Adaptive extraction of water in urban areas based on local iteration using high-resolution multi-spectral image

Urban water extraction from high-resolution remote sensing image is one of important aspects for regional-urban environment research. However, the past researches mainly centered upon moderate and low resolution image, water body in open country and global scale for water extraction, which can´t achieve better performance. To solve those problems, an adaptive method to extract urban water was proposed based on local iteration using high-resolution remote sensing image. In each iteration, segmented buffers were constructed with adaptive length and radius to exploit information in local scale, and also spatial consistency was token into account for an improvement of local classification. Experiments demonstrated that the proposed method was applicable in urban water extraction from high-resolution image.