Extraction of Urban Road Network from Multispectral Images

This book is focused on the extraction of the urban Road network from multispectral images by combining kernel statistic and mathematical morphology. This research is focused on kernel statistics segmentation techniques and morphological operations such as dilation erosion opening and closing to extract the urban road from high-resolution satellite imagery such as IKONOS and Quickbird images. Furthermore we applied and developed morphological operation and automatic thresholding methods combine to extract the road centrelines of the urban environment. Based on the morphological methods an object''s extractor is designed to extract road networks from high satellite images. The unsupervised classification techniques such as ISODATA and K-mean algorithm employed to classify the images and to extract the road network.