[1]王朝硕,李伟性,郑武略,等.一种改进SSD的输电线路电力部件识别方法[J].应用科技,2020,47(4):75-81.[doi:10.11991/yykj.201912012]
 WANG Chaoshuo,LI Weixing,ZHENG Wulue,et al.An improved SSD method for power component identification of transmission lines[J].Applied science and technology,2020,47(4):75-81.[doi:10.11991/yykj.201912012]
点击复制

一种改进SSD的输电线路电力部件识别方法(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第47卷
期数:
2020年4期
页码:
75-81
栏目:
计算机技术与应用
出版日期:
2020-07-05

文章信息/Info

Title:
An improved SSD method for power component identification of transmission lines
作者:
王朝硕1 李伟性2 郑武略2 王宁1 赵航航2
1. 中国南方电网超高压输电公司信通中心,广东 广州 510000;
2. 中国南方电网超高压输电公司广州局,广东 广州 510000
Author(s):
WANG Chaoshuo1 LI Weixing2 ZHENG Wulue2 WANG Ning1 ZHAO Hanghang2
1. China Southern Power Grid EHV Transmission Company ICT Center, Guangzhou 510000, China;
2. China Southern Power Grid EHV Transmission Company Guangzhou Bureau, Guangzhou 510000, China
关键词:
SSD模型电力部件多尺度注意力机制膨胀卷积特征融合反卷积语义信息
Keywords:
SSD modelpower componentsmulti-scaleattention mechanismdilated convolutionmultiscale feature fusiondeconvolutionsemantic information
分类号:
TP751
DOI:
10.11991/yykj.201912012
文献标志码:
A
摘要:
为解决单阶段多框检测器(single shot multibox setector, SSD)算法识别较小尺寸电力部件准确率低的问题,本文提出一种注意力机制和多尺度特征融合的单阶段多框检测器(attention mechanism and multiscale feature fusion single shot multibox detector, amSSD)算法。该方法在SSD网络特征提取层引入压缩和激励网络(squeeze-and-excitation networks, SENet)结构,筛选并保留更多与目标相关的特征通道;对浅层特征图采用膨胀卷积操作,使目标语义信息更加丰富;对高层特征图进行反卷积操作,并与浅层特征进行融合,得到具有更高分辨率高语义信息的目标特征图,提高对较小尺寸电力部件的识别能力。利用实际无人机飞行数据进行测试验证,实验结果表明:本文方法能够有效地识别出电力部件,而且识别平均准确率达到89.6%,比SSD方法的识别准确率提升了6.2%。
Abstract:
In order to solve the problem of low accuracy of SSD (single shot multibox detector) algorithm in identifying small size power components, this paper proposes an attention mechanism and multi-scale feature fused amSSD (attention mechanism and multiscale feature fusion single shot multibox detector)algorithm. Firstly, the SENet (squeeze-and-excitation networks)structure is introduced into the feature extraction layer of SSD network to filter and retain more feature channels related to the target; secondly, the expansion convolution operation is adopted for the shallow feature map to enrich the semantic information of the target; finally, the deconvolution operation is carried out for the high-level feature map and the shallow feature is integrated. The target feature map with higher-resolution semantic information is obtained to improve the recognition ability of small size power components. The experiment has been carried out with actual UAV flight data. The results show that this method can effectively identify power components, and the average recognition accuracy is 89.6%, which is 6.2% higher than that of SSD method.

参考文献/References:

[1] 张秋雁, 杨忠, 姜遇红, 等. 一种基于CNN的航拍输电线路图像分类方法[J]. 应用科技, 2019, 46(6): 41–45
[2] 李军华, 权小霞, 汪宇玲. 多特征融合的瓷砖表面缺陷检测算法研究[J]. 计算机工程与应用, 2020, 56(15): 191-198.
[3] 付波, 徐超, 赵熙临, 等. 基于最值平均的人脸识别LBP算法[J]. 计算机应用与软件, 2019, 36(9): 209–213
[4] 刘兴长, 孟昱煜. 基于HOG特征提取和模糊支持向量机的西夏文字识别[J]. 西北师范大学学报(自然科学版), 2019, 55(5): 39–43
[5] 林刚, 王波, 彭辉, 等. 基于改进Faster-RCNN的输电线巡检图像多目标检测及定位[J]. 电力自动化设备, 2019, 39(5): 213–218
[6] REN S, HE K, 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.
[7] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]//Proc of the 14th European Conference on Computer Vision. Amsterdam, the Netherlands, 2016: 21-37.
[8] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vega, USA, 2016:779-788.
[9] FU C Y, LIU W, RANGA A, et al. DSSD : deconvolutional single shot detector[C]//Computer Vision and Pattern Recognition. Hawaii, USA, 2017:2881-2890.
[10] 刘涛, 汪西莉. 采用卷积核金字塔和空洞卷积的单阶段目标检测[J]. 中国图象图形学报, 2020, 25(1): 102–112
[11] 刘学平, 李玙乾, 刘励, 等. 嵌入SENet结构的改进YOLOV3目标识别算法[J]. 计算机工程, 2019, 45(11): 243–248
[12] 彭晏飞, 梅金业, 王恺欣, 等. 基于区域注意力机制的遥感图像检索[J]. 激光与光电子学进展, 2020, 57(10): 180–188
[13] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 7132-7141.
[14] TAO X, ZHANG D, WANG Z, et al. Detection of power line insulator defects using aerial images analyzed with convolutional neural networks[J]. IEEE transactions on systems, man, and cybernetics: systems, 2018: 1–13.
[15] 马健, 史文旭, 鲍胜利. 基于特征融合SSD的遥感图像舰船目标检测[J]. 计算机应用, 2019, 39(S2): 253–256
[16] 陈庆, 闫斌, 叶润, 等. 航拍绝缘子卷积神经网络检测及自爆识别研究[J]. 电子测量与仪器学报, 2017, 31(6): 942–953
[17] 徐诚极, 王晓峰, 杨亚东. Attention-YOLO:引入注意力机制的YOLO检测算法[J]. 计算机工程与应用, 2019, 55(6): 13–23, 125
[18] 赵文清, 程幸福, 赵振兵, 等. 注意力机制和Faster RCNN相结合的绝缘子识别[J]. 智能系统学报, 2020, 15(1): 92–98
[19] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International journal of computer vision, 2014, 115(3): 211–252.
[20] 颜宏文, 陈金鑫. 基于改进YOLOv3的绝缘子串定位与状态识别方法[J]. 高电压技术, 2020, 46(2): 423–432

备注/Memo

备注/Memo:
收稿日期:2019-11-11。
基金项目:中国南方电网有限责任公司科技项目(CGYKJXM20160006)
作者简介:王朝硕,男,高级工程师;李伟性,男,高级工程师
通讯作者:李伟性,E-mail:1647124073@qq.com
更新日期/Last Update: 2020-11-27