Automatic Extraction of Built-up Area Based on Deep Convolution Neural Network

Built-up area has been one of the most important objects to be extracted in remote sensing images. Several factors such as complex structure, diverse texture and varied background, bring the challenges for the task of built-up area extraction. In this paper, a multiple input structure of deep convolution neural network (CNN) is proposed to extract built-up area automatically, which can fuse the information of panchromatic and multispectral remote sensing image. The image patch based classification results are further refined by postprocessing of segmentation techniques. The experiments demonstrate that the proposed method has better generalization ability compared to the state-of-the-art method, and the overall classification accuracy is above 98%.