计算机工程与应用2024，Vol.60Issue(20)：189-197,9.DOI:10.3778/j.issn.1002-8331.2312-0100
改进YOLOv7的航拍图像目标检测
Object Detection Based on Improved YOLOv7 for UAV Aerial Image
摘要
Abstract
An improved YOLOv7 aerial image object detection algorithm is proposed to solve the problems of low detec-tion accuracy caused by mesoscale changes,small targets and dense occlusion in UAV aerial images.Firstly,a weighted sampling module with joint dynamic convolution is designed to capture features from multiple dimensions and improve the feature extraction ability of the model.Secondly,add a shallow feature detection head to retain more detailed information and enhance the ability to utilize small target features.Then,a multi-scale feature aggregation module(C2-Res2Block)with residual structure is constructed in the feature fusion part to make the model fuse rich multi-scale information.Finally,the MPDIoU measure is used to replace the traditional IOU to calculate the boundary regression loss and improve the localization ability of the model to the densely occluding target.Experiments on UAV aerial photography data set VisDrone2019 show that the improved algorithm is 4.3 percentage points higher than the original model on mAP@0.5,2.4 percentage points on mAP@0.5:0.95,the number of parameters is reduced by 6.81×106,and the detection accuracy is higher than the current mainstream object detection algorithms.It effectively improves the detection accuracy of UAV aerial images,and obviously improves the false detection and missing detection of aerial objects.关键词
目标检测/YOLOv7/动态卷积/检测头/C2-Res2Block/MPDIoUKey words
object detection/YOLOv7/dynamic convolution/detection head/C2-Res2Block/MPDIoU分类
计算机与自动化引用本文复制引用
崔丽群,曹华维..改进YOLOv7的航拍图像目标检测[J].计算机工程与应用,2024,60(20):189-197,9.基金项目
辽宁省高等学校基本科研项目(LJKMZ20220699). （LJKMZ20220699）
