基于轻量化结构和特征均衡网络的输电线路无人机图像典型故障检测

IF 4.4 2区 地球科学 Q1 REMOTE SENSING Drones Pub Date : 2023-10-17 DOI:10.3390/drones7100638
Gujing Han, Ruijie Wang, Qiwei Yuan, Liu Zhao, Saidian Li, Ming Zhang, Min He, Liang Qin
{"title":"基于轻量化结构和特征均衡网络的输电线路无人机图像典型故障检测","authors":"Gujing Han, Ruijie Wang, Qiwei Yuan, Liu Zhao, Saidian Li, Ming Zhang, Min He, Liang Qin","doi":"10.3390/drones7100638","DOIUrl":null,"url":null,"abstract":"In the context of difficulty in detection problems and the limited computing resources of various fault scales in aerial images of transmission line UAV inspections, this paper proposes a TD-YOLO algorithm (YOLO for transmission detection). Firstly, the Ghost module is used to lighten the model’s feature extraction network and prediction network, significantly reducing the number of parameters and the computational effort of the model. Secondly, the spatial and channel attention mechanism scSE (concurrent spatial and channel squeeze and channel excitation) is embedded into the feature fusion network, with PA-Net (path aggregation network) to construct a feature-balanced network, using channel weights and spatial weights as guides to achieving the balancing of multi-level and multi-scale features in the network, significantly improving the detection capability under the coexistence of multiple targets of different categories. Thirdly, a loss function, NWD (normalized Wasserstein distance), is introduced to enhance the detection of small targets, and the fusion ratio of NWD and CIoU is optimized to further compensate for the loss of accuracy caused by the lightweightedness of the model. Finally, a typical fault dataset of transmission lines is built using UAV inspection images for training and testing. The experimental results show that the TD-YOLO algorithm proposed in this article compresses 74.79% of the number of parameters and 66.92% of the calculation amount compared to YOLOv7-Tiny and increases the mAP (mean average precision) by 0.71%. The TD-YOLO was deployed into Jetson Xavier NX to simulate the UAV inspection process and was run at 23.5 FPS with good results. This study offers a reference for power line inspection and provides a possible way to deploy edge computing devices on unmanned aerial vehicles.","PeriodicalId":36448,"journal":{"name":"Drones","volume":"39 1","pages":"0"},"PeriodicalIF":4.4000,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Typical Fault Detection on Drone Images of Transmission Lines Based on Lightweight Structure and Feature-Balanced Network\",\"authors\":\"Gujing Han, Ruijie Wang, Qiwei Yuan, Liu Zhao, Saidian Li, Ming Zhang, Min He, Liang Qin\",\"doi\":\"10.3390/drones7100638\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the context of difficulty in detection problems and the limited computing resources of various fault scales in aerial images of transmission line UAV inspections, this paper proposes a TD-YOLO algorithm (YOLO for transmission detection). Firstly, the Ghost module is used to lighten the model’s feature extraction network and prediction network, significantly reducing the number of parameters and the computational effort of the model. Secondly, the spatial and channel attention mechanism scSE (concurrent spatial and channel squeeze and channel excitation) is embedded into the feature fusion network, with PA-Net (path aggregation network) to construct a feature-balanced network, using channel weights and spatial weights as guides to achieving the balancing of multi-level and multi-scale features in the network, significantly improving the detection capability under the coexistence of multiple targets of different categories. Thirdly, a loss function, NWD (normalized Wasserstein distance), is introduced to enhance the detection of small targets, and the fusion ratio of NWD and CIoU is optimized to further compensate for the loss of accuracy caused by the lightweightedness of the model. Finally, a typical fault dataset of transmission lines is built using UAV inspection images for training and testing. The experimental results show that the TD-YOLO algorithm proposed in this article compresses 74.79% of the number of parameters and 66.92% of the calculation amount compared to YOLOv7-Tiny and increases the mAP (mean average precision) by 0.71%. The TD-YOLO was deployed into Jetson Xavier NX to simulate the UAV inspection process and was run at 23.5 FPS with good results. This study offers a reference for power line inspection and provides a possible way to deploy edge computing devices on unmanned aerial vehicles.\",\"PeriodicalId\":36448,\"journal\":{\"name\":\"Drones\",\"volume\":\"39 1\",\"pages\":\"0\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2023-10-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Drones\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/drones7100638\",\"RegionNum\":2,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"REMOTE SENSING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Drones","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/drones7100638","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"REMOTE SENSING","Score":null,"Total":0}
引用次数: 0

摘要

针对传输线无人机检测航图中各种故障尺度检测问题难解、计算资源有限的情况,本文提出了一种TD-YOLO算法(YOLO for transmission detection)。首先,利用Ghost模块对模型的特征提取网络和预测网络进行轻量化,显著减少了模型的参数数量和计算量;其次,将空间和通道关注机制scSE(并发空间和通道挤压和通道激励)嵌入到特征融合网络中,结合PA-Net(路径聚合网络)构建特征平衡网络,以通道权值和空间权值为导向,实现网络中多层次、多尺度特征的平衡,显著提高了多个不同类别目标共存下的检测能力。第三,引入损失函数NWD(归一化Wasserstein距离)来增强对小目标的检测,并优化NWD与CIoU的融合比例,进一步弥补模型轻量化带来的精度损失。最后,利用无人机检测图像构建典型输电线路故障数据集,进行训练和测试。实验结果表明,与YOLOv7-Tiny相比,本文提出的TD-YOLO算法压缩了74.79%的参数个数和66.92%的计算量,mAP(平均精度)提高了0.71%。TD-YOLO部署在Jetson Xavier NX中模拟无人机检测过程,并以23.5 FPS的速度运行,取得了良好的效果。该研究为电力线检测提供了参考,并为无人机部署边缘计算设备提供了可能的途径。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Typical Fault Detection on Drone Images of Transmission Lines Based on Lightweight Structure and Feature-Balanced Network
In the context of difficulty in detection problems and the limited computing resources of various fault scales in aerial images of transmission line UAV inspections, this paper proposes a TD-YOLO algorithm (YOLO for transmission detection). Firstly, the Ghost module is used to lighten the model’s feature extraction network and prediction network, significantly reducing the number of parameters and the computational effort of the model. Secondly, the spatial and channel attention mechanism scSE (concurrent spatial and channel squeeze and channel excitation) is embedded into the feature fusion network, with PA-Net (path aggregation network) to construct a feature-balanced network, using channel weights and spatial weights as guides to achieving the balancing of multi-level and multi-scale features in the network, significantly improving the detection capability under the coexistence of multiple targets of different categories. Thirdly, a loss function, NWD (normalized Wasserstein distance), is introduced to enhance the detection of small targets, and the fusion ratio of NWD and CIoU is optimized to further compensate for the loss of accuracy caused by the lightweightedness of the model. Finally, a typical fault dataset of transmission lines is built using UAV inspection images for training and testing. The experimental results show that the TD-YOLO algorithm proposed in this article compresses 74.79% of the number of parameters and 66.92% of the calculation amount compared to YOLOv7-Tiny and increases the mAP (mean average precision) by 0.71%. The TD-YOLO was deployed into Jetson Xavier NX to simulate the UAV inspection process and was run at 23.5 FPS with good results. This study offers a reference for power line inspection and provides a possible way to deploy edge computing devices on unmanned aerial vehicles.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Drones
Drones Engineering-Aerospace Engineering
CiteScore
5.60
自引率
18.80%
发文量
331
期刊最新文献
Firefighting Drone Configuration and Scheduling for Wildfire Based on Loss Estimation and Minimization Wind Tunnel Balance Measurements of Bioinspired Tails for a Fixed Wing MAV Three-Dimensional Indoor Positioning Scheme for Drone with Fingerprint-Based Deep-Learning Classifier Blockchain-Enabled Infection Sample Collection System Using Two-Echelon Drone-Assisted Mechanism Joint Trajectory Design and Resource Optimization in UAV-Assisted Caching-Enabled Networks with Finite Blocklength Transmissions
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1