A method for detecting artificial objects in natural environments

In this paper we present a method for automatic detection of man-made objects in digital images representing natural environments. This method is based on statistical distribution of texture patterns in the image. This distribution is computed using Zipf´s law. The image is divided into sub-frames and Zipf´s distribution is computed for each sub-frame. Then the surfaces under Zipf´s plots of the different sub-frames are compared in order to determine which sub-frame contains an object. The sensitivity of this detection method to image resolution is also examined.