| 刘兰兰,万旭东,汪志刚,张 建,彭 昊,杨嘉妮.基于超分辨率重建与多尺度特征融合的
输电线路缺陷检测方法[J].电子测量与仪器学报,2023,37(1):130-139 |
| 基于超分辨率重建与多尺度特征融合的
输电线路缺陷检测方法 |
| Transmission line defect detection method based on super-resolutionreconstruction and multi-scale feature fusion |
| |
| DOI：10.13382/j.issn.1000-7105.2023.01.015 |
| 中文关键词: 输电线路缺陷检测 超分辨率 卷积块注意力 多尺度特征融合 |
| 英文关键词:transmission line defect detection super resolution convolutional block attention multiscale feature fusion |
| 基金项目:智能带电作业技术及装备(机器人) 湖南省重点实验室开放基金( 2021KZD3001)、湖北省输电线路工程技术研究中心开放课题(2019KXL05)项目资助 |
|
|
|
|
| 摘要点击次数: 976 |
| 全文下载次数: 1100 |
| 中文摘要: |
| 针对输电线路巡检中可能存在拍摄图像质量不高的问题,以及线路缺陷目标小而分布密集而导致传统方法检测精度不
高的问题,提出一种基于超分辨率重建与多尺度特征融合的输电线路缺陷检测方法。 首先,使用超分辨率网络对巡检图像进行
重建,提升清晰度,丰富图像中包含的特征信息;然后使用改进的 YOLOX 网络检测巡检图像中的缺陷,在主干网络中嵌入卷积
块注意力机制,强化模型对重叠小目标的定位能力;为进一步提升小目标的检测能力,在 YOLOX 的特征融合网络中新增浅层
检测尺度进行特征融合;最后,通过使用 CIOU 优化边界框损失函数提升模型收敛能力,降低缺陷目标的漏检率。 实验结果表
明,所提方法能在提升巡检图像质量的基础上对输电线路缺陷准确地检测,精度达到 93. 27%,相比 SSD 等经典模型,对小而密
集的缺陷目标有着更强的提取能力和鲁棒性。 |
| 英文摘要: |
| Aiming at the problem that the quality of the captured image may be poor in the inspection of transmission lines, and the
problem that the detection accuracy of traditional methods is not high due to the line defect that the targets are small and densely
distributed, a transmission line defect detection method based on super-resolution reconstruction and multi-scale feature fusion is
proposed. First, the super-resolution network is used to reconstruct the inspection image, improve the clarity and enrich the feature
information contained in the image. Then the improved YOLOX network is used to detect defects in the inspection image, and the
convolution block attention mechanism is embedded in the backbone network to strengthen the positioning ability of the model for
overlapping small targets. In order to further improve the detection ability of small targets, a shallow detection scale is added to
YOLOX’s feature fusion network for feature fusion. Finally, by using CIOU to optimize the loss function of the bounding box, improve
the convergence ability of the model and reduce the missed detection rate of the defect targets. The experimental results show that the
proposed method can accurately detect the transmission line defects on the basis of improving the inspection image quality, with an
accuracy of 93. 27%. Compared with classical models such as SSD, it has stronger extraction ability and robustness for small and dense
defect targets. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
