光伏板的异物检测方法、装置、设备及存储介质
By fusing and matching the image to be tested and the template image of the photovoltaic panel and performing image processing, combined with the genetic algorithm to determine the connected components, the problem of low accuracy in foreign object detection of photovoltaic panels is solved, and efficient identification of foreign objects is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GREE ELECTRIC APPLIANCE INC OF ZHUHAI
- Filing Date
- 2023-12-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for detecting foreign objects in photovoltaic panels have low accuracy when data is limited, especially for small-sized foreign objects and foreign object types not included in the dataset.
By acquiring the image of the photovoltaic panel to be tested and the template image, fusion matching and image processing are performed. The optimal matching coefficient is determined by using a genetic algorithm, and the presence of connected components is determined by image processing to identify foreign objects.
It improves the accuracy of foreign object detection on photovoltaic panels, avoids the problem of low detection accuracy due to small datasets, and can effectively identify foreign objects under different detection environments.
Smart Images
Figure CN117522858B_ABST