Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (1): 84-95.DOI: 10.3778/j.issn.1002-8331.2302-0061

• Special Issue on YOLO Improvements and Applications • Previous Articles     Next Articles

Improved YOLOv5 Photovoltaic Module Thermal Spot and Occlusion Small Target Detection

LIN Zhengwen, SONG Siyu, FAN Junwei, ZHAO Wei, LIU Guangchen   

  1. 1.School of Mathematics and Statistics, Ludong University, Yantai, Shandong 264025, China
    2.School of Information and Electrical Engineering, Ludong University, Yantai, Shandong 264025, China
  • Online:2024-01-01 Published:2024-01-01

改进YOLOv5的光伏组件热斑及遮挡小目标检测

林正文,宋思瑜,范钧玮,赵薇,刘广臣   

  1. 1.鲁东大学 数学与统计科学学院,山东 烟台 264025
    2.鲁东大学 信息与电气工程学院,山东 烟台 264025

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

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