Building recognition hybrid algorithm for satellite images based on the beetle method and the area exclusion algorithm

The article proposes a new method for recognizing buildings on satellite images. The proposed method is a hybrid, it is based on the region exclusion algorithm and the beetle method. The region exclusion algorithm is a well-known and effective approach to object detection on the image. Its main idea is to segment an image into regions of similar pixels based on various characteristics: color, texture, brightness, shape, etc. The beetle method is a classic contour analysis method that sequentially draws the boundary between an object and its background. As part of the proposed method, the beetle method first identifies potential areas where buildings may be located. The region exclusion method then eliminates unwanted elements in the image (vegetation, water surfaces and roads) that could be falsely identified as buildings, and accurately determines the location and outline of buildings. The offered algorithm shows good recognition accuracy regardless of image quality and does not require a training sample. The article also describes the software implementation of the proposed method and discusses the results of computational experiments to assess the quality of the method and compare it with three well-known recognition algorithms.