Landslide terrain detection method based on deep neural network

A deep neural network and detection method technology, applied in the field of geological disaster prediction, can solve time-consuming and labor-intensive problems, and achieve the effect of improving imperfect defects and perfect learning effect

Pending Publication Date: 2020-06-02
中国地质环境监测院
View PDF3 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main problem to be solved by the present invention is to overcome the great dependence of the prior art on labor, reduce the influence of external equipment errors, get rid of the time-consuming and laborious dilemma of landslide survey, provide a landslide terrain detection method based on deep neural network, and use advanced artificial Intelligent technology, using accurate satellite remote sensing data, combined with expert knowledge in the field, the result accuracy rate is high, while ensuring the accuracy of segmentation results, it greatly reduces the investment of human, material and financial resources

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
  • Landslide terrain detection method based on deep neural network
  • Landslide terrain detection method based on deep neural network
  • Landslide terrain detection method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The specific implementation scheme of a landslide terrain detection method based on a deep neural network involved in the present invention will be described in detail below in conjunction with the accompanying drawings and implementation.

[0041]

[0042] In this embodiment, the landslide terrain detection method based on the deep neural network is described by taking the landslide remote sensing image and the digital elevation model as examples.

[0043] Such as figure 1 As shown, a kind of landslide terrain detection method based on deep neural network provided by this embodiment is specifically implemented according to the following steps:

[0044] Step 1, get data:

[0045] Using the open source satellite image download platform, set a unified tile level, download landslide remote sensing images and digital elevation models; use the mask labeling function on the platform to mark the specific range of the landslide, download and obtain the latitude and longitude...

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 provides a landslide terrain detection method based on a deep neural network, and the method comprises the steps: collecting a landslide remote sensing image and digital elevation modeldata, obtaining specific range coordinates of a landslide, and generating a landslide marking map; carrying out data preprocessing on the landslide remote sensing image, the digital elevation model and the landslide labeling graph; and constructing a geologic feature extraction model taking DeepLab V3 + as a framework, and extracting rich geologic features from the remote sensing terrain data set.According to the method, landslide remote sensing image features and digital elevation model features are fused, landslide domain knowledge is combined, geological feature parameters are loaded, a terrain segmentation model is realized on the basis of the DeepLab V3 + architecture, landslide terrain segmentation of pixel-level granularity is completed, and the purpose of landslide terrain detection is achieved.

Description

technical field [0001] The invention belongs to the technical field of geological disaster prediction, and in particular relates to a landslide terrain detection method based on a deep neural network of remote sensing images and digital elevation model data. Background technique [0002] "Hidden dangers of geological disasters" are mostly distributed in the vast western region, where transportation, communication, and electricity are extremely inconvenient, and manual verification is very difficult. On average, landslides cause more than 1,000 casualties, more than 900,000 affected people, and direct economic losses of 2-6 billion yuan each year. How to carry out long-term effective monitoring and timely early warning of hidden dangers of geological disasters, especially landslides and other geological disasters that are extremely harmful, to protect people's lives and reduce property losses of the people, is the key to geological monitoring personnel and related geological ...

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): G06T17/05
CPCG06T17/05
Inventor 黄坚朱赛楠贾雪婷杜博文殷跃平
Owner 中国地质环境监测院
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