1. 安徽大学 人工智能学院,安徽,合肥,230601
2. 华北电力大学 电气与电子工程学院,北京,102206
3. 国网物资有限公司,北京,100120
纸质出版:2025
移动端阅览
徐程,郑春厚,胡祥,王丽丽,张庚生,郭昊博.基于TLI-DETR的输电线路巡检图像小目标检测方法[J].智慧电力,2025,53(9):117-125.
XU Cheng, ZHENG Chunhou, HU Xiang, et al. A Small Object Detection Method for Transmission Line Inspection Images Based on TLI-DETR[J]. 2025, 53(9): 117-125.
徐程,郑春厚,胡祥,王丽丽,张庚生,郭昊博.基于TLI-DETR的输电线路巡检图像小目标检测方法[J].智慧电力,2025,53(9):117-125. DOI: 10.20204/j.sp.2025.09014.
XU Cheng, ZHENG Chunhou, HU Xiang, et al. A Small Object Detection Method for Transmission Line Inspection Images Based on TLI-DETR[J]. 2025, 53(9): 117-125. DOI: 10.20204/j.sp.2025.09014.
针对输电线路巡检(TLI)中存在的复杂背景干扰、目标尺度跨度大及器件密集分布导致小目标检测精度低的问题,提出一种适用于TLI的检测变压器(DETR)模型TLI-DETR。首先,通过在骨干网络各阶段末层用多尺度可分离卷积网络替换残差块,提取并融合各阶段输出的特征图作为多尺度特征,以增强小目标特征提取能力;其次,在多尺度特征图中引入通道空间融合交叉注意力机制,抑制图像中背景噪声对小目标检测的干扰;最后,设计层级交互特征融合模块,通过动态调整注意力区域提升密集小目标检测精度。实验结果表明,所提方法在输电线路巡检任务中的综合性能优于当前主流模型,可有效识别输电线路中的小目标部件,有助于发现潜在的安全隐患。
Aiming at the problem of low small target detection accuracy caused by complex background interference, large target scale variations, and densely distributed components in transmission line inspection (TLI), this paper proposes a detection transformer (DETR) model named TLI-DETR for TLI tasks. Firstly, multi-scale separable convolutional networks are used to replace the residual blocks at the final layer of each stage in the backbone network. The feature maps output from each stage are extracted and fused as multi-scale features to enhance small target feature extraction capability. Secondly, a channel-spatial fusion cross-attention mechanism is introduced into the multi-scale feature maps to suppress interference from background noise on small target detection. Finally, a hierarchical interactive feature fusion module is designed to improve the detection accuracy of densely distributed small targets by dynamically adjusting attention regions. Experimental results demonstrate that the proposed method outperforms current mainstream models in comprehensive performance for TLI tasks, effectively identifying small target components in transmission lines and facilitating the detection of potential safety hazards.
陈杰,唐占元,安之焕,等. 基于无人机采集图像的输电线路异常检测方法研究 [J ] .电测与仪表,2023,60(7):122-127.
LI Z R,WANG Q,ZHANG T Y,et al. UAV high-voltage power transmission line autonomous correction inspection system based on object detection [J ] . IEEE Sensors Journal,2023,23(9):10215-10230.
HUANG X B,WU Y Q,ZHANG Y,et al. Structural defect detection technology of transmission line damper based on UAV im-age [J ] . IEEE Transactions on Instrumentation and Measurement,2022,72:3504314.
ALHASSAN A B,ZHANG X D,SHEN H M,et al. Power transmission line inspection robots:A review,trends and challenges for future research [J ] .International Journal of Electrical Power & Energy Systems,2020,118:105862.
周文青,刘刚. 基于深度学习和无人机图像的架空线路缺陷巡检综述 [J ] .电力工程技术,2024,43(2):73-82.
LI J,YE D H,KOLSCH M,et al. Fast and robust UAV to UAV detection and tracking from video [J ] . IEEE Transactions on Emerging Topics in Computing,2022,10(3):1519-1531.
王晓红,胡豫. 复杂背景下的无人机图像小目标检测 [J ] .计算机工程与应用,2023,59(15):107-114.
田子建,吴佳奇,张文琪,等. 基于二阶段目标增强网络的低照度复杂环境下绝缘子故障检测方法 [J ] .电网技术,2024,48(3):1331-1343.
TAN L,LV X Y,LIAN X F,et al. YOLOv4_Drone:UAV image target detection based on an improved YOLOv4 algorithm [J ] .Com puters & Electrical Engineering,2021,93:107261.
陈奎,刘晓,贾立娇,等. 基于轻量化网络与增强多尺度特征融合的绝缘子缺陷检测 [J ] .高电压技术,2024,50(3):1289-1300.
高黎明. 基于轻量化目标检测的绝缘子缺陷识别 [J ] .高压电器,2023,59(12):237-244.
ZHAO W Q,XU M F,CHENG X F,et al. An insulator in transmission lines recognition and fault detection model based on improved faster RCNN [J ] .IEEE Transactions on Instrumentation and Measurement,2021,70:5016408.
SOUZA B J,STEFENON S F,SINGH G,et al. Hybrid-YOLO for classification of insulators defects in transmission lines based on UAV [J ] . International Journal of Electrical Power & Energy Systems,2023,148:108982.
谢静,杜耀文,刘志坚,等. 基于轻量化改进型YOLOv5s的可见光绝缘子缺陷检测算法 [J ] .电网技术,2023,47(12):5273-5283.
CARION N,MASSA F,SYNNAEVE G,et al. End-to-end object detection with transformers [C ] //Computer Vision-ECCV 2020. Glasgow,UK,2020:213-229.
YESHURUN Y,CARRASCO M. Spatial attention improves performance in spatial resolution tasks [J ] . Vision Research,1999,39(2):293-306.
TONG W,CHEN W T,HAN W,et al. Channel-attention-based DenseNet network for remote sensing image scene classification [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,13:4121-4132.
GAO L F,ZHANG J X,YANG C H,et al. Cas-VSwin transformer:A variant swin transformer for surface-defect detection [J ] . Computers in Industry,2022,140:103689.
伍箴燎,吴正平,孙水发. 基于改进YOLOv5算法的绝缘子多缺陷检测 [J ] .高压电器,2024,60(12):95-102,112.
白晓静,谢雅祺,赵淼,等. 基于局部特征深度信息的绝缘子小样本缺陷检测 [J ] .电网技术,2024,48(2):740-752.
艾上美,周剑峰,张必朝,等. 基于改进SSD算法的光伏组件缺陷检测研究 [J ] .智慧电力,2023,51(12):53-58.
刘甜甜,彭放,卢伟龙,等. 基于YOLOv7的智能电网外部安全帽佩戴风险因素识别与检测 [J ] .电测与仪表,2024,61(12):42-48.
LIN T Y,GOYAL P,GIRSHICK R,et al. Focal loss for dense object detection [C ] //2017 IEEE International Conference on Computer Vision (ICCV). Venice,Italy,2017:2999-3007.
LI F,ZENG A L,LIU S L,et al. Lite DETR:an interleaved multi-scale encoder for efficient DETR [C ] //2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,Canada,2023:18558-18567.
SELVARAJU R R,COGSWELL M,DAS A,et al. Grad-CAM:visual explanations from deep networks via gradient-based localization [J ] . International Journal of Computer Vision,2020,128(2):336-359.
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