Unlock instant, AI-driven research and patent intelligence for your innovation.

Remote sensing image color evaluation method and system based on multilayer perceptron

A multi-layer perceptron and remote sensing image technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of poor anomaly detection effect, achieve high detection accuracy and automation, simple training, and improve detection efficiency Effect

Active Publication Date: 2020-05-01
CHINA SURVEY SURVEYING & MAPPING TECH
View PDF16 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, since there are various types of abnormal color images, for example, color cast images have various problems such as blue cast, purple cast, green cast, red cast, etc. Therefore, a single problem-oriented direct analysis and calculation method is used to perform abnormal Poor detection effect

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
  • Remote sensing image color evaluation method and system based on multilayer perceptron
  • Remote sensing image color evaluation method and system based on multilayer perceptron
  • Remote sensing image color evaluation method and system based on multilayer perceptron

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Such as figure 1 , in this embodiment, the remote sensing image color evaluation method based on the multi-layer perceptron includes:

[0028] Step 101, constructing a remote sensing image thumbnail sample library carrying tag information.

[0029] In this embodiment, the construction method of the sample library can be as follows: obtain the multi-spectral remote sensing image collected by the multi-spectral camera of the remote sensing satellite; perform down-sampling and true-color composite processing on the multi-spectral remote sensing image to obtain the remote sensing image in jpg format Thumbnail; According to the color state information of the remote sensing image thumbnail in jpg format, tag the obtained remote sensing image thumbnail in jpg format; according to the tagged remote sensing image thumbnail in jpg format, construct the obtained The remote sensing image thumbnail sample library with label information is described.

[0030] Step 102, performing f...

Embodiment 2

[0058] On the basis of the above embodiments, the following will be described in conjunction with a specific example.

[0059] The embodiment of the present invention proposes a remote sensing image color evaluation method based on a multi-layer perceptron, which is used for automatic detection of problematic images in an optical remote sensing image production system. Firstly, extract the thumbnail features of the sample library; then build a multi-layer perceptron model; then use the feature set for model training to obtain tuned network parameters; finally use the trained network to evaluate the color of the new image.

[0060] Step 1: Prepare a remote sensing image thumbnail sample library.

[0061] Remote sensing image data are multi-spectral remote sensing images collected by remote sensing satellite multi-spectral cameras. Extract red, green, and blue channels from remote sensing images to synthesize true-color remote sensing images and down-sample to generate thumbnai...

Embodiment 3

[0074] On the basis of the above-mentioned embodiments, the present invention also discloses a remote sensing image color evaluation system based on a multi-layer perceptron, including: a sample construction module, used to construct a sample library of remote sensing image thumbnails carrying label information; feature extraction The module is used to extract the features of each thumbnail sample in the remote sensing image thumbnail sample library; the model building module is used to build a multi-layer perceptron neural network model to be trained for binary classification; the parameter training module is used to Each thumbnail sample and the extracted features in the remote sensing image thumbnail sample library are trained to train the multi-layer perceptron neural network model to obtain network parameters; the model update module is used to train the multi-layer perceptron neural network model according to the obtained network parameters. The parameters of the machine ...

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 remote sensing image color evaluation method and system based on a multilayer perceptron. The method comprises the following steps: constructing a remote sensing image thumbnail sample library carrying label information; performing feature extraction on each thumbnail sample in the remote sensing image thumbnail sample library; constructing a to-be-trained multilayer perceptron neural network model for binary classification; training a to-be-trained multilayer perceptron neural network model according to each thumbnail sample in the remote sensing image thumbnail sample library and the extracted features to obtain network parameters; according to the obtained network parameters, carrying out parameter updating on a to-be-trained multi-layer perceptron neural network model to obtain a multi-layer perceptron neural network model; and performing color evaluation on the to-be-tested remote sensing image according to the multi-layer perceptron neural network model.According to the invention, automatic detection and recognition of the remote sensing image are realized, and a prediction result about whether the color is normal is given.

Description

technical field [0001] The invention belongs to the technical field of visible light remote sensing images, and in particular relates to a remote sensing image color evaluation method and system based on a multilayer perceptron. Background technique [0002] Remote sensing is remote sensing, which generally refers to the non-contact and long-distance detection of the electromagnetic wave radiation and reflection characteristics of objects by sensors, and through analysis, reveals the comprehensive detection technology of the characteristic properties and changes of objects. Optical remote sensing is a kind of remote sensing, and its products are generally multi-band remote sensing images. [0003] At present, my country has launched many high-resolution optical satellites, dozens of them are in orbit, and the daily production tasks of remote sensing images are relatively heavy. In the image production process, due to various reasons such as abnormal sensor, abnormal data tr...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/90G06K9/46G06K9/62
CPCG06T7/0002G06T7/90G06T2207/10032G06T2207/20081G06T2207/20084G06T2207/30168G06V10/56G06F18/24Y02P90/30
Inventor 王海波尤江彬徐文喻文勇王巍霖李晓进
Owner CHINA SURVEY SURVEYING & MAPPING TECH