Partitioned landslide detection system and method based on cascaded deep convolutional neural network

A deep convolution and neural network technology, applied in the field of landslide recognition, can solve the problem of difficult landslide image recognition, and achieve the effect of saving manpower, improving recognition rate, improving efficiency and accuracy rate

Active Publication Date: 2020-11-06
XI AN JIAOTONG UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a landslide detection system and method based on a cascaded deep convolutional neural network, which combines artificial intelligence technology with landslide disaster identification, utilizes the regional commonality of landslide disasters, and generates different detection models for different regions; Aiming at the difficult problem of landslide image recognition, a deep convolutional neural network with cascading characteristics is constructed, which not only realizes intelligent interpretation of landslide disasters, but also improves the efficiency and accuracy of landslide disaster recognition

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
  • Partitioned landslide detection system and method based on cascaded deep convolutional neural network
  • Partitioned landslide detection system and method based on cascaded deep convolutional neural network
  • Partitioned landslide detection system and method based on cascaded deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0052] This specific example is only an explanation of the present invention, and it is not a limitation of the present invention. Those skilled in the art can make modifications without creative contribution to this embodiment according to needs after reading this description, but as long as the claims of the present invention are protected by patent law.

[0053] according to figure 1 The shown partitioned landslide detection system based on cascaded deep convolutional neural network includes an image acquisition module for acquiring images, a database module for storing images, and a landslide detection model preparation module for performing detection model pre-generation related operations , and a landslide detection model generation module for generating multiple regional detection models;

[0054] The partition landslide detection method based on the...

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 partitioned landslide detection system and method based on a cascaded deep convolutional neural network. According to the partitioned landslide detection method, an image collection module used for acquiring landslide disaster images is included; the database module is used for constructing and storing landslide disaster image samples with different attributes and different regions; the landslide detection model preparation module is used for preprocessing the image, constructing an image pyramid and determining a corresponding region coefficient of each region; and the landslide detection model generation module is used for generating landslide disaster recognition detection models corresponding to different regions, and comprises a visual DLNet detector generation optimization module and a multi-layer cascaded deep convolutional neural network detection model module. According to the method, an artificial intelligence technology is combined with landslide disaster recognition, and a detection model is generated for different regions by using the regional universality of landslide disasters; and a deep convolutional neural network with cascade characteristics is constructed, so that intelligent interpretation of landslide disasters is realized, and the landslide disaster recognition accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of landslide identification, and in particular relates to a partitioned landslide detection system and method based on a cascaded deep convolutional neural network. Background technique [0002] my country has a vast territory, complex terrain and geological conditions, about 70% of the area is mountainous, and geological disasters occur frequently. As a common type of geological disasters, the proportion of landslide disasters is increasing year by year. According to the National Geological Disaster Notification, the number of landslides in my country exceeds a thousand every year, which poses a huge threat to the safety of people's lives and property. In recent years, many hidden dangers of landslide disasters have been detected across the country, and a large number of land areas have been affected by landslide disasters. The monitoring and prevention of landslide disasters is particularly important, and...

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
IPC IPC(8): G06K9/00G06K9/40G06N3/04G06N3/08
CPCG06N3/084G06V20/13G06V10/30G06N3/045
Inventor 许领雷捷扬苑超张静逸
Owner XI AN JIAOTONG UNIV
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