An Image Segmentation Algorithm for the Hyperspectral Remote Sensing Image

The technology of hyperspectral remote sensing image improves the capability of collecting the objects such as lakes, rivers, farmlands, buildings, forest and desert in the ground surface. Since the spatial resolution is becoming higher recently, image segmentation of hyperspectral remote sensing is important to the next step of remote sensing image classification and object recognition. In this paper, we proposed a new algorithm using mean shift filtering, and watershed transform, for hyperspectral image segmentation. Usually, hyperspectral image has hundreds of spectral bands, thus, it is difficult for image segmentation. First, the mean shift algorithm is used for smoothing these all bands. Second, Canny edge detection method and vector field model are used to calculate edge strength of these bands, respectively. Finally, automatic marker watershed transform is applied for the edge strength to obtain the segmentation result. In order to evaluate the efficiency of the novel hyperspectral image segmentation algorithm, an unsupervised entropy based evaluation method, is performed on the segmentation result from AVIRIS hyperspectral data. The experimental results illustrate that the proposed algorithm can be used to obtain better segmentation results for hyperspectral data.