YOLOv5-Based Vehicle Detection Method for High-Resolution UAV Images

Figure 1

As can be seen from the figure, the vehicle images collected by the UAV are divided into a training set and a test set. The training set is processed by an adaptive clipping algorithm and then trained using YOLOv5. The images from the test set are adaptively chunked and fed into the improved YOLOv5 for detection. The detection results of both branches are nonmaximum suppressed to obtain the final detection frame.