基于改进Faster R-CNN的输电线路断股识别算法研究  被引量:1

Modified-faster-R-CNN-based Identification Algorithm for Transmission Line Broken Strand

在线阅读下载全文

作  者:张吉庆 姚攀 宋坤 谢蓉 廖红华 ZHANG Jiqing;YAO Pan;SONG Kun;XIE Rong;LIAO Honghua(School of Information and Engineering,Hubei University for Nationalities,Enshi 445000,China;State Grid Hubei Electric Power Company Limited,Enshi Power Supply Company,Enshi 445000,China)

机构地区:[1]湖北民族大学信息工程学院,湖北恩施445000 [2]国网湖北省电力有限公司恩施供电公司,湖北恩施445000

出  处:《电工技术》2024年第5期110-113,共4页Electric Engineering

基  金:国家自然科学基金项目(编号62163013);湖北省自然科学基金项目(编号2021CFB542)。

摘  要:为解决输电线路断股图像识别不精确的问题,设计了一种基于改进Faster R-CNN算法的输电线路断股识别检测方法。该方法利用DenseNet121代替VGG16,并融合各密集块的输出特征;同时,采用Soft-NMS算法取代NMS算法来缓解重叠目标漏检的问题。实验结果表明,更换特征提取网络后,mAP达85.1%,且特征融合后的mAP达到了90.2%,相比改进前提升5.1%。采用Soft-NMS算法后,mAP提升了1.6%。最终改进后的模型mAP从80.8%提高到了92.5%,证明了改进后的算法能有效提高检测能力。In order to solve the problem of inaccurate image recognition of power transmission line broken strands,an identification method for power transmission line broken strands was designed based on modified Faster R-CNN algorithm.This method uses DenseNet121 instead of VGG16 and integrates the output features of each dense block.At the same time,NMS algorithm is replaced by Soft-NMS algorithm to alleviate false negative identification of overlapping targets.The experimental results showed that after replacing feature extraction network,the mAP reaches 85.1%.Meanwhile,the mAP after feature fusion reached 90.2%,achieving an increase of 5.1% compared to before improvement.By adopting the Soft-NMS algorithm,mAP was increased by 1.6%.The final improved model had an mAP increment from 80.8% to 92.5%,demonstrating its effectiveness in improving detection performance.

关 键 词:输电线路 Faster R-CNN 断股 特征融合 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象