Real-time Vehicle Pedestrian Detection and Tracking Algorithm based on Computer Vision

Detection and tracking of vehicle pedestrians have important application values in the fields of intelligent driving and traffic monitoring. To this end, the study improves the YOLOv5s algorithm by replacing the backbone network of YOLOv5s with SGWin Transformer V2, and introduces the CBAM module, while optimizing the SIoU loss function to obtain the improved YOLOv5s algorithm. The improved YOLOv5s algorithm is used for the detection of vehicles and pedestrians in real-time video, then the fusion model is used to correlate the motion trajectories of the detected targets, and finally the Kalman filter tracking algorithm is applied to correct the tracking prediction results to realize the fast, accurate and continuous detection and tracking of vehicles and pedestrians. The results show that the tracking and detection accuracy of the method used in the study is 84.7%, and 51 vehicles and 32 pedestrians are accurately labeled. Research algorithms can accurately achieve vehicle and pedestrian recognition in complex road environments, and provide technical guidance for object recognition of the same type.