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.
- SourceAvailable from: psu.edu[show abstract] [hide abstract]
ABSTRACT: A fast and flexible algorithm for computing watersheds in digital gray-scale images is introduced. A review of watersheds and related motion is first presented, and the major methods to determine watersheds are discussed. The algorithm is based on an immersion process analogy, in which the flooding of the water in the picture is efficiently simulated using of queue of pixel. It is described in detail provided in a pseudo C language. The accuracy of this algorithm is proven to be superior to that of the existing implementations, and it is shown that its adaptation to any kind of digital grid and its generalization to n -dimensional images (and even to graphs) are straightforward. The algorithm is reported to be faster than any other watershed algorithm. Applications of this algorithm with regard to picture segmentation are presented for magnetic resonance (MR) imagery and for digital elevation models. An example of 3-D watershed is also providedIEEE Transactions on Pattern Analysis and Machine Intelligence 07/1991; 13(6):583-598. · 4.80 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: A new segmentation method based on the morphological characteristic of connected components in images is proposed. Theoretical definitions of morphological leveling and morphological spectrum are used in the formal definition of a morphological characteristic. In multiscale segmentation, this characteristic is formalized through the derivative of the morphological profile. Multiscale segmentation is particularly well suited for complex image scenes such as aerial or fine resolution satellite images, where very thin, enveloped and/or nested regions must be retained. The proposed method performs well in the presence of both low radiometric contrast and relatively low spatial resolution. Those factors may produce a textural effect, a border effect, and ambiguity in the object/background distinction. Segmentation examples for satellite images are givenIEEE Transactions on Geoscience and Remote Sensing 03/2001; · 3.47 Impact Factor
Conference Proceeding: Use of watersheds in contour detectionInternational workshop on image processing, real-time edge and motion detection; 01/1979