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

Extraction method of snow cover in alpine mountainous area using high-resolution remote sensing images

A remote sensing image, high-resolution technology, applied in the field of remote sensing, can solve problems such as the phenomenon of salt and pepper, and achieve the effect of eliminating the phenomenon of salt and pepper, improving accuracy, and strong applicability

Active Publication Date: 2021-06-01
CCCC SECOND HIGHWAY CONSULTANTS CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Furthermore, considering that using traditional pixel-based methods to extract snow areas on high-resolution images is prone to salt and pepper phenomena, and high-resolution images contain rich information such as texture, geometry, and spatial relationships, it is urgent to provide a high-resolution image of alpine mountain area. Snow extraction method to effectively eliminate the salt and pepper phenomenon in the snow extraction results, so as to obtain accurate and continuous snow areas

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
  • Extraction method of snow cover in alpine mountainous area using high-resolution remote sensing images
  • Extraction method of snow cover in alpine mountainous area using high-resolution remote sensing images
  • Extraction method of snow cover in alpine mountainous area using high-resolution remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0041] In view of the lack of short-wave infrared bands required for calculating the NDSI index in high-resolution remote sensing images, in order to eliminate the salt and pepper phenomenon in the snow extraction results, Ben Fangming’s snow extraction method using high-resolution remote sensing images in alpine mountainous areas uses an object-oriented combination of depth Deep Belief Network (DBN) and fully connected Conditional Random Fields (Conditional Random Fields, CRF) high-resolution image snow extraction method in alpine mountainous areas to obtain accurate and continuous snow extraction results, such as figure 1 , including the following steps:

[0042] Step S1), optimal scale fractal network evolution segmentation of high-resolution remote sensing images. For the high-resolution remote sensing image to be extracted snow ...

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 the field of remote sensing technology, and discloses a method for extracting snow in alpine mountainous areas by using high-resolution remote sensing images, comprising the following steps: Step S1), using an optimal scale fractal network evolution segmentation algorithm to perform extraction on the high-resolution remote sensing images. Segmentation to obtain a high-resolution image object; step S2), using the high-resolution image object to construct a feature map of a high-dimensional image object; step S3), constructing a deep confidence network model; step S4), constructing a fully connected conditional random field model; step S5), output the snow extraction result. The method of the invention has stronger applicability to different sensor data, and is more suitable for snow extraction of high-resolution remote sensing images; the object-oriented idea is used to combine the deep belief network with the fully connected conditional random field model, and the high-resolution The spectrum, shape, texture and spatial relationship information of the image can eliminate the salt and pepper phenomenon in the snow extraction results and improve the accuracy of snow extraction.

Description

technical field [0001] The invention relates to the technical field of remote sensing, in particular to a method for extracting snow in alpine mountainous areas by using high-resolution remote sensing images. Background technique [0002] Restricted by factors such as topography, geology and environmental protection, it is difficult to quantitatively obtain snow cover data in alpine mountainous areas by traditional methods of geography and meteorology. With the rapid development of remote sensing technology, new technology means are provided for snow cover monitoring. [0003] Currently MODIS data and its snow cover products are widely used in snow cover monitoring. "Study on the Method of Identifying Snow Cover in Qilian Mountains Using MODIS Data" (Wang Xing, Zhang Qiang, Guo Niobium, etc., "Arid Meteorology", Volume 25, No. 2, June 2007), reveals the use of MODIS images of The snow cover area was extracted using the Normalized Difference Snow Index (NDSI) index. "Study...

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): G06K9/00G06K9/34G06N3/04
Inventor 徐乔余绍淮张霄余飞罗博仁刘德强
Owner CCCC SECOND HIGHWAY CONSULTANTS CO LTD
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