1.三峡大学电气与新能源学院 / 湖北省输电线路工程技术研究中心,湖北 宜昌 443002
2.重庆市三峡水利电力学校,重庆 404000
王彦海(1981年生),男;研究方向:智慧化检测与识别; E-mail:45245356@qq.com
收稿:2026-02-03,
修回:2026-03-30,
录用:2026-03-09,
网络首发:2026-06-26,
移动端阅览
王彦海, 白昱哲, 王杨, 等. 基于改进YOLOv11的树木入侵目标检测算法[J/OL]. 中山大学学报(自然科学版)(中英文), 2026,1-13.
Wang Yanhai, Bai Yuzhe, Wang Yang, et al. A target detection algorithm for tree encroachment on transmission lines based on improved YOLOv11[J/OL]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2026, 1-13.
王彦海, 白昱哲, 王杨, 等. 基于改进YOLOv11的树木入侵目标检测算法[J/OL]. 中山大学学报(自然科学版)(中英文), 2026,1-13. DOI: 10.11714/acta.snus.ZR20260042.
Wang Yanhai, Bai Yuzhe, Wang Yang, et al. A target detection algorithm for tree encroachment on transmission lines based on improved YOLOv11[J/OL]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2026, 1-13. DOI: 10.11714/acta.snus.ZR20260042.
基于YOLOv11提出了一种航拍图像检测算法MA-YOLOv11。首先设计SE-C3k2模块,在轻量化同时保留细小树枝特征。其次,采用多尺度共享卷积模块替换SPPF模块。然后,结合MAFPN结构增加小目标检测头P2并设计了HMA-Net网络结构,强化浅层细节信息与高层语义信息的交互,提高对小目标的检测精度。最后,采用多尺度注意力检测头,使其能有效地处理树叶遮挡场景。实验结果表明:相较于基准模型,改进的MA-YOLOv11模型精确度和召回率分别上升4.2%和4.1%,而mAP50指标上升5.2%,验证了方法对树木入侵检测的有效性。
An aerial image detection algorithm named MA-YOLOv11 is proposed based on YOLOv11. First,the SE-C3k2 module is designed to preserv the features of small branches while achieving lightweight. Second,the multi-scale shared convolution module replaces the SPPF module. Then,a novel HMA-Net network structure is constructed by incorporating the MAFPN architecture,adding a small target detection head P2,and reducing redundant paths. This enhances the interaction between shallow detail information and high-level semantic information,thereby improving the detection accuracy for small targets. Finally,a multi-scale attention detection head is employed to effectively handle scenes with leaf occlusion. Experimental results show that compared to the baseline model,the improved MA-YOLOv11 model increases of 4.2% in precision,4.1% in recall,and 5.2% in the mAP50 metric,validating the effectiveness of this method for treeencroachment detection.
厉秉强 , 王骞 , 王滨海 , 等 , 2010 . 利用无人直升机巡检输电线路 [J]. 山东电力技术 , 37 ( 1 ): 1 - 4 .
刘高 , 陈浩 , 廖建东 , 等 , 2025 . 架空输电线路无人机巡检影像中的隐患识别 [J]. 沈阳工业大学学报 , 47 ( 2 ): 258 - 264 .
刘宏志 , 黄振龙 , 邱彬 , 等 , 2026 . 基于改进YOLOv11n的输电线路主要缺陷检测方法 [J/OL]. 高电压技术 , 1 - 12 .[ 2026-06-24 ]. https://doi.org/10.13336/j.1003-6520.hve.20241908 https://doi.org/10.13336/j.1003-6520.hve.20241908 .
马富齐 , 王波 , 董旭柱 , 等 , 2020 . 电力视觉边缘智能: 边缘计算驱动下的电力深度视觉加速技术 [J]. 电网技术 , 44 ( 6 ): 2020 - 2029 .
聂凯 , 李泽 , 高文豪 , 等 , 2025 . 基于YOLOv8-RFL模型的电力绝缘子缺陷检测方法 [J]. 电网技术 , 49 ( 9 ): 3948 - 3957 .
王彦海 , 郭宸昕 , 吴德强 , 2026 基于改进YOLOv 7的输电线路机械外破隐患目标检测方法 [J]. 电测与仪表 , 63 ( 1 ): 64 - 71 .
王强 , 冯云涛 , 周超 , 2025 . 基于GE-YOLO算法的输电线路绝缘子多类型缺陷检测研究 [J]. 高压电器 , 61 ( 6 ): 92 - 101 .
王彧 , 2023 . 基于YOLOv7的输电线路防振锤识别及缺陷检测 [D]. 哈尔滨 : 东北农业大学 .
谢从珍 , 黄梦成 , 黄奕琅 , 等 , 2026 . 基于WMEF-YOLO的绝缘子缺陷图像检测方法 [J]. 高电压技术 , 52 ( 3 ): 1268 - 1279 .
张文丽 , 2024 . 搭载于某型巡线机器人的架空输电线路故障检测系统研究 [D]. 北京 : 华北电力大学 .
Chen J Q , Ma A Q , Huang L X , et al , 2024 . Efficient and lightweight grape and picking point synchronous detection model based on key point detection [J]. Comput Electron Agric , 217 : 108612 .
Finder S E , Amoyal R , Treister E , et al , 2024 . Wavelet convolutions for large receptive fields [M]// Computer Vision-ECCV 2024 . Springer : 363 - 380 .
Girshick R , 2016 . Fast R-CNN [C]// International Conference on Computer Vision . Santiago,Chile : 1440 - 1448 .
He K , Zhang X , Ren S , et al , 2015 . Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Trans Pattern Anal Mach Intell , 37 ( 9 ): 1904 - 1916 .
Li J F , Wen Y , He L H , 2023 . SCConv: Spatial and channel reconstruction convolution for feature redundancy [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition . Vancouver, BC, Canada : 6153 - 6162 .
Liu W , Anguelov D , Erhan D , et al , 2016 . SSD: Single shot MultiBox detector [M]// Computer Vision-ECCV 2016 . Springer : 21 - 37 .
Ma F Q , Wang B , Dong X Z , et al , 2020 . Power vision edge intelligence:Edge computing-driven acceleration technology for deep vision in electric power [J]. Power System Technology , 44 ( 6 ): 2020 - 2029 .
Redmon J , Divvala S , Girshick R , et al , 2016 . You only look once:Unified,real-time object detection [C]// IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas,NV, USA : 779 - 788 .
Ren S , He K , Girshick R , et al , 2017 . Faster R-CNN: Towards real-time object detection with region proposal networks [J]. IEEE Trans Pattern Anal Mach Intell , 39 ( 6 ): 1137 - 1149 .
Yang Z , Guan Q , Zhao K , et al , 2024 . Multi-branch auxiliary fusion YOLO with re-parameterization heterogeneous convolutional for accurate object detection [C]// Pattern Recognition and Computer Vision . ACM : 492 - 505 .
Yu Z P , Huang H B , Chen W J , et al , 2024 . YOLO-FaceV2: A scale and occlusion aware face detector [J]. Pattern Recognit , 155 : 110714
0
浏览量
20
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
