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

A cable force measurement method based on edge recognition in computer vision

A computer vision and edge recognition technology, applied in the directions of calculation, measurement force, measurement device, etc., can solve the problems of matching failure, sensitive to light conditions, unable to achieve long-term stable monitoring, etc., and achieve the effect of saving test costs and test time.

Active Publication Date: 2020-10-02
SOUTHEAST UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, the correlation-based template matching method needs to select a rectangular area in the video image as the tracking target. The target area may contain background objects such as clouds and branches that are inconsistent with the vibration of the cable itself, resulting in matching failure or measurement error; based on The optical flow estimation method of the gradient field, although it has been verified in some small-span and long-span bridge applications, is very sensitive to lighting conditions and cannot achieve long-term stable monitoring

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
  • A cable force measurement method based on edge recognition in computer vision
  • A cable force measurement method based on edge recognition in computer vision
  • A cable force measurement method based on edge recognition in computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0027] The specific implementation of the present invention will be described below through a case of a pedestrian cable-stayed bridge under environmental excitation in combination with the technical solution.

[0028] S1: Set up a camera at a suitable location to collect video, and ensure that the cable components to be tested in the structure are all within the field of view of the camera; the camera used is a GoPro Hero 4, and the initial video frame intercepted is shown in figure 2 ;

[0029] S2: Select multiple parts of the cable to be tracked in the initial frame of the video as the target area, such as figure 2 The two longest cables C1 and C2 on one side of the middle bridge; use the Sobel operator to preliminarily determine the possible edge points of the cables, and the coordinate accuracy of the obtained edge points is at the pixel level; use Zernike moments to correct the coordinates of the edge points of the cables, and the obtained accuracy is the sub-pixel le...

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

PropertyMeasurementUnit
lengthaaaaaaaaaa
lengthaaaaaaaaaa
Login to View More

Abstract

The invention discloses a cable force measurement method based on edge recognition in computer vision, and belongs to the technical field of structure health monitoring. According to the method, a structure does not need to be reached, no sensor device needs to be mounted on cables, normal operation of the structure cannot be disturbed, synchronous non-contact measurement of multi-cable force is realized, and test costs and time are saved; and an edge recognition method combining a Sobel operator and a Zernike moment is utilized, vibration time history of the structure cables can be accuratelymeasured, and the vibration characteristics and the cable force of multiple cable members in the structure can be quickly and simultaneously measured. The method of the invention is not sensitive toenvironmental conditions of illumination changes, cable background changes and the like, and can be used for long-term monitoring.

Description

technical field [0001] The invention relates to a non-contact measurement technology for cable vibration characteristics and cable force of a cable-stayed bridge, and belongs to the technical field of structural health monitoring. Specifically, a non-contact measurement method for cable vibration characteristics and cable forces of cable-stayed bridges based on edge recognition in computer vision is provided, which can quickly and synchronously measure the vibration characteristics and real-time cable forces of multiple cable components in the structure. Background technique [0002] Stay cables are important structural components in cable-stayed bridge structures. Most of the self-weight and running live loads on the bridge deck, such as vehicles and pedestrian loads, are transmitted to the tower columns through the cables, and the cable forces directly affect the distribution of internal forces that control the entire bridge deck system. Therefore, the cable force is a ke...

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): G01L1/10G06T7/00G06T7/13
CPCG01L1/103G06T7/0004G06T7/13G06T2207/10016
Inventor 徐燕郑宝锋
Owner SOUTHEAST UNIV
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