改进YOLOv5的光伏组件热斑及遮挡小目标检测

doi:10.3778/j.issn.1002-8331.2302-0061

摘要/Abstract

摘要： 热斑会严重影响光伏组件发电效率，利用红外光图像检测热斑，难以同时实现树叶、鸟粪等小型异物遮挡的有效识别，及时发现和清理异物可以有效降低因受到持续遮挡而引起的热斑。为实现对热斑更加全面的识别和处理，基于无人机巡检可见光和红外光视频图像尺寸及检测任务特点，结合K-means++算法与IoU指标改进了YOLOv5的锚框设定方案以改善结果的随机性；可见光场景中，针对遮挡物体较小导致难以检测的问题，在YOLOv5s6的主干网络中嵌入坐标注意力机制（coordinate attention，CA），设计了遮挡小目标检测模型（CA-YOLOv5s6）；红外光场景中，热斑区域较为明显，选择轻量化网络YOLOv5n作为其检测模型。实验结果显示：相较于YOLOv5s6，CA-YOLOv5s6的mAP提升了2.97个百分点，达到83.78%，Parameters减少了4.8×105，达到1.18×107，有效地提高了遮挡小目标的检测精度；YOLOv5n模型的mAP、FPS、Parameters分别为93.31%、83.3、1.76×106，可以更好地满足红外图像热斑检测的任务需求。

关键词: 光伏组件, 热斑故障, 异物遮挡, 小目标检测, YOLOv5, 坐标注意力

Abstract: Hot spots will seriously affect the power generation efficiency of photovoltaic modules, infrared image detection of hot spots is difficult to realize effective recognition of small foreign matters such as leaves and bird droppings, discovering and cleaning foreign matters timely can effectively reduce the hot spots caused by continuous covering. In order to realize more comprehensive recognition and treatment of hot spots, based on the image size of UAV inspection visible and infrared video and the characteristics of detection task, YOLOv5’s anchor frame setting scheme is improved by combining K-means++ algorithm and IoU index, the randomness of results has been improved. In the visible scene, aiming at the problem that small occluded objects make detection difficult, the small occluded objects detection model (CA-YOLOv5s6) is designed by embedding coordinate attention (CA) in YOLOv5s6’s backbone. In the infrared scene, the hot spot area is obvious in infrared image, the lightweight network YOLOv5n is selected as its detection model. The experimental results show that, compared with YOLOv5s6, the mAP of CA-YOLOv5s6 is increased by 2.97 percentage points to 83.78%, and the Parameters are reduced by 4.8×105 to 1.18×107, which effectively improves the detection accuracy of the occlusion small target. The mAP, FPS and Parameters of YOLOv5n are 93.31%, 83.3 and 1.76×106, which can better meet the task requirements of infrared image hot spot detection.

Key words: photovoltaic module, hot spot fault, foreign matters occlusion, small target detection, YOLOv5, coordinate attention

林正文, 宋思瑜, 范钧玮, 赵薇, 刘广臣. 改进YOLOv5的光伏组件热斑及遮挡小目标检测[J]. 计算机工程与应用, 2024, 60(1): 84-95.

LIN Zhengwen, SONG Siyu, FAN Junwei, ZHAO Wei, LIU Guangchen. Improved YOLOv5 Photovoltaic Module Thermal Spot and Occlusion Small Target Detection[J]. Computer Engineering and Applications, 2024, 60(1): 84-95.

参考文献

[1] 姜红丽, 刘羽茜, 冯一铭, 等. 碳达峰、碳中和背景下“十四五”时期发电技术趋势分析[J]. 发电技术, 2022, 43(1): 54-64.
JIANG H L, LIU Y X, FENG Y M, et al. Analysis of power generation technology trend in 14th Five-Year Plan under the background of carbon peak and carbon neutral[J]. Power Generation Technology, 2022, 43(1): 54-64.
[2] 李晖, 刘栋, 姚丹阳. 面向碳达峰碳中和目标的我国电力系统发展研判[J]. 中国电机工程学报, 2021, 41(18): 6245-6259.
LI H, LIU D, YAO D Y. Analysis and reflection on the development of power system towards the goal of carbon emission peak and carbon neutrality[J]. Proceedings of the CSEE, 2021, 41(18): 6245-6259.
[3] 李世民, 喜文华. 光伏组件热斑对发电性能的影响[J]. 发电设备, 2013, 27(1): 61-63.
LI S M, XI W H. Influence of hot sopt on power generaation performance of photovoltaic module[J]. Power Equipment, 2013, 27(1): 61-63.
[4] AZIZ F, UL HAQ A, AHMAD S, et al. A novel convolutional neural network-based approach for fault classification in photovoltaic arrays[J]. IEEE Access, 2020, 8: 41889-41904.
[5] 张文军. 基于深度学习的光伏发电系统运行状态监测与诊断研究[D]. 北京: 华北电力大学, 2021.
ZHANG W J. Research on operation condition monitoring and diagnosis of photovoltaic system based on deep learning[D]. Beijing: North China Electric Power University, 2021.
[6] 车曦. 基于红外图像识别的光伏组件热斑故障检测方法研究[D]. 重庆: 重庆大学, 2015.
CHE X. Research on image processing based photovoltaic modules hotspot detection[D]. Chongqing: Chongqing University, 2015.
[7] PIERDICCA R, MALINVERNI E S, PICCININI F, et al. Deep convolutional neural network for automatic detection of damaged photovoltaic cells[J]. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, 2018, 42(2): 893-900.
[8] 王奇, 任一峰, 王璐. 小型光伏热斑的全卷积网络模型检测[J]. 测试技术学报, 2022, 36(3): 199-205.
WANG Q, REN Y F, WANG L. Full convolutional network model detection for small photovoltaic hot spots[J]. Journal of Test and Measurement Technology, 2022, 36(3): 199-205.
[9] 郭梦浩, 徐红伟. 基于Faster RCNN的红外热图像热斑缺陷检测研究[J]. 计算机系统应用, 2019, 28(11): 265-270.
GUO M H, XU H W. Hot spot defect detection based on infrared thermal image and Faster RCNN[J]. Computer Systems & Applications, 2019, 28(11): 265-270.
[10] 贾帅康. 基于残差注意力机制的光伏组件热斑图像检测方法研究[D]. 北京: 华北电力大学, 2021.
JIA S K. Research on hot spot image detection method of photovoltaic module based on residual attention mechanism[D]. Beijing: North China Electric Power University, 2021.
[11] DI TOMMASO A, BETTI A, FONTANELLI G, et al. A multi-stage model based on YOLOv3 for defect detection in PV panels based on IR and visible imaging by unmanned aerial vehicle[J]. Renewable Energy, 2022, 193: 941-962.
[12] ZEFRI Y, SEBARI I, HAJJI H, et al. Developing a deep learning-based layer-3 solution for thermal infrared large-scale photovoltaic module inspection from orthorectified big UAV imagery data[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 106: 102652.
[13] 刘川. 基于工程环境背景下安全帽佩戴检测算法研究[J]. 河南科技, 2022, 41(4): 7-12.
LIU C. Research on the algorithm of safety helmet wearing detection based on the background of engineering environment[J]. Henan Science and Technology, 2022, 41(4): 7-12.
[14] 陈子文, 李卓璐, 杨志鹏, 等. 基于YOLOv5的工厂化养殖虾目标检测方法研究[J]. 海洋渔业, 2022, 44(5): 610-620.
CHEN Z W, LI Z L, YANG Z P, et al. Research on YOLOv5-based object detection method for factory farmed shrimp[J]. Marine Fisheries, 2022, 44(5): 610-620.
[15] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016: 779-788.
[16] REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[17] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[18] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland, September 6-12, 2014: 740-755.
[19] ARTHUR D, VASSILVITSKII S. k-means++: the advantages of careful seeding[C]//Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, 2007: 1027-1035.
[20] 傅荟瑾, 史天运, 王瑞, 等. 基于改进YOLOv5的高铁周界入侵人员检测方法研究[J]. 铁道标准设计, 2023, 67(9): 162-169.
FU H J, SHI T Y, WANG R, et al. Research on intrusion detection of high speed railway perimeter based on improved YOLOv5[J]. Railway Standard Design, 2023, 67(9): 162-169.
[21] 李登峰, 高明. 基于改进YOLOv5的海面目标检测算法[J]. 激光杂志, 2023, 44(5): 47-52.
LI D F, GAO M. Sea surface target detection algorithm based on improved YOLOv5[J]. Laser Journal, 2023, 44(5): 47-52.
[22] 高新波, 莫梦竟成, 汪海涛, 等. 小目标检测研究进展[J]. 数据采集与处理, 2021, 36(3): 391-417.
GAO X B, MO M J C, WANG H T, et al. Recent advances in small object detection[J]. Journal of Data Acquisition and Processing, 2021, 36(3): 391-417.
[23] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13713-13722.
[24] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125.
[25] LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8759-8768.
[26] 赵辉, 李志伟, 张天琪. 基于注意力机制的单发多框检测器算法[J]. 电子与信息学报, 2021, 43(7): 2096-2104.
ZHAO H, LI Z W, ZHANG T Q. Attention based single shot multibox detector[J]. Journal of Electronics & Information Technology, 2021, 43(7): 2096-2104.
[27] 王一旭, 肖小玲, 王鹏飞, 等. 改进YOLOv5s的小目标烟雾火焰检测算法[J]. 计算机工程与应用, 2023, 59(1): 72-81.
WANG Y X, XIAO X L, WANG P F, et al. Improved YOLOv5s small target smoke and fire detection algorithm[J]. Computer Engineering and Applications, 2023, 59(1): 72-81.
[28] 胡均平, 王鸿树, 戴小标, 等. 改进YOLOv5的小目标交通标志实时检测算法[J]. 计算机工程与应用, 2023, 59(2): 185-193.
HU J P, WANG H S, DAI X B, et al. Real-time detection algorithm for small-target traffic signs based on improved YOLOv5[J]. Computer Engineering and Applications, 2023, 59(2): 185-193.
[29] 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.
[30] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016: 21-37.