Offshore haze remote sensing identification method and system under clear sky condition

A remote sensing recognition and haze technology, applied in scene recognition, neural learning methods, character and pattern recognition, etc., can solve the problems of high difficulty of haze monitoring, time-consuming and laborious, and limited observation space.

Pending Publication Date: 2020-08-14
中国人民解放军61540部队
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, traditional ground observation methods are time-consuming and laborious, and the observation space is limited. It is more difficult to monitor the haze over the ocean.

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
  • Offshore haze remote sensing identification method and system under clear sky condition
  • Offshore haze remote sensing identification method and system under clear sky condition
  • Offshore haze remote sensing identification method and system under clear sky condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Such as figure 1 As shown, this embodiment provides a remote sensing identification method for sea haze under clear sky conditions, including the following steps.

[0044] Step 101: Obtain satellite remote sensing data over the ocean corresponding to the monitoring area under clear sky conditions.

[0045] Among them, the satellite remote sensing data over the ocean used in this embodiment comes from MODIS L1A data on the ocean color data website (https: / / oceancolor.gsfc.nasa.gov / ).

[0046] Step 102: Extract the spectral feature value of the pixel according to the satellite remote sensing data over the ocean.

[0047] In this embodiment, the spectral characteristic value of the pixel is the remote sensing reflectance R after de-Rayleigh correction rc , Referred to as Rayleigh remote sensing reflectivity R rc .

[0048] Due to the serious situation of cloud masks on satellite remote sensing data over the ocean, the remote sensing reflectivity of MODIS L1A data is R rs There are m...

Embodiment 2

[0073] In order to achieve the above objective, this embodiment also provides a remote sensing recognition system for sea haze under clear sky conditions, such as Figure 8 Shown, including:

[0074] The satellite remote sensing data acquisition module 201 over the ocean is used to acquire satellite remote sensing data over the ocean corresponding to the monitoring area under clear sky conditions.

[0075] The pixel spectral feature value extraction module 202 is configured to extract the pixel spectral feature value according to the satellite remote sensing data over the ocean.

[0076] The haze distribution determination module 203 over the ocean is used to determine the haze distribution over the ocean corresponding to the monitored area according to the spectral feature values ​​of the pixels and the trained neural network haze remote sensing recognition model; wherein the trained neural network The network haze remote sensing recognition model is obtained by training the MLP neu...

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 offshore haze remote sensing recognition method and system under a clear sky condition, and relates to the field of ocean remote sensing data and application, and the methodcomprises the steps: obtaining ocean overhead satellite remote sensing data corresponding to a monitoring area under the clear sky condition; extracting a pixel spectral characteristic value according to the satellite remote sensing data above the sea; and according to the pixel spectral characteristic value and a trained neural network haze remote sensing identification model, determining the haze distribution above the sea corresponding to the monitoring area. The trained neural network haze remote sensing recognition model is obtained by training an MLP neural network model according to sample data; wherein the sample data comprises types of pixel regions and pixel spectral characteristic values corresponding to the pixel regions; the types include clean water, turbid water and haze. According to the invention, satellite remote sensing data over the sea are combined with a neural network machine learning algorithm, so that the purpose of accurately and effectively monitoring the haze distribution over the sea is achieved.

Description

Technical field [0001] The invention relates to the field of ocean remote sensing data and application, in particular to a remote sensing identification method and system for maritime haze under clear sky conditions. Background technique [0002] In recent years, the occurrence of smog has become more frequent and the range affected by smog has become wider. The smog has caused destructive effects on human travel, health, and the ecological environment. It has caused government departments, The widespread attention of scientists and society has become a hot topic. [0003] As an important part of the global climate system, the ocean has an important impact on global climate change. my country borders the Pacific Ocean and is a large maritime country. At the same time, the eastern coastal area is where my country's economic and social development is relatively fast, and it is also my country's main economic contribution area. About 60% of the country's population is located in the ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V20/13G06N3/045G06F18/214
Inventor 沈晓晶姜祝辉程锐陈建刘娟金宝刚
Owner 中国人民解放军61540部队
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products