Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multispectral Image Classification Method Based on Recoding and Deep Fusion Convolutional Networks

A multi-spectral image and convolutional network technology, applied in the field of multi-spectral image classification, can solve the problems of high classification accuracy, difficult to achieve, and inability to make full use of data information, and achieve the effect of improving classification accuracy and enhancing generalization ability

Active Publication Date: 2020-11-03
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, in the processing of multispectral remote sensing images, the traditional convolutional neural network only extracts features on one scale and performs feature re-extraction for the same target. It does not consider the information fusion problem of different scales and cannot make full use of existing It is difficult to achieve high classification accuracy due to the data information

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
  • Multispectral Image Classification Method Based on Recoding and Deep Fusion Convolutional Networks
  • Multispectral Image Classification Method Based on Recoding and Deep Fusion Convolutional Networks
  • Multispectral Image Classification Method Based on Recoding and Deep Fusion Convolutional Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described below in conjunction with the accompanying drawings.

[0048] refer to figure 1 , the specific implementation steps of the present invention are as follows:

[0049] Step 1, input the multispectral image to be classified.

[0050] The images to be classified select the multispectral images of five cities obtained by Sentinel-2 satellite. The five cities are: Berlin (Germany), Hong Kong (China), Paris (France), Rome (Italy), and Sao Paulo (Brazil). A given multispectral image is partially labeled. There are 17 categories in total.

[0051] In step 2, the data of different bands in each given city image are stacked together to obtain the 3D image feature FA of the data source.

[0052] Step 3, input the classification auxiliary data of the multispectral image to be classified.

[0053] The classification auxiliary data uses the Osm Raster data corresponding to the five cities in step 1. The Osm Raster data comes from th...

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 a multi-spectral image classification method based on data recoding and deep fusion convolutional network, which stacks data of different bands in multi-spectral images to be classified to obtain three-dimensional image features FA; input the multi-spectral image to be classified Classify auxiliary data; then encode to obtain the three-dimensional image feature FB; combine the three-dimensional feature matrix FA and FB obtained after processing the two data sources as the input feature F; normalize F, and normalize the normalized feature Each element in the matrix F1 takes a block to form a feature matrix F2 based on the image block; according to F2, the feature matrix W1 of the training data set and the feature matrix W2 of the test data set are obtained; a classification model based on a multi-scale depth filter is constructed; The feature matrix W1 of the training data set is used to train the classification model; the feature matrix W2 of the test data set is used to classify the trained classification model. The invention improves the classification accuracy of the multi-spectral remote sensing images and can be used for classification of ground objects.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a multispectral image classification method based on data recoding and deep fusion convolutional network. Background technique [0002] Multi-spectral images are remote sensing images obtained by using satellite multi-spectral ground scanning systems, usually containing more than two spectral channels for synchronous imaging of ground objects. [0003] With the rapid development of the economy, the land use is also constantly changing. It is also becoming more and more difficult to monitor land use in real time by human. The development of satellite remote sensing technology has solved this problem to a certain extent. Through high-altitude scanning and imaging, satellite remote sensing can obtain real-time information on ground conditions, and has been more and more widely used in land use monitoring and other aspects. As an important source of remote sensing data,...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V20/13G06N3/045G06F18/2414
Inventor 焦李成屈嵘侯瑶淇马文萍杨淑媛侯彪刘芳尚荣华张向荣张丹唐旭马晶晶
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products