Vehicle detection in aerial image based on deep learning

Abstract

At present, urban traffic congestion is becoming more and more serious. Traditional vehicle detection methods generally have problems of low precision and low recognition rate. In order to solve these problems, a vehicle detection method in aerial image based on deep learning is proposed. The method uses the YOLOv3 algorithm and optimizes the algorithm network, increase the number of rasters of the final predicted output, improves the detection ability of the network for dense groups, and verifies the effect by training a new model. The experimental results show that the new training model has a good effect on vehicle detection, which solves the problem of low detection and recognition rate of urban traffic vehicle detection, and makes good predictions and judgments on urban traffic congestion.