基于改进YOLOv5算法的无人机遥感影像车辆检测研究
Research on Vehicle Detection in UAV Remote Sensing Image Based on Improved YOLOv5
DOI: 10.12677/AIRR.2022.114034, PDF,    科研立项经费支持
作者: 耿利川：许昌学院，河南 许昌；智慧中原地理信息技术河南省协同创新中心，河南 郑州；时空信息感知与融合技术自然资源部重点实验室，河南 郑州；王帮进, 崔云龙：浙江省测绘科学技术研究院，浙江 杭州；缑艳方：许昌学院，河南 许昌
关键词: 目标检测；YOLOv5；无人机遥感；损失函数；Object Detection； YOLOv5； UAV Remote Sensing； Cost Function
摘要: 针对无人机遥感影像中的车辆检测问题，本文对YOLOv5算法中损失函数仅利用边界框长宽比不能反映边界框宽高分别与其置信度的真实差异的缺点，对损失函数进行了改进，消除了因为不能反映宽高真实差异引起的收敛过慢问题。利用改进的YOLOv5算法进行了训练和检测，验证了该算法对于无人机航拍影像中车辆检测的有效性。
Abstract: Aiming at the problem of vehicle detection in UAV remote sensing images, this paper improves the loss function of YOLOv5 algorithm, which only uses the length-width ratio of the bounding box and cannot reflect the real difference between the width and height of the bounding box and its confidence. It eliminates the problem of slow convergence caused by the failure to reflect the real difference in width and height, and uses the improved YOLOv5 algorithm for training and detection. The effectiveness of the algorithm for vehicle detection in UAV aerial images is verified.
文章引用：耿利川, 王帮进, 崔云龙, 缑艳方. 基于改进YOLOv5算法的无人机遥感影像车辆检测研究[J]. 人工智能与机器人研究, 2022, 11(4): 325-332. https://doi.org/10.12677/AIRR.2022.114034

参考文献

[1] 王利鑫. 基于改进的Faster R-CNN的无人机影像车辆检测[D]: [硕士学位论文]. 湘潭: 湖南科技大学, 2019.
[2] 董丽君, 曾志高, 易胜秋. 基于YOLOv5的遥感图像目标检测[J]. 湖南工业大学学报, 2022, 36(3): 44-50.
[3] 谭路文, 哈斯巴干, 陈超民, 等. 基于深度学习的无人机遥感影像车辆检测[J]. 红外, 2022, 43(5): 41-48.
[4] Wang, C., et al. (2019) Multiscale Visual Attention Networks for Object Detection in VHR Remote Sensing Images. IEEE Geoscience and Remote Sensing Letters, 16, 310-314. [Google Scholar] [CrossRef] 
[5] Zhang, Y., et al. (2019) Hierarchical and Robust Convolutional Neural Network for Very High-Resolution Remote Sensing Object Detection. IEEE Transactions on Geoscience and Remote Sensing, 57, 5535-5548. [Google Scholar] [CrossRef] 
[6] Cheng, G., et al. (2016) Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 54, 7405-7415. [Google Scholar] [CrossRef] 
[7] Li, K., et al. (2017) Rotation-Insensitive and Context-Augmented Object Detection in Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 56, 2337-2348. [Google Scholar] [CrossRef] 
[8] Wu, X., et al. (2019) ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features. IEEE Transactions on Geoscience and Remote Sensing, 57, 5146-5158. [Google Scholar] [CrossRef] 
[9] Ren, S., He, K., Girshick, R., et al. (2017) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis & Machine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] 
[10] He, K.M., Gkioxari, G., Dollar, P. and Girshick, R. (2017) Mask R-CNN. IEEE International Conference on Computer Vision, Venice, 22-29 October 2017, 2980-2988. [Google Scholar] [CrossRef] 
[11] Lin, T.Y., Goyal, P., Girshick, R., et al. (2017) Focal Loss for Dense Object Detection. IEEE Transactions on Pattern Analysis & Machine Intelligence, 99, 999-3007. [Google Scholar] [CrossRef] 
[12] Zhang, H.K., Chang, H., Ma, B.P., Wang, N.Y. and Chen, X.L. (2020) Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training. European Conference on Computer Vision, Glasgow, 23-28 August 2020, 260-275. [Google Scholar] [CrossRef] 
[13] Kim, K.-J. and Lee, H.S. (2020) Probabilistic Anchor Assignment with IoU Prediction for Object Detection. 2020 European Conference on Computer Vision, ECCV, Glasgow, 23-28 August 2020, 1-17. [Google Scholar] [CrossRef] 
[14] Zhang, S., Chi, C., Yao, et al. (2020) Bridging the Gap between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 9759-9768. [Google Scholar] [CrossRef] 
[15] Redmon, J., Divvala, S.K., Ross, B., et al. (2015) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[16] Redmon, J. and Farhadi, A. (2017) YOLO9000: Better, Faster, Stronger. IEEE Conference on Computer Vision & Pattern Recognition, Honolulu, 21-26 July 2017, 6517-6525. [Google Scholar] [CrossRef] 
[17] Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incremental Improvement.
[18] Bochkovskiy, A., Wang, C.Y. and Liao, H. (2020) YOLOv4: Optimal Speed and Accuracy of Object Detection.
[19] 邢宇驰, 李大军, 叶发茂. 基于YOLOv5的遥感图像目标检测[J]. 江西科学, 2021, 39(4): 725-732.
[20] 李柯泉, 陈燕, 刘佳晨, 等. 基于深度学习的目标检测算法综述[J]. 计算机工程, 2022, 48(7): 1-12.
[21] 马跃, 赵志浩, 尹震宇, 等. 分段反卷积改进SSD的目标检测算法[J]. 小型微型计算机系统, 2021, 42(7): 1415-1420.
[22] 李科岑, 王晓强, 林浩, 等. 深度学习中的单阶段小目标检测方法综述[J]. 计算机科学与探索, 2022, 16(1): 41-58.
[23] 冯加明, 储茂祥, 杨永辉, 等. 改进YOLOv3算法的车辆信息检测[J]. 重庆大学学报, 2021, 45(12): 71-79.
[24] 汪昱东, 郭继昌, 王天保. 一种改进的雾天图像行人和车辆检测算法[J]. 西安电子科技大学学报, 2020, 47(4): 70-77.
[25] Yu, J., Jiang, Y., Wang, Z., et al. (2016) UnitBox: An Advanced Object Detection Network. Proceedings of the 24th ACM International Conference on Multimedia, New York, October 2016, 516-520. [Google Scholar] [CrossRef] 
[26] Rezatofighi, H., Tsoi, N., Gwak, J.Y., et al. (2019) Generalized Intersection over Union: A Metric and a Loss for Bounding Box Regression. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 658-666. [Google Scholar] [CrossRef] 
[27] Zheng, Z., Wang, P., Liu, W., et al. (2019) Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 12993-13000. [Google Scholar] [CrossRef] 
[28] Zhang, Y.F., Ren, W., Zhang, Z., et al. (2021) Focal and Efficient IOU Loss for Accurate Bounding Box Regression. Neurocomputing, 506, 146-157. [Google Scholar] [CrossRef] 

为你推荐