A method and apparatus for image fusion classification

A technology of classifier and segmentation method, applied in the computer field, can solve the problem that the number of superpixels is difficult to obtain accurate estimation

Active Publication Date: 2019-03-15
SHENZHEN UNIV
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the existing methods using superpixels, there is a huge defect, th

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and apparatus for image fusion classification
  • A method and apparatus for image fusion classification
  • A method and apparatus for image fusion classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] An embodiment of the present invention provides a method and device for image fusion classification, the method includes: using a support vector machine classifier to obtain a three-dimensional weight matrix of a hyperspectral image; performing superpixel segmentation on the hyperspectral image to obtain K A superpixel map, wherein K is a positive integer; the three-dimensional weight matrix is ​​regularized by using the segmentation method of the superpixel map to obtain a regular matrix; and the category to which the sample belongs is determined according to the regular matrix. By using the method provided by the present invention, the problem of estimating the number of superpixels can be avoided, and further, the spatial structure information of ground objects contained in different superpixel maps is fused in a cascading manner, which significantly improves the discrimination of features.

[0049] In order to enable those skilled in the art to better understand the so...

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

No PUM Login to view more

Abstract

The invention provides a method and a device for image fusion classification. The method comprises the following steps: obtaining a three-dimensional weight matrix of a hyperspectral image by a support vector machine classifier; Performing superpixel segmentation on the hyperspectral image to obtain K superpixel images, wherein K is a positive integer; Regularizing the three-dimensional weight matrix using a partitioning method of the superpixel map to obtain a regular matrix; The category to which the sample belongs is determined according to the regular matrix. By using the method provided by the invention, the problem of estimating the number of the superpixels can be avoided, furthermore, the spatial structure information of the ground objects contained in different superpixel maps isfused in a cascade manner, and the distinguishing power of the features is remarkably improved.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method and device for image fusion classification. Background technique [0002] With the advancement of image segmentation technology in the field of computer vision, superpixel extraction can provide a homogeneous spatial representation of observed objects, thus providing an important means of describing ground object information for hyperspectral image analysis. [0003] Specifically, a superpixel refers to a homogeneous region that contains multiple pixels. Since the distribution of ground objects often has certain regularity, hyperspectral images based on superpixel segmentation can better mine the gaps between neighboring pixels. mutual relationship. At present, the methods of using superpixels to classify hyperspectral images are mainly divided into two categories: pre-processing and post-processing. In the pre-processing, the superpixel information is mainly used to obtain th...

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
no application Login to view more
IPC IPC(8): G06K9/00G06K9/34G06K9/62G06V20/13
CPCG06V20/194G06V20/13G06V10/267G06F18/2411G06T7/11G06F18/2415G06F18/21G06F18/254
Inventor 贾森邓彬朱家松邓琳李清泉
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap