Hyperspectral image sub-pixel positioning method under description of spatial attraction
A hyperspectral image and sub-pixel technology, applied in the field of remote sensing information processing, can solve problems such as limiting deeper applications, correlation without considering pixel correlation, and spatial correlation without consideration
Inactive Publication Date: 2011-12-28
HARBIN ENG UNIV
View PDF2 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the SPSAM method does not fully implement the spatial correlation theory, and this defect also limits its deeper application to a certain extent.
On the one hand, when SPSAM solves the spatial gravitational force of the neighboring pixels on the sub-pixels in the central pixel, it considers the neighboring pixels as a whole to calculate the gravitational force. This way of describing the spatial gravitational force is inaccurate
On the other hand, SPSAM only considers the spatial correlation between the neighboring pixels and the central pixel, but does not consider the spatial correlation of the sub-pixels in the central pixel itself, that is, only the correlation between the pixels is considered and the The correlation within the pixel is not considered, so the expression of spatial correlation is not perfect
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
[0026] The present invention will be described in more detail below in conjunction with the accompanying drawings.
[0027] Step 1: Preprocessing of hyperspectral images:
[0028] The hyperspectral image is input, and the spectral mixture analysis technology of the linear spectral mixture model (LSMM) is used to obtain the mixture ratio value of each category in the mixed pixel of the hyperspectral image. Set S as the magnification ratio of sub-pixel positioning, that is, each pixel is divided into SλS sub-pixels, and each mixing ratio value is quantized as One of them, get the component map F of each category c ( C is the total number of categories), as the input data for the next step of sub-pixel positioning.
[0029] Step 2: Initialization of the SPSAM method:
[0030] 1. Select the mixed pixel P to be analyzed ab , the operation steps are as follows:
[0031] 1), calculate each sub-pixel p ij ( S is the magnification ratio) affected by the neighborhood pixel P ...
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 provides a hyperspectral image sub-pixel positioning method under description of spatial attraction. the method comprises the following steps: pretreatment on a hyperspectral image; initialization of a sub-pixel / pixel spatialattraction model (SPSAM) method; and description on spatial attraction, wherein spatial correlation are completely implemented in the description. According to the initialization of the SPSAM method, a preliminary sub-pixel positioning result is obtained by utilizing the SPSAM method and is used as an input of the next step. According to the spatial attraction description method with complete implementation of spatial correlation, the spatial correlation between pixels is considered and correlation between the sub-pixels in a pixel is also taken into account; meanwhile, the description on spatial correlation between the pixels is realized by calculating spatial attraction between a sub-pixel and a sub-pixel in a neighborhood pixel. Therefore, the method provided in the invention has advantages of complete implementation of spatial correlation and high-precision positioning of a sub-pixel.
Description
technical field [0001] The invention relates to a sub-pixel positioning method of a hyperspectral image, in particular to a sub-pixel positioning method under spatial gravity description, and belongs to the technical field of remote sensing information processing. Background technique [0002] The spectral resolution of hyperspectral images is high, but their spatial resolution is generally low, which leads to the widespread existence of mixed pixels, that is, a pixel may be a mixture of several categories. For such pixels, using the traditional hard classification method to judge them as any type will lead to the loss of information and it is difficult to meet the realistic requirements. Spectral mixing analysis (also known as spectral unmixing) technology solves the proportion of each category in the mixed pixel, but fails to give the spatial distribution of categories. Sub-pixel positioning technology is developed to solve this problem. In fact, spatial resolution is an...
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 IPC IPC(8): G06K9/80
Inventor 王立国王群明刘丹凤赵春晖
Owner HARBIN ENG UNIV