An Approach for Shadow Detection in Aerial Images Based on Multi-Channel Statistics

Abstract

Shadows are likely to cause flaws in color interpretation, loss of image information or deformation of objects; this is a relevant issue owing to the fact that with the development of unmanned aerial vehicles and satellite devices, object detection by aerial images has become an essential aim to research works. The main contribution of this article is the development of an algorithm that processes shadow detection by detaching the channels red, green, blue and an additional low saturation channel on individual masks; having created those masks, the task of shadow detection is accomplished by conducting a pixel-by-pixel basis with the aid of a decision tree and statistical descriptors extracted out of the image, where the low saturation channel information leads to improvements on shadow detection accuracy in regions that contain asphalt and concrete. Thus, experimental results show the good behavior of shadow detection algorithm in terms of accuracy, over-segmentation, and under-segmentation, in which the accuracy of obtained shadow detection approaches a 94%.

Keywords

• Unmanned aerial vehicles
• color
• remote sensing
• image processing
• image segmentation
• pattern recognition