长安大学信息工程学院;
针对无人机影像中道路小目标漏检和目标之间遮挡导致的目标检测精度低、鲁棒性差等问题，提出一种多尺度的道路目标检测算法——YOLOv5-FTCE。执行多尺度的目标定位改进，采用完全交并比(Complete Intersection over Union, CIoU)边界框损失，通过K-means算法对先验框进行重聚类，调整先验框的锚框参数并增加一个针对小目标的YOLO检测头；引入Transformer encoder结构融入C3模块改进Backbone网络，增强网络对不同局部信息的捕获能力；选用基于特征重组的Content-Aware ReAssembly of FEatures (CARAFE)模块进行上采样，提高上采样性能的同时减少特征处理过程中的信息损失；引入高效注意力模块(Efficient Attention Module, EAM)融合空间和通道信息，对网络中重要的信息进行增强。结果表明，YOLOv5-FTCE算法在VisDrone数据集上，检测精确率相比原始算法提高了9.5%,mAP50提高了8.9%,优于YOLOv7等其他常见的算法，有效改善了道路小目标和遮挡目标的漏检现象。
| 659 | 0 | 187 |
| 下载次数 | 被引频次 | 阅读次数 |
[1] 范智翰.基于YOLO的道路目标检测研究与应用[D].成都：四川大学，2021.
[2] 张菁，吴鑫嘉，赵晓蕾，等.全局关系注意力引导场景约束的高分辨率遥感影像目标检测[J].电子与信息学报，2022,44(8):2924-2931.
[3] 陈旭，彭冬亮，谷雨.基于改进 YOLOv5s 的无人机图像实时目标检测 [J].光电工程，2022,49(3):69-81.
[4] DALAL N,TRIGGS B.Histograms of Oriented Gradients for Human Detection[C]//2005 IEEE Computer Society Conference on Computer Vision & Pattern Recognition.San Diego:IEEE,2005:886-893.
[5] GAO X R,WU Y Y,YANG K,et al.Vehicle Bottom Anomaly Detection Algorithm Based on SIFT[J].Optik-International Journal for Light and Electron Optics,2015,126(23):3562-3566.
[6] HENG C K,MATSUMOTO Y,YOKOMITSU S,et al.Shrink Boost for Selecting Multi-LBP Histogram Features in Object Detection[C]//2012 IEEE Computer Vision and Pattern Recognition.Providence:IEEE,2012:3250-3257.
[7] ARDIANTO S,CHEN C J,HANG H M.Real-time Traffic Sign Recognition Using Color Segmentation and SVM[C]//2017 International Conference on Systems,Signals and Image Processing (IWSSIP).Poznan:IEEE,2017:1-5.
[8] ELLAHYANI A,ANSARI M E,JAAFARI I E.Traffic Sign Detection and Recognition Based on Random Forests[J].Applied Soft Computing,2016,46:805-815.
[9] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE,2014:580-587.
[10] GIRSHICK R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision.Santiago:IEEE,2015:1440-1448.
[11] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[12] REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-time Object Detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE,2016:779-788.
[13] BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:Optimal Speed and Accuracy of Object Detection[EB/OL].(2020-04-23)[2023-02-20].https://arxiv.org/abs/2004.10934.
[14] WANG C Y,BOCHKOVSKIY A,LIAO H Y M.YOLOv7:Trainable Bag-of-freebies Sets New State-of-the-art for Real-time Object Detectors[EB/OL].(2022-07-06][2023-02-10].https://arxiv.org/abs/2207.02696.
[15] ZHU X K,LYU S C,WANG X O,et al.TPH-YOLOv5:Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios[C]//IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).Montreal:IEEE,2021:2778-2788.
[16] 赵璐璐，王学营，张翼，等.基于YOLOv5s融合Senet的车辆目标检测技术研究[J].图学学报，2022,43(5):776-782.
[17] 张上，王恒涛，冉秀康.基于YOLOv5的轻量化交通标志检测方法[J].电子测量技术，2022,45(8):129-135.
[18] ZHENG S X,LU J C,ZHAO H S,et al.Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Nashville:IEEE,2021:6877-6886.
[19] 付国栋，黄进，杨涛，等.改进CBAM的轻量级注意力模型[J].计算机工程与应用.2021,57(20):150-156.
[20] DU D W,ZHU P F,WEN L Y,et al.VisDrone-DET2019:The Vision Meets Drone Object Detection in Image Challenge Results[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop.Seoul:IEEE,2019:213-226.
[21] 刘展威，陈慈发，董方敏.基于YOLOv5s的航拍小目标检测改进算法研究[J/OL].无线电工程，1-10[2023-04-17].http://kns.cnki.net/kcms/detail/13.1097.TN.20230411.1645.026.html.
[22] 王一旭，肖小玲，王鹏飞，等.改进 YOLOv5s 的小目标烟雾火焰检测算法[J].计算机工程与应用，2023,59(1):72-81.
基本信息:
DOI：
中图分类号:U495;TP391.41
引用信息:
[1]马荣贵,张翼,董世浩.基于无人机影像的改进YOLOv5道路目标检测[J].无线电工程,2025,55(01):1-10.
基金信息:
国家重点研发计划(2021YFB1600104); 国家自然科学基金青年基金(52002031); 陕西省交通运输厅科研项目(20-24K,20-25X)~~