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

Automatic river levee collapse monitoring method

An automatic monitoring and embankment technology, applied in the field of video image processing technology and deep learning algorithm, can solve the problems of collapse detection lag

Pending Publication Date: 2020-10-30
郑州信大先进技术研究院
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies in the prior art, thereby providing an automatic monitoring method for river embankment collapse, solving the problem of collapse detection hysteresis, and solving the problem of human resources at the same time

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
  • Automatic river levee collapse monitoring method
  • Automatic river levee collapse monitoring method
  • Automatic river levee collapse monitoring method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] The invention provides an automatic monitoring method for river embankment collapse, such as figure 1 As shown, it specifically includes the following steps:

[0035] Step 1, obtain the monitoring video of multiple monitoring devices in real time, use the temporal convolution dynamic change monitoring video frame detection model to initially screen the monitoring video, and obtain the monitoring video clips that may have river embankment collapse;

[0036] Step 2, using the moving object detection model to perform moving object detection on the acquired surveillance video clips, and obtain an image of the moving object area;

[0037] Use the river embankment detection semantic segmentation model to perform semantic segmentation detection on the acquired surveillance video clips, and extract the image of the river embankment area;

[0038] Step 3, performing image difference between the extracted embankment area and the acquired moving target area, to obtain an image of...

Embodiment 2

[0073] This embodiment provides an automatic monitoring system for embankment collapse, such as image 3 As shown, it includes a multi-channel monitoring device, an edge computing device connected to the multi-channel monitoring device, and a cloud monitoring platform connected to the edge computing device;

[0074] The multi-channel monitoring equipment is arranged on the embankment to obtain the monitoring video of the embankment;

[0075] The edge meter device is provided with a timing convolution dynamic change monitoring video frame detection module, and the timing convolution dynamic change monitoring video frame detection module has a built-in timing convolution dynamic change monitoring video frame detection model for monitoring the monitoring video. Preliminary screening to obtain surveillance video clips that may have collapsed river embankments;

[0076] The cloud monitoring platform is provided with a moving object detection module, a river embankment detection se...

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 an automatic river levee collapse monitoring method. The method comprises the following steps: 1, acquiring monitoring videos of multiple paths of monitoring equipment in real time, and performing preliminary screening on the monitoring videos by using a time sequence convolution dynamic change monitoring video frame detection model to acquire monitoring video clips possiblyhaving river levee collapse; 2, performing moving target detection on the obtained monitoring video clip by using a moving target detection model to obtain a moving target region image; performing semantic segmentation detection on the obtained monitoring video clip by using a river levee detection semantic segmentation model, and extracting a river levee region image; 3, performing image subtraction on the extracted river levee area and the obtained moving target area to obtain a river levee area image not containing the moving target; 4, creating a Gaussian filter, performing gray processing and Gaussian filtering on the obtained river levee area image without the moving target, and establishing a background template; and 5, finally, determining the collapse position and area by utilizing a frame difference method.

Description

technical field [0001] The invention relates to the field of video image processing technology and deep learning algorithm, in particular to an automatic monitoring method for river embankment collapse. Background technique [0002] The collapse of the river embankment refers to the fact that the river embankment is affected by factors such as river water immersion, wind and wave impact, water erosion, and alternation of dryness and wetness, which intensifies the weathering of the river embankment soil, reduces the erosion resistance, and is caused by the change of groundwater dynamic pressure caused by the fluctuation of the river water level. Unfavorable geological phenomena of reconstruction deformation such as erosion (abrasion), collapse (collapse), displacement, etc. of river embankments. The embankment collapse not only leads to the instability of the main channel of the river, but also destroys the embankment, threatens the embankment, and even breaks the embankment,...

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): G06T7/215G06T7/246G06T7/90G06T5/00
CPCG06T7/215G06T7/248G06T7/90G06T2207/10016G06T2207/20024G06T2207/20081G06T2207/20084G06T2207/30184G06T5/90
Inventor 徐妙语王坤高毫林叶森张洁闫红刚
Owner 郑州信大先进技术研究院
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