Quick auction chart-based semi-supervised polarimetric SAR classification method
A classification method and a semi-supervised technology, applied in the field of image processing, can solve the problems of ignoring the spatial information of the image, the division error of the details of the image, and the large amount of calculation, so as to reduce the time, improve the accuracy, and reduce the time of composition Effect
Inactive Publication Date: 2016-11-16
XIDIAN UNIV
View PDF3 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Although the graph-based classification methods have achieved a high classification accuracy rate in image classification, there are still two shortcomings: one is that in the process of composition, the spatial information of the image is ignored, resulting in a certain degree of difficulty in dividing the details of the image. error
Second, the composition method has a high time complexity and a large amount of computation
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] refer to figure 1 , the specific implementation steps of the present invention are as follows:
[0023] Step 1. Image preprocessing
[0024] (1a) Obtain the coherent feature data X of the polarimetric SAR image from the polarimetric SAR image data folder of the computer hard disk;
[0025] (1b) Using the Pauli decomposition method to process the coherent feature data of the polarimetric SAR image to obtain the Pauli RGB image
[0026] (1c) Use the superpixel segmentation method to divide its Pauli RGB image into 50 blocks. The polarimetric SAR image used in this experiment
[0027] It is a 120×80 farmland simulation map;
[0028] Step 2. Use the segmented Pauli RGB image to weight the spatial information of each pixel
[0029] (2a) Each pixel of the Pauli RGB image x i The surrounding m pixels are X m ={x i1 ,x i2 ,x ij ...,x im}∈R d×m means that x ij ∈X m Represents the pixel point x i The jth pixel around, j=1,2,...,m, d is the dimension of the pixel dat...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a quick auction chart-based semi-supervised polarimetric SAR classification method, and mainly aims at solving the problem that the structural map matrixes are high in complexity and low in classification correctness in the prior art. The method comprises the following steps of: 1) segmenting polarimetric SAR image data; 2) adding spatial information to pixel points in segmented images; 3) solving a similar adjacency matrix for a pixel point data set after spatial information weighting; 4) optimizing the similar adjacency matrix to obtain an auction chart matrix; 5) carrying out sparse processing on the auction chart matrix to obtain a sparse auction chart matrix; 6) carrying out semi-supervised classification on the data set by utilizing the sparse auction chart matrix so as to obtain a class label matrix of each pixel point after classification; and 7) coloring all the pixel points by utilizing a class label of each pixel sample point and outputting the classified images. The method disclosed by the invention can be used for improving the classification correctness and shortening the classification time, and can be applied to the ground-object classification and object recognition of polarimetric SAR images.
Description
technical field [0001] The invention belongs to the technical field of image processing and relates to applications in the field of image classification, in particular to a semi-supervised polarization SAR classification method, which can be used for ground object classification and target recognition of polarization SAR images. Background technique [0002] Polarization SAR is a microwave imaging radar that utilizes the principle of synthetic aperture to achieve high resolution. Texture features and obvious geometric structures of ground objects can be widely used in many fields such as military affairs, agriculture, navigation, and geographical surveillance. It is highly valued in the field of international remote sensing, so polarimetric SAR image classification has become an important research direction of polarimetric SAR information processing. [0003] The purpose of polarimetric SAR image classification is to use the polarization measurement data obtained by airborn...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/241
Inventor 刘红英邢兴焦李成熊涛慕彩红王艺恺缑水平王爽侯彪
Owner XIDIAN UNIV