Target detection method for UAV aerial images based on improved yolo V5

Abstract

The invention discloses an improved YOLO V5-based target detection method for aerial images of unmanned aerial vehicles, which belongs to the field of deep learning and target detection. In this method, firstly, the relevant data set is constructed by using aerial images of drones, and then the convolutional layer is used to replace the slice layer in the Focus module in the backbone network of YOLO V5, and then the image features are further processed by using the Neck part, and then the high-altitude aerial photography of the drone is used. The target stray distribution caused by the viewing angle and the target pixel ratio is too small. In the network prediction layer, the large detection head of 76×76×255 is optimized and eliminated, and the anchor frame is adjusted at the same time. Finally, the generalized intersection ratio and average accuracy And the inference speed evaluates the target detection performance. On the basis of improving the recognition accuracy and feature extraction performance, the method can realize the rapid and accurate detection of the target in the aerial image of the UAV.

Description

technical field [0001] The invention relates to an improved YOLO V5-based target detection method for aerial images of unmanned aerial vehicles, belonging to the technical field of deep learning and target detection. Background technique [0002] The intelligent perception of drone images can not only efficiently extract ground object information, but also expand the scene understanding ability of drones, and provide technical support for autonomous detection and flight of drones. Target detection is one of the key technologies to improve the intelligent perception of UAV images. However, UAV aerial images generally have the characteristics of complex background, dense distribution of targets, small scale, and large angle differences of the same category of targets. The traditional "manual feature extraction + classifier-based" target detection algorithm can no longer meet the detection accuracy requirements in complex environments and multi-scales. With the high efficiency...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that YOLO V5 is applied to the target detection of UAV aerial images because the detection targets are aggregated into small targets, which makes the detection difficult, and the backbone network is complicated, resulting in insufficient real-time performance. YOLO V5's UAV aerial photography target detection method, which can improve the YOLO V5 backbone network architecture on the premise of improving the accuracy of the original YOLO V5, lightweight its network model, improve its reasoning speed, and achieve fast and accurate UAV Aerial Object Detection

Images