The number of photovoltaic panels installed globally is continuously growing, requiring an automatic inspection procedure for operation and maintenance. Drones can be a useful tool to this aim as they enable fast acquisition of various imaging modalities: visual, infrared, or electroluminescence (EL). Image distortions due to perspective must be corrected to allow further automatic processing. It can be done by estimating the corresponding rotation angles to control the camera gimbal or as postprocessing to rectify the images. This article presents two methods to achieve both goals by identifying known points in the acquired image. The first method detects the four panel corners, whereas the second method finds the corners of each cell. The performance evaluation is performed first quantitatively on a validation dataset composed of 113 EL images and their corresponding ground-truth orientations. A qualitative evaluation shows satisfying performance of the rectification similarly for both methods. The quantitative performance is varying for each rotation axis. The average absolute error is 2.78$^{\circ }$ along the $x$-axis, 2.64$^{\circ }$ along the $y$-axis, and 1.28$^{\circ }$ along the $z$-axis for the panel method and 3.26$^{\circ }$, 2.05$^{\circ }$, and 1.24$^{\circ }$ for the cell method. As a proof of concept, a final test on drone-acquired EL images shows good performance for the image rectification in real-life conditions.

中文翻译：

---

光伏板电致发光图像透视畸变的估计和校正方法

全球安装的光伏面板数量不断增加，需要自动检查程序进行操作和维护。无人机可以成为实现这一目标的有用工具，因为它们能够快速获取各种成像模式：视觉、红外或电致发光 (EL)。必须校正由于透视导致的图像失真，以允许进一步的自动处理。它可以通过估计相应的旋转角度来控制相机万向节或作为后处理来校正图像来完成。本文介绍了通过识别获取图像中的已知点来实现这两个目标的两种方法。第一种方法检测四个面板角，而第二种方法找到每个单元格的角。性能评估首先在由 113 个 EL 图像及其相应的地面实况方向组成的验证数据集上进行定量。定性评估表明两种方法的整流性能相似。每个旋转轴的定量性能都不同。平均绝对误差为 2.78$^{\circ }$ 沿着 $x$-轴，2.64$^{\circ }$ 沿着 $y$-轴和 1.28$^{\circ }$ 沿着 $z$- 面板方法和 3.26 的轴$^{\circ }$, 2.05$^{\circ }$, 和 1.24$^{\circ }$对于细胞方法。作为概念证明，对无人机获取的 EL 图像的最终测试显示了在现实生活条件下图像校正的良好性能。