Shadows, in aerial and satellite high-resolution images of earth, are a common phenomenon. Shadow causes false-color image, loss of information in the image, and false image segmentation. This leads to incorrect outputs of many image processing applications. In this paper, we address the problem of shadow detection in aerial high-resolution images of earth. The paper presents a proposed method that can be valuable in comparing it with other existing methods. The proposed work exploits the impact of ratio image pixel values on the process of shadow detection. The ratio image is the mathematical division of hue over the intensity component in the invariant color model. We propose a method, design, and develop an algorithm. In the designed algorithm, the input RGB aerial image of the earth is transformed into the invariant color model hue, saturation, and value (HSV). It acquires the average intensity value of pixels of the input RGB image components. Then, the ratio image of Hue (H) over Value (V) is calculated. Afterward, a power function is applied to this ratio to modify it by increasing the difference between pixel values very effectively. Finally, a threshold is applied to the modified ratio image to classify pixels into shadow and nonshadow. The proposed power function helps the threshold to better classify pixels into shadow and nonshadow. It has been implemented and experimented extensively. A comparative study has also been made with existing methods in the literature. In comparing the proposed algorithm and some existing algorithms, the experimental results show that the proposed has the ability to detect shadows with satisfying accuracy.

在航空和卫星高分辨率地球图像中的阴影是一种常见现象。阴影会导致图像伪彩色，图像信息丢失以及图像分割错误。这导致许多图像处理应用程序的输出不正确。在本文中，我们解决了地球航拍高分辨率图像中的阴影检测问题。本文提出了一种建议的方法，该方法在与其他现有方法进行比较中可能是有价值的。拟议的工作利用比率图像像素值对阴影检测过程的影响。比率图像是色调在不变颜色模型中强度分量的数学划分。我们提出一种方法，设计并开发一种算法。在设计的算法中，输入RGB地球的航拍图像被转换为​​不变的颜色模型色调，饱和度和值（HSV）。它获取输入的RGB图像分量的像素的平均强度值。然后，色相（H）与值（V）进行计算。之后，将幂函数应用于此比率，以通过非常有效地增加像素值之间的差异来修改此比率。最后，将阈值应用于修改后的比率图像，以将像素分为阴影和非阴影。提出的幂函数有助于阈值更好地将像素分为阴影和非阴影。它已被实施和广泛试验。文献中的现有方法也进行了比较研究。实验结果表明，该算法具有较好的检测效果。