Pedestrian Detection Algorithm Based on ViBe and YOLO

As more and more monitoring devices are deployed in various cities around the world, the technology of intelligent analysis and processing of video image data based on the computer is becoming more and more mature. This paper adopts an algorithm based on the combination of traditional ViBe and YOLO algorithm to realize the pedestrian detection of internal personnel in the surveillance video. Firstly, ViBe algorithm is used to detect pedestrians once, and some pedestrian frames are selected. Then the pedestrian frames are sent to YOLO network for secondary detection. The second pedestrian detection based on deep learning uses K-means algorithm to complete the clustering of prior frames, and then uses the CSPDarkNet53 network to extract pedestrian features. In order to improve the ability of YOLO small target detection, SPP-Net structure is added to the YOLO model to improve the accuracy of small target detection. The self-built pedestrian dataset used to train and test on the constructed network. The experimental results show that the detection algorithm based on the combination of ViBe and YOLO optimizes the regression of pedestrian boundary frame improves the positioning accuracy of pedestrians.