This paper puts forward an effective, specific algorithm for edge detection. Based on multi-structure elements of gray mathematics morphology, in the light of difference between noise and edge shape of RS images, the ...This paper puts forward an effective, specific algorithm for edge detection. Based on multi-structure elements of gray mathematics morphology, in the light of difference between noise and edge shape of RS images, the paper establishes multi-structure elements to detect edge by utilizing the grey form transformation principle. Compared with some classical edge detection operators, such as Sobel Edge Detection Operator, LOG Edge Detection Operator, and Canny Edge Detection Operator, the experiment indicates that this new algorithm possesses very good edge detection ability, which can detect edges more effectively, but its noise-resisting ability is relatively low. Because of the bigger noise & remote sensing image, the authors probe into putting forward other edge detection method based on combination of wavelet directivity checkout technology and small-scale Mathematical Morphology finally. So, position at the edge can be accurately located, the noise can be inhibited to a certain extent and the effect of edge detection is obvious.展开更多
The subsiding land can be extracted from Remote Sensing image based on itsspectral and spatial features. The features of subsiding land caused by raining, especially its RSinformation features and relative knowledge a...The subsiding land can be extracted from Remote Sensing image based on itsspectral and spatial features. The features of subsiding land caused by raining, especially its RSinformation features and relative knowledge are proposed. Three methods can be used to extractsubsiding land from RS image. The first is to categorize the region into different blocks (orlayers) according to their features and apply corresponding strategies for each block, the second isto identify the changeable region based on GIS firstly and then to classify those regions, and thethird is to post-process the classified image by traditional methods or ANN (Artificial NeuralNetwork) methods based on domain knowledge and GIS. Two direct extraction methods are introducedalso. One is the extraction based on the water accumulating property of subsiding land, and theother is based on the dynamic change of land cover in subsiding land.展开更多
基金Foundation item: Under the auspices of the National Natural Science Foundation of China (No. 49971055
文摘This paper puts forward an effective, specific algorithm for edge detection. Based on multi-structure elements of gray mathematics morphology, in the light of difference between noise and edge shape of RS images, the paper establishes multi-structure elements to detect edge by utilizing the grey form transformation principle. Compared with some classical edge detection operators, such as Sobel Edge Detection Operator, LOG Edge Detection Operator, and Canny Edge Detection Operator, the experiment indicates that this new algorithm possesses very good edge detection ability, which can detect edges more effectively, but its noise-resisting ability is relatively low. Because of the bigger noise & remote sensing image, the authors probe into putting forward other edge detection method based on combination of wavelet directivity checkout technology and small-scale Mathematical Morphology finally. So, position at the edge can be accurately located, the noise can be inhibited to a certain extent and the effect of edge detection is obvious.
基金Under the auspices of the Research Foundation of Doctoral Point of China(No.RFDP20010290006).
文摘The subsiding land can be extracted from Remote Sensing image based on itsspectral and spatial features. The features of subsiding land caused by raining, especially its RSinformation features and relative knowledge are proposed. Three methods can be used to extractsubsiding land from RS image. The first is to categorize the region into different blocks (orlayers) according to their features and apply corresponding strategies for each block, the second isto identify the changeable region based on GIS firstly and then to classify those regions, and thethird is to post-process the classified image by traditional methods or ANN (Artificial NeuralNetwork) methods based on domain knowledge and GIS. Two direct extraction methods are introducedalso. One is the extraction based on the water accumulating property of subsiding land, and theother is based on the dynamic change of land cover in subsiding land.
