•  
  •  
 

Corresponding Author

朱俊清, 男, 博士, 副教授.E-mail: zhujq@seu.edu.cn

Abstract

To address the problems of insufficient detection accuracy and poor real-time performance caused by small detection objects, complex backgrounds, and large calculation volume in routine highway inspection tasks using unmanned aerial vehicles (UAVs), this paper proposed an improved UAV-based routine highway inspection algorithm relying on YOLOv 11n, YOLOv 11-UR. The algorithm incorporated the multi-level channel and attention (MLCA) mechanism into the backbone network to fuse channel and spatial dimension information, integrate local and global receptive fields, and effectively enhance feature expression capability. It achieved a significant improvement in detection accuracy with only a small increase in parameters. In the Neck part, GSConv was introduced to replace standard convolution, making the output of the convolution calculation as close as possible to standard convolution while reducing computational costs. VoVGSCSP was introduced to replace C 3k2, reducing the model parameter volume and computational complexity while enhancing feature extraction capability. Experimental results show that the YOLOv 11-UR algorithm has significant advantages in UAV-based routine highway inspection. It effectively reduces the parameter volume and computational overhead of the model without losing much inference speed. The model detection precision (RP) and mean average precision (mAP) reach 78.26% and 73.34%, respectively. The improved algorithm balances detection accuracy and inference efficiency and can better meet the needs of UAV-based routine highway inspection.

Publication Date

2-5-2026

DOI

10.14048/j.issn.1671-2579.2026.01.025

First Page

229

Last Page

239

Submission Date

February 2026

Reference

[1]赵文俊,刘凯,许国伟,等.基于 EDR-YOLOv 7的架空输电线路无人机巡检边缘端目标检测方法 [J/OL ].南方电网技术,1-10（2025 -02-19）[2025 -05-12].http://kns.cnki.net/kcms/detail/ 44.1643.tk.20250219.1327.008.html.ZHAO Wenjun,LIU Kai,XU Guowei,et al.Edge-end target detection method for UAVs inspection of overhead transmission lines based on EDR-YOLOv 7[J/OL ].Southern Power System Technology,1-10（2025 -02-19）
[2025 -05-12].http://kns.cnki.net/kcms/detail/ 44.1643.tk.20250219.1327.008.html.
[2]KHALILULLAH I.Unmanned aerial vehicle and artificial intelligence assisted oil and gas pipeline inspection system [D].Beaumont:Lamar University- Beaumont,2021.
[3]相诗尧,徐润,张常勇,等.基于无人机倾斜摄影技术的高 速 公 路 边 坡 三维 重 建 [J].中 外 公 路,2020,40(5):10-12.XIANG Shiyao,XU Run,ZHANG Changyong,et al.Three-dimensional reconstruction of highway slope based on UAV oblique photography technology [J].Journal of China & Foreign Highway,2020,40(5):10-12.
[4]WANG Z P,ZHU J Q,MA T.Deep learning –based detection of vehicle axle type with images collected via UAV [J].Journal of Transportation Engineering,Part B:Pavements,2024,150(3):04024032.
[5]BU T X,ZHU J Q,MA T,et al.Pavement point cloud upsampling based on transformer:toward enhancing 3D pavement data [J].IEEE Transactions on Intelligent Transportation Systems,2024,25(12):21647 -21657.
[6]ZHU J Q,BU T X,MA T,et al.Raster-based point cloud mapping of defective road marking:Toward automated road inspection via airborne LiDAR [J].Journal of Transportation Engineering,Part B:Pavements,2024,150(2):04024015.
[7]李会兴,张敬,张健南,等.改进 YOLO模型的岩体节理特征快速检测与应用 [J/OL ].中外公路,1-13（2025 -09-26）
[2025 -10-20].https://link.cnki.net/urlid/ 43.1363.U.20250926.1043.020.LI Huixing,ZHANG Jing,ZHANG Jiannan,et al.Rapid detection and application of rock mass joint features with the improved YOLO Model [J/OL ].Journal of China & Foreign Highway,1-13（2025 -09-26）[2025 -10-20].https://link.cnki.net/urlid/ 43.1363.U.20250926.1043.020.
[8]黄蓉,李睿,翟雨辰,等.基于改进 YOLOv 5算法的桥梁表观病害检测 [J/OL ].中外公路,1-10（2025 -08-05）[2025 -10-20].https://link.cnki.net/urlid/ 43.1363.U.20250805.1009.002.HUANG Rong,LI Rui,ZHAI Yuchen,et al.Bridge apparent disease detection based on improved YOLOv 5 algorithm [J/OL ].Journal of China & Foreign Highway,1-10（2025 -08-05）[2025 -10-20].https://link.cnki.net/urlid/43.1363.U.20250805.1009.002.
[9]BU T X,LIU X Y,ZHU J Q,et al.Unsupervised pavement anomaly detection via conditional diffusion model and domain adaptive feature selection [J].Computer-Aided Civil and Infrastructure Engineering,2025,40(28):5195 -5211.
[10]ZHONG J T,ZHU J Q,JU H Y,et al.Multi-scale feature fusion network for pixel-level pavement distress detection[J].Automation in Construction,2022,141:104436.
[11]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation [C]//Columbus：2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ),2014:580-587.
[12]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.
[13]章洋,何莉,汤青洲,等.基于智能手机的农村公路路面破损检测方法 [J].中外公路,2023,43(2):51-57.ZHANG Yang,HE Li,TANG Qingzhou,et al.Detection method of rural road pavement damage based on smart phone [J].Journal of China & Foreign Highway,2023,43(2):51-57.
[14]REDMONJ,DIVVALAS,GIRSHICKR,et al.You only look once:Unified,real-time object detection [C]//Las Vegas:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ),2016.
[15]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multiBox detector [M]//Computer Vision-ECCV 2016.Cham:Springer International Publishing,2016:21-37.
[16]苏卫国,王景霄.基于 YOLO v 3深度学习算法的道路裂缝识别模型研究 [J].中外公路,2023,43(2):58-63.SU Weiguo,WANG Jingxiao.Research on road crack recognition model based on YOLO v 3 deep learning algorithm [J].Journal of China & Foreign Highway,2023,43(2):58-63.
[17]谢海波,朱玮峻,张璧,等.面向高强度螺栓检测的YOLOv 5-Ganomaly 联合算法研究 [J].中外公路,2024,44(4):171-179.XIE Haibo,ZHU Weijun,ZHANG Bi,et al.Research on YOLOv 5-ganomaly joint algorithm for high-strength bolt detection [J].Journal of China & Foreign Highway,2024,44(4):171-179.
[18]ZHU J Q,ZHONG J T,MA T,et al.Pavement distress detection using convolutional neural networks with images captured via UAV [J].Automation in Construction,2022,133:103991.
[19] CARION N,MASSA F,SYNNAEVE G,et al.End-to-end object detection with transformers [J].Lecture Notes in Computer Science,2020,12346:213-229.
[20]ZHANG H,LI F,LIU S L,et al.DINO:DETR with improved DeNoising anchor boxes for end-to-end object detection [EB/OL ].（2022 -03-08）[2025 -05-20].https://arxiv.org/abs/ 2203.03605,arXiv:2203.03605.
[21]WAN H F,GAO L,YUAN Z D,et al.A novel transformer model for surface damage detection and cognition of concrete bridges [J].Expert Systems with Applications,2023,213:119019.
[22]WANG Q Y,CHEN B.A novel transfer learning model for the real-time concrete crack detection [J].Knowledge-Based Systems,2024,301:112313.
[23]ZUO C H,HUANG N X,YUAN C,et al.Pavement-DETR:A high-precision real-time detection transformer for pavement defect detection [J].Sensors,2025,25(8):2426.
[24]HE J J,WANG Y C,WANG Y T,et al.A lightweight road crack detection algorithm based on improved YOLOv 7 model [J].Signal,Image and Video Processing,2024,18(1):847-860.
[25]ZHU J Q,WU Y X,MA T.Multi-object detection for daily road maintenance inspection with UAV based on improved YOLOv 8[J].IEEE Transactions on Intelligent Transportation Systems,2024,25(11):16548 -16560.
[26]NIU G Z,LI G M,WANG C Y,et al.LBN-YOLO:A lightweight road damage detection model based on multiscale contextual feature extraction and fusion [J].Structural Control and Health Monitoring,2025,2025 (1):5595809.
[27]KHANAM R,HUSSAIN M.YOLOv 11:an overview of the key architectural enhancements [EB/OL ].（2024 -10-23）[2025 -05-20].https://arxiv.org/abs/ 2410.17725,arXiv:2410.17725 v1.
[28]WAN D H,LU R S,SHEN S Y,et al.Mixed local channel attention for object detection [J].Engineering Applications of Artificial Intelligence,2023,123:106442.
[29]LI H L,LI J,WEI H B,et al.Slim-neck by GSConv:A lightweight-design for real-time detector architectures [J].Journal of Real-Time Image Processing,2024,21(3):62.
[30]LEE Y,HWANG J W,LEE S,et al.An energy and GPU-computation efficient backbone network for real-time object detection [C]//Long Beach:2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW ),2019:752-760.
[31]潘晓英,贾凝心,穆元震,等.小目标检测研究综述 [J].中国图象图形学报,2023,28(9):2587 -2615.PAN Xiaoying,JIA Ningxin,MU Yuanzhen,et al.Survey of small object detection [J].Journal of Image and Graphics,2023,28(9):2587 -2615.
[32]ZHAO Y A,LYU W Y,XU S L,et al.DETRs beat YOLOs on real-time object detection [C]//Seattle:2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ),2024.

Download

Share

COinS