Defect detection method and device for facilities on both sides of road

A defect detection and facility technology, applied in image analysis, image enhancement, instruments, etc., can solve problems such as poor performance and reduce highway traffic efficiency, and achieve the effects of improving detection efficiency, realizing automatic detection, and ensuring traffic efficiency

Active Publication Date: 2022-07-26
KEY & CORE TECH INNOVATION INST OF THE GREATER BAY AREA
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing road detection is mainly based on manual detection, which does not perform well in practical applications
And when manually inspecting facilities on both sides of the road such as guardrails and sunshades, it is necessary to close some sections of the expressway, which greatly reduces the traffic efficiency of the expressway.

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
  • Defect detection method and device for facilities on both sides of road
  • Defect detection method and device for facilities on both sides of road
  • Defect detection method and device for facilities on both sides of road

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] like figure 1 and figure 2 As shown, the present invention discloses a defect detection method for facilities on both sides of a road, including:

[0044] In step S1, images of facilities on both sides of the road are acquired, and the images are input into the trained image segmentation network to obtain a guardrail mask and a visor mask;

[0045] Step S2, according to the obtained guardrail mask and shading plate mask, determine whether the guardrail and the shading plate have defects, specifically:

[0046] Traverse the guardrail mask along the column direction and collect candidate edge points, select the interior points of the guardrail boundary by random sampling consensus algorithm, and fit the boundary line by the least square method; judge whether there is existence according to the distance from all candidate edge points to the fitting boundary Defect, the candidate edge point is the pixel point of the mask edge;

[0047] Perform edge detection on the shad...

Embodiment 2

[0071] refer to Image 6 , the present invention also discloses a defect detection device for facilities on both sides of the road, comprising: an image acquisition module 101, an image segmentation module 102, a defect analysis module 103 and a result output module 104;

[0072] The image acquisition module 101 is used to acquire images of facilities on both sides of the road;

[0073] The image segmentation module 102 is used to input the acquired image into the trained image segmentation network to obtain a guardrail mask and a visor mask;

[0074] The defect analysis module 103 is used for traversing and searching the guardrail mask along the column direction and collecting candidate edge points, selecting the inner points of the guardrail boundary through the random sampling consensus algorithm and fitting the boundary line through the least square method; according to all the candidate edge points The distance to the fitting boundary is used to judge whether there is a ...

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 belongs to the technical field of road facility defect detection, and discloses a defect detection method and device for facilities on both sides of a road, comprising: acquiring images of facilities on both sides of the road, inputting the images into a trained image segmentation network, and obtaining guardrail masks film and shading plate mask; according to the obtained guardrail mask and shading plate mask, determine whether the guardrail and the shading plate have defects, collect candidate edge points for the guardrail mask, and obtain the fitting boundary line, according to the candidate edge point to the fitting boundary Determine whether there is a defect; perform edge detection on the visor mask to obtain edge contour information, obtain the minimum circumscribed rectangle from the edge contour information, and judge the tilt defect of the visor according to the long side direction of the minimum circumscribed rectangle; according to the center distance of the visor Determining missing defects. The invention detects the damage information of the highway guardrail and the shading plate through the image segmentation network and the visual algorithm, realizes the automatic detection, improves the detection efficiency and guarantees the traffic efficiency of the road.

Description

technical field [0001] The invention relates to the technical field of road facility defect detection, in particular to a defect detection method and device for facilities on both sides of a road. Background technique [0002] With the continuous improvement of the road network and the increasing construction of expressways, the inspection, maintenance and management of roads has become an important task in the field of road construction in China. The existing road detection is mainly based on manual detection, which does not perform well in practical applications. In addition, when manually inspecting the facilities on both sides of the road, such as guardrails and visors, it is necessary to close some sections of the expressway, which greatly reduces the traffic efficiency of the expressway. SUMMARY OF THE INVENTION [0003] The purpose of the present invention is to provide a defect detection method and device for facilities on both sides of the road, which can detect ...

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): G06V10/26G06V10/44G06V10/764G06V10/80G06V10/82G06K9/62G06N3/04G06T7/00
CPCG06T7/0006G06T2207/20084G06T2207/30108G06N3/045G06F18/2431G06F18/253
Inventor 黄智刚吴清泉李然崔开金杨军红刘浩王家赞
Owner KEY & CORE TECH INNOVATION INST OF THE GREATER BAY AREA
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