is extracted by a lightweight semantic segmentation algorithm. Finally, by judging the coordinate position, the pedestrian intrusion detection in the railway track area is realized. In experiments, the positive detection rate is 94.84%, and the missing detection rate is 0.97%, and the false detection rate is 0.81%, which can effectively detect the pedestrian intrusion in the railway track and further improve the intelligent perception system of railway operation environment, which has practical significance and application value for railway safety.