High-resolution image classification method and system based on pixel pairs and weighted voting
A weighted voting, high-resolution technology, applied in the field of remote sensing image processing, can solve problems such as different classification results and classification errors, different image segmentation results, etc., achieve strong spatial consistency, avoid high classification uncertainty, accuracy and highly adaptive effect
Active Publication Date: 2020-02-14
WUHAN UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Different image segmentation methods and segmentation parameters will inevitably lead to different image segmentation results, and different segmentation results will inevitably lead to different classification results and classification errors.
Therefore, there are often high uncertainties in the classification process and classification results of object-based image classification
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
[0051] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.
[0052] At present, most of the classic classification algorithms are mainly proposed for pixel-based classification, but in the classification of high-resolution images with obvious phenomena such as large noise and large intra-class differences, the pixel-by-pixel classification method that only uses pixels as the basic unit of classification , naturally have high classification uncertainty; and in object-oriented image classification, due to the high uncertainty of object segmentation, the classification process and results often have high classification unc...
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-resolution image classification method based on pixel pairs and weighted voting. The method comprises the following steps of: pairing all pixels in an image to form a series of pixel pairs, and initially classifying the image in different pairing modes by taking the pixel pairs as basic units of image classification to obtain a series of initial classification results; then, the junction suitability of each pixel pair formed by the junction pair is evaluated. And finally, taking the matching suitability as a weight, and carrying out weighted voting on an initialclassification result to obtain a final classification graph of the image. According to the classification method provided by the invention, the spatial correlation between pixels in the image is effectively considered to improve the precision and reliability of high-resolution image classification. The method has the advantages that the natural classification uncertainty of a single-pixel classification method is overcome by means of the pixel cluster classification advantage of object-oriented classification, and meanwhile high classification uncertainty caused by inaccurate image segmentation in object-oriented classification can be avoided.
Description
technical field [0001] The invention belongs to the field of remote sensing image processing, in particular to a high-resolution image classification method and system based on pixel pairs and weighted voting. Background technique [0002] Classification of high-resolution remote sensing images plays a very important role in many application fields, such as monitoring of the environment and sudden disasters, precision agriculture, urban management and decision-making, etc. However, with the continuous improvement of the spatial resolution of remote sensing images, the traditional pixel-based classification method is no longer suitable for the classification of high-resolution images, because the phenomena of noise and large intra-class differences in high-resolution images become more prominent, which is extremely It greatly affects the accuracy and reliability of pixel-based image classification methods. [0003] Object-based image classification methods take image objects...
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 Applications(China)
IPC IPC(8): G06K9/62G06K9/00G06K9/34
CPCG06V20/194G06V20/13G06V10/267G06F18/241
Inventor 张齐肖窈
Owner WUHAN UNIV