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
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