Multi-scale segmentation of remote sensing image based on watershed transformation
ABSTRACT Image segmentation is an important step for classification and feature extraction of high resolution remote sensing image. The purpose of this study is to find an improved segmentation method suitable for high resolution remote sensing image. Firstly a region homogeneity indictor called H index was introduced. Then the optimized edge gradient was obtained based on the integration of Canny operator and H index. A watershed transformation followed up to acquire the initial segmentation of the remote sensing image. To eliminate the over-segmentation, a multi-scale merging according to object-oriented principle was finally conducted. A multi-spectrum QuickBird remote sensing image was segmented per the above-mentioned method. The improved H gradient image effectively overcame the limitations of week edges in high resolution remote sensing image, and on the whole the QuickBird image was segmented into homogeneity objects. It proves that the improved segmentation method is suitable to high resolution remote sensing images.
- [Show abstract] [Hide abstract]
ABSTRACT: Some remote sensing image segmentation algorithm can not make full use of local and global information and Normalized has NP-hard problem. In order to solve the problems, image can be described through the graph model and the Normalized cut can be used to cut graph for image segmentation. Watershed algorithm is applied to create the initial segments, and then Normalized cut is used to segment among regions. Experimental result shows that the method is effective.
Conference Paper: A new image segmentation method based on optical degradation model[Show abstract] [Hide abstract]
ABSTRACT: For machine vision inspection systems, captured images are often degraded to various extents because of the lens spherical aberration. In order to solve this problem, this paper introduces a new method which first found an optical degradation model (ODM) by the point illumination in the image plane, and simplified the optical degradation model based on the properties of illumination distribution. The method compensated the background from the original image and employed global threshold to make better segmentation. The performance of the new method is validated by a comparison with the Otsu's segmentation method, as well as the adaptive threshold method.International Conference on Automatic Control and Artificial Intelligence (ACAI 2012); 01/2012