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

A Convolutional Neural Network Based Multispectral Remote Sensing Image Dehazing Method

A convolutional neural network and multispectral image technology, applied in the field of remote sensing image processing

Active Publication Date: 2020-01-24
BEIHANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the fog occlusion problem existing in multi-spectral remote sensing images, the present invention proposes a dehazing method based on convolutional neural network

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 Convolutional Neural Network Based Multispectral Remote Sensing Image Dehazing Method
  • A Convolutional Neural Network Based Multispectral Remote Sensing Image Dehazing Method
  • A Convolutional Neural Network Based Multispectral Remote Sensing Image Dehazing Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] In order to better understand the technical solution of the present invention, the embodiments of the present invention will be further described below in conjunction with the accompanying drawings:

[0075] The flow chart of the present invention is as figure 1 shown. The computer configuration adopts: Intel Core i5-6600k processor, Nvidia GeForce GTX 1080 graphics processor, main frequency 3.5GHz, memory 16GB, operating system is ubuntu 16.04. The implementation of the dehazing method is based on the Caffe toolkit. The present invention is a multispectral image defogging method based on a convolutional neural network, specifically comprising the following steps:

[0076] Step 1: Multispectral image dehazing band selection

[0077] The invention adopts the multispectral remote sensing image data collected by the landsat8OLI sensor. The Landsat8OLI image includes 9 bands, among which the coastal band, visible light band (blue band, green band, red band), near-infrar...

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 relates to a multispectral remote sensing image dehazing method based on a convolutional neural network, which is characterized in that: the method includes the following steps: Step 1: Multispectral image dehazing band selection; Step 2: Establishing a dehazing model; Step 3 : Design a convolutional neural network; Step 4: Train the convolutional neural network; Step 5: Dehaze multispectral remote sensing images. The present invention directly learns the mapping relationship between foggy images and clear images through a convolutional neural network, and can achieve end-to-end defogging. The convolutional network uses a cascaded residual structure to learn the defogging model with reference and achieve gradual defogging. This method is not only easy to learn and train, but also can achieve higher-precision dehazing results by deepening the number of network layers.

Description

[0001] (1) Technical field: [0002] The invention relates to a multispectral remote sensing image defogging method based on a convolutional neural network, belonging to the technical field of remote sensing image processing. [0003] (two) background technology: [0004] Multispectral remote sensing images can not only provide rich ground object information, but also have spectral characteristics, which play a very important role in the fields of environment, monitoring, military, surveying and mapping. However, multi-spectral remote sensing images are often disturbed by fog, resulting in blurred objects in the image and loss of information in the region of interest, which not only seriously affects the interpretation of image data by human eyes, but also affects the automatic interpretation of remote sensing data . [0005] Dehazing research on remote sensing images can improve image quality, thus providing guarantee for subsequent remote sensing image processing and applica...

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): G06T5/00
CPCG06T2207/10036G06T2207/10032G06T2207/20081G06T5/73
Inventor 谢凤英秦曼君姜志国
Owner BEIHANG UNIV