Supercharge Your Innovation With Domain-Expert AI Agents!

Object-oriented single-class classification method for remote sensing image

A remote sensing image, object-oriented technology, used in instruments, character and pattern recognition, computer parts and other directions, can solve the problem of complex parameter settings, simplify the classification process, reduce intra-class variance, and increase inter-class separability Effect

Inactive Publication Date: 2016-05-04
ZHENGZHOU UNIVERSITY OF AERONAUTICS
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There is also a method based on support domain description (support vector data description, SVDD), using a sphere as small as possible containing the target data for discrimination, and a better classification effect can be obtained by training with a small sample. The main disadvantage of the SVDD method is also the comparison of parameter settings. complex

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
  • Object-oriented single-class classification method for remote sensing image
  • Object-oriented single-class classification method for remote sensing image
  • Object-oriented single-class classification method for remote sensing image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Example 1: The experimental images are two TM remote sensing images, such as figure 1 Shown, where figure 1 (a) Contains four categories of impervious surface, grassland, woodland and water body, figure 1 (b) It also contains four categories: impervious surface, water body, cultivated land and village.

[0031] The nearest neighbor method is used to extract single-type information, and non-interest-type samples are selected around the interest-type samples. This method reduces the workload of sample selection. Correct figure 1 The TM experimental image in (a), with impervious surface as the interest category, the selection of training samples is as figure 2 As shown in (a), the white area is the interest category sample, and the surrounding black area is the non-interest category sample. figure 2 (b) is the classification result. The accuracy evaluation indicators of single-type information extraction are generally production accuracy and user accuracy. Production accurac...

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 discloses an object-oriented single-class classification method for a remote sensing image and relates to the technical field of remote sensing image classification. The method comprises following steps: (1) a class space is divided into an interest class and a non-interest class; (2) training samples of interest class and training samples of the non-interest class are selected according to the image space proximity; (3) partial training samples of interest class and partial training samples of the non-interest class are selected according to the image space proximity; (4) on the basis of samplings of the two classes, nearest-neighbor classifying is performed to extract an interest class. By use of the method, sampling selection process is simplified, and remote sensing image single-class information is effectively extracted.

Description

Technical field [0001] The present invention relates to the technical field of remote sensing image classification, in particular to an object-oriented single-class classification method of remote sensing images. Background technique [0002] In recent years, multi-class classification methods have emerged in an endless stream, and the use of single-class classifiers to extract interest categories in remote sensing images, there are few related studies. A commonly used single-class classifier is the one-class support vector machine (OCSVM). In the high-dimensional space, the OCSVM method finds a hyperplane with the largest interval that can separate the interest categories. Its disadvantage is that it is difficult to select free parameters. In the process of constructing classifiers, in addition to interest category samples, unlabeled samples also provide useful information. For example, the TransductiveSVM (TSVM) method can get better classification performance by using unlabel...

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): G06K9/62
CPCG06F18/24317
Inventor 薄树奎李向荆永菊郑小东金秋春李玲玲
Owner ZHENGZHOU UNIVERSITY OF AERONAUTICS
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com