An Automatic Detection Algorithm of Metro Passenger Boarding and Alighting Based on Deep Learning and Optical Flow

Urban rail transit is one of the important application areas of autonomous driving, which will require an algorithm to monitor the exchange of passengers between metro carriages and stations. To this end, this article first proposes a metro passenger detection (MPD) algorithm to track passengers getting on or off, namely the MPD algorithm. The algorithm is composed of two MetroNexts and an optical flow algorithm. The two MetroNexts are based on a novel multiple scales attention convolution (MSAC) block and detect metro carriages and passengers fast and accurately with small model size. The optical flow algorithm predicts the direction of moving passengers, which help the MPD algorithm filter out unrelated ones. Combining the coordinates and moving direction of passengers, the MPD algorithm can determine whether passengers are boarding or alighting. Based on various benchmark data sets and a new metro station data set, the experimental results have demonstrated that the MSAC block is effective to improve detection accuracy. Compared with the existing state-of-the-art detection networks, the two MetroNexts have achieved competitive results with good time/memory efficiency on pedestrian data sets. On the metro station data set, the MPD algorithm robustly recognizes target passengers, the detection speed of which remains competitive even on the embedded platform, thus becoming an intelligent instrument of the metro station.