High spatial resolution image residential area extraction method based on characteristics of spatial correlation and heterogeneity
A technology of spatial correlation and extraction method, applied in the field of high-resolution image residential area extraction, which can solve the problem of insufficient accuracy of target structure description
Inactive Publication Date: 2017-03-22
WUHAN UNIV
View PDF3 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In the traditional image structure feature modeling method based on spatial statistics, only the spatial correlation or variability features between pixels are used, which has insufficient accuracy in describing the target structure.
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
[0029] The present invention is mainly based on remote sensing information science, combined with the method of spatial statistics to quantify the spatial layout mode in high-resolution images, and proposes a structural feature modeling method that integrates spatial autocorrelation statistics and spatial variation functions in spatial statistics. The present invention starts from the completeness of describing the characteristics of the object, and describes the structure of the object from the two perspectives of correlation and variation, so as to obtain more effective and robust structural characteristic description parameters.
[0030] The following will take QuickBird high-resolution remote sensing image residential area extraction as an example, combined with figure 1 The process of the present invention is described in detail.
[0031] Step 1. Use ENVI to perform false-color synthesis on multi-band original images. Select band 3 to correspond to the red channel, band 2...
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 high spatial resolution image residential area extraction method based on characteristics of spatial correlation and heterogeneity. The high spatial resolution image residential area extraction method based on characteristics of spatial correlation and heterogeneity includes the steps: performing false color composite on the original images of multiband to obtain false color images; selecting natural object samples from the false color images, and calculating the spectral characteristic curve of each type of natural object, wherein the spectral values corresponding to the spectral characteristic wave bands are the spectral characteristics; utilizing a spatial autocorrelation accountancy capability as the local tolerance index of spatial correlation, and constructing the spatial correlation characteristics of the false color images; utilizing a spatial variation function to calculate the characteristics of spatial heterogeneity of the false color images; and combined with the spectral characteristics, the characteristics of spatial correlation, and the characteristics of spatial heterogeneity, constructing a characteristic set, and performing target natural object extraction on the false color images. The high spatial resolution image residential area extraction method based on characteristics of spatial correlation and heterogeneity comprehensively utilizes the spatial correlation accountancy capability and the spatial variation function to describe the spatial structure mode of images to realize effective modeling of high spatial resolution image spatial structural characteristics and provide reliable support for effective identification of the image target.
Description
technical field [0001] The invention belongs to the field of remote sensing science and technology, and in particular relates to a high-resolution image residential area extraction method based on spatial correlation and heterogeneity features. Background technique [0002] In recent years, remote sensing earth observation technology has developed rapidly, the types of data obtained have been continuously enriched, and the quality of data has been continuously improved. Modern remote sensing is entering a new era that can provide high spatial resolution (hereinafter referred to as "high score"), high temporal resolution, and high spectral resolution image data from multiple platforms, multiple sensors, and multiple angles. The spatial resolution of some commercial satellites has reached the meter or sub-meter level. For example, the image resolution of QuickBird reaches 0.61m, the image resolution of GeoEye-1 is 0.41m, and the spatial resolution of some military satellite im...
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): G06K9/00G06K9/46
CPCG06V20/176G06V10/44
Inventor 秦昆张恩兵张晔岳梦雪
Owner WUHAN UNIV