Affiliation:
1. College of Field Engineering, Army Engineering University of PLA, Nanjing 210007, China
Abstract
Due to the broad usage and widespread popularity of drones, the demand for a more accurate object detection algorithm for images captured by drone platforms has become increasingly urgent. This article addresses this issue by first analyzing the unique characteristics of datasets related to drones. We then select the widely used YOLOv7 algorithm as the foundation and conduct a comprehensive analysis of its limitations, proposing a targeted solution. In order to enhance the network’s ability to extract features from small objects, we introduce non-strided convolution modules and integrate modules that utilize attention mechanism principles into the baseline network. Additionally, we improve the semantic information expression for small targets by optimizing the feature fusion process in the network. During training, we adopt the latest Lion optimizer and MPDIoU loss to further boost the overall performance of the network. The improved network achieves impressive results, with mAP50 scores of 56.8% and 94.6% on the VisDrone2019 and NWPU VHR-10 datasets, respectively, particularly in detecting small objects.
Funder
National Natural Science Foundation of China
Reference56 articles.
1. Unmanned aerial vehicles: Applications, techniques, and challenges as aerial base stations;Rolly;Int. J. Distrib. Sens. Netw.,2022
2. Object Detection in 20 Years: A Survey;Zou;Proc. IEEE,2023
3. Wu, X., Li, W., Hong, D., Tao, R., and Du, Q. (2021). Deep Learning for UAV-based Object Detection and Tracking: A Survey. arXiv.
4. A Survey of Deep Learning-based Object Detection Methods and Datasets for Overhead Imagery;Kang;IEEE Access,2022
5. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2022, January 17–24). YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献