A UAV Aerial Image Target Detection Algorithm Based on YOLOv7 Improved Model

Author:

Qin Jie1,Yu Weihua1,Feng Xiaoxi2,Meng Zuqiang13,Tan Chaohong3

Affiliation:

1. School of Computer Science and Electronic Engineering, Guangxi University, Nanning 530004, China

2. School of Electrical Engineering, Guangxi University, Nanning 530004, China

3. Guangxi Key Laboratory of Digital Infrastructure, Guangxi Zhuang Autonomous Region Information Center, Nanning 530201, China

Abstract

To address the challenges of multi-scale objects, dense distributions, occlusions, and numerous small targets in UAV image detection, we present CMS-YOLOv7, a real-time target detection method based on an enhanced YOLOv7 model. Firstly, the detection layer P2 for small targets was added to YOLOv7 to enhance the detection ability of small and medium-sized targets, and the deep detection head P5 was taken out to mitigate the influence of excessive downsampling on small target images. The anchor frame was calculated by the K-means++ method. Using the concept of Inner-IoU, the Inner-MPDIoU loss function was constructed to control the range of the auxiliary border and improve detection performance. Furthermore, the CARAFE module was introduced to replace traditional upsampling methods, offering improved integration of semantic information during the image upsampling process and enhancing feature mapping accuracy. Simultaneously, during the feature extraction stage, a non-strided convolutional SPD-Conv module was constructed using space-to-depth techniques. This module replaced certain convolutional operations to minimize the loss of fine-grained information and improve the model’s ability to extract features from small targets. Experiments on the UAV aerial photo dataset VisDrone2019 demonstrated that compared with the baseline YOLOv7 object detection algorithm, CMS-YOLOv7 achieved an improvement of 3.5% mAP@0.5, 3.0% mAP@0.5:0.95, and the number of parameters decreased by 18.54 M. The ability of small target detection was significantly enhanced.

Funder

National Natural Science Foundation of China

Open Project Program of Guangxi Key Laboratory of Digital Infrastructure

National Training Program of Innovation and Entrepreneurship for Undergraduates

Publisher

MDPI AG

Reference36 articles.

1. Review on the technological development and application of UAV systems;Fan;Chin. J. Electron.,2020

2. Joint optimisation of real-time deployment and resource allocation for UAV-aided disaster emergency communications;Nguyen;IEEE J. Sel. Areas Commun.,2021

3. Workflow for capturing information and characterizing difficult-to-access geological outcrops using unmanned aerial vehicle-based digital photogrammetric data;Villarreal;J. Ind. Inf. Integr.,2022

4. Object detection with deep learning: A review;Zhao;IEEE Trans. Neural Netw. Learn. Syst.,2019

5. Deep learning;LeCun;Nature,2015

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3