A classification method and device based on hyperspectral remote sensing images
A hyperspectral remote sensing and image technology, applied in the field of remote sensing, can solve problems such as over-classification and achieve the effect of avoiding over-classification
Active Publication Date: 2016-11-30
CENT FOR EARTH OBSERVATION & DIGITAL EARTH CHINESE ACADEMY OF SCI
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of this, an embodiment of the present invention provides a hyperspectral remote sensing image classification method and device, with the purpose of solving the problem of over-classification caused by the existing hyperspectral remote sensing image classification method
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
[0064] The embodiment of the present invention discloses a method and device for classifying hyperspectral remote sensing images. The core invention is to use the artificial bee colony algorithm to classify hyperspectral remote sensing images using the spatial neighborhood information of pixels in hyperspectral remote sensing images as constraints. The cluster center set of the image is optimized to obtain the optimal cluster center, and the hyperspectral remote sensing image is classified using the optimal cluster center.
[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative e...
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 embodiment of the present invention provides a hyperspectral remote sensing image classification method and device, using the spatial neighborhood information of the pixel in the hyperspectral remote sensing image as a constraint condition, and according to the calculated set of cluster centers, determined by artificial bee colony algorithm The optimal clustering center of the hyperspectral remote sensing image, and use the optimal clustering center to classify the targets in the hyperspectral remote sensing image. Therefore, in the process of classifying the targets in the image, not only the spectrum of the pixel is used as the basis , and based on the spatial neighborhood information of the pixel, according to the principle in geography that the closer in space, the higher the possibility of belonging to the same category. After considering the spatial neighborhood information of the pixel, the spectral difference is large but in space The possibility of the adjacent pixels being classified into one class is greatly increased, so the problem of over-classification can be avoided.
Description
technical field [0001] The invention relates to the field of remote sensing, in particular to a classification method and device based on hyperspectral remote sensing images. Background technique [0002] Hyperspectral remote sensing image is a kind of remote sensing image acquired by hyperspectral sensor, which can classify targets in hyperspectral remote sensing image and understand the situation of ground coverage. The existing classification methods for hyperspectral remote sensing images usually identify the categories of different targets based on the spectral information of different targets in hyperspectral images. [0003] Remote sensing images include a relatively wide range of coverage. What users want to know through hyperspectral remote sensing images is usually the main category of ground coverage, not the details. The existing hyperspectral image classification methods distinguish different targets based on different targets. Spectral features, therefore, are...
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 Patents(China)
IPC IPC(8): G06K9/62G06N3/00
Inventor 张兵孙旭高连如吴远峰李利伟庄丽娜
Owner CENT FOR EARTH OBSERVATION & DIGITAL EARTH CHINESE ACADEMY OF SCI