Multi-scale and Multi-feature Segmentation of High Resolution Remote Sensing Image

Abstract

With the development of the remote sensing technology, high resolution remote sensing images widely penetrates into the common people's life. Traditional medium or low resolution image processing method based on pixel doesn't meet people's requirement any more. In view of it, this paper puts forward a high resolution remote sensing image segmentation method based on the traditional watershed algorithm with multiple scales and characteristics and introduces two new concepts-wrong waterlogging basin and merging array. It firstly improves the immersion process of traditional algorithm, then optimizes the wrong water logging basin and the merging array of basin, adopts the eight immersion neighbors avoiding the wrong division based on four neighbors immersion, optimizes the multilayer immersion process, segments the high resolution remote sensing image with different scales and different features, and finally combines the similar regions. The simulation experiments show that the improved watershed algorithm not only keeps the accurate segmentation effect of traditional algorithm, but also has much higher efficiency.