Research on Multi-Target Detection and Tracking Algorithm Based on Improved YOLOv5

A detection and tracking algorithm based on improved YOLOv5 is proposed for the poor recognition and tracking of obscured targets and small-sized targets. The K-means ++ algorithm is used to cluster to obtain new anchor values; the CIOU-NMS is introduced to improve the missed detection problem when the target is obscured; the CBAM is proposed to be embedded into the Backbone and Neck part to improve the feature extraction capability of the algorithm for small targets. DeepSORT is chosen as the multi-target tracker to plot the motion trajectory of the target in real time. The experimental results show that the improved algorithm has a 2.1% improvement in detection accuracy and a detection speed of 32.32/s, satisfying real-time efficient detection with better tracking.