Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

An Efficient and Fast Extraction Algorithm and System of Subway Crack Trunk Based on Computational Geometry

A computationally geometric and efficient technology, applied in the field of rail transit, which can solve the problem of inaccurate extraction of crack trunk areas

Inactive Publication Date: 2017-03-15
BEIJING JIAOTONG UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to overcome the shortcomings of inaccurate extraction of the fracture trunk region in the prior art, the present invention identifies connected bifurcation and interweaving fractures by referring to the relevant knowledge of computational geometry, and further uses this algorithm to accurately extract the fracture trunk part of the bifurcation and interweaving region, in order to To ensure the accuracy of crack identification, and to provide more important and detailed information for repairing cracks after the construction

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
  • An Efficient and Fast Extraction Algorithm and System of Subway Crack Trunk Based on Computational Geometry
  • An Efficient and Fast Extraction Algorithm and System of Subway Crack Trunk Based on Computational Geometry
  • An Efficient and Fast Extraction Algorithm and System of Subway Crack Trunk Based on Computational Geometry

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0066] Example: such as Figure 1 to Figure 8 As shown, the core algorithm process we propose is specifically divided into three modules: the algorithm process for machine identification of connected fractures, the algorithm process for constructing convex polygons in fracture regions, and the algorithm process for identifying fracture backbones with rectangular boxes.

[0067] First, the first module, the algorithm flow of machine identification of connected cracks, is introduced in detail. We first define an empty waiting queue C n , and an empty storage space C xy . Step 1: Take a black pixel point C b1 As a starting point for crack identification, the C b1 Add to waiting queue C n in the C b1 Coordinates are stored in C xy middle. The second step: the C b1 mark as detected crack pixels, and then search with C b1 All the adjacent black pixels, put the unvisited black pixels C b2 , C b3 ,...,C bn Put them in the waiting queue C in turn n and store the respectiv...

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 rail transit, and particularly relates to an efficient and fast metro crack trunk extraction algorithm and system based on computation geometry. According to the efficient and fast metro crack trunk extraction algorithm and system based on the computation geometry, a machine identifies connected cracks, and an empty queue Cn to be visited and an empty storage space Cxy are defined firstly; a convex polygon is constructed at the crack area through calculation according to horizontal coordinates and vertical coordinates of all crack pixel points obtained from the last step through calculation, wherein the convex polygon is formed by a crack pixel point set; a crack trunk is marked by a rectangular frame, the truck area of the cracks is identified based on the convex polygon obtained from the first two steps, and corresponding areas are marked by matching rectangular frames. The efficient and fast metro crack trunk extraction algorithm and system based on the computation geometry have the advantages that the advantages of automatic detection and the advantages of manual detection are combined, the manual workload is reduced greatly, and accuracy is guaranteed. The efficient and fast metro crack trunk extraction algorithm and system based on the computation geometry are worth using.

Description

technical field [0001] The invention belongs to the technical field of rail transit, and in particular relates to an efficient and fast extraction algorithm and system for the trunk of subway cracks based on computational geometry. Background technique [0002] In recent years, with the rapid development of urban construction, the continuous expansion of urban scale and the rapid expansion of urban population, many cities have experienced traffic congestion problems to varying degrees. In order to effectively alleviate the problem of urban public transportation, everyone has turned their attention to the development of urban rail transit. Many subway lines have been put into operation in Beijing, Guangzhou, Nanjing, Shenzhen, Chongqing and other cities in China, and subways in Chengdu, Qingdao, Shenyang and other cities are also under construction. [0003] Urban rail transit is characterized by fast running speed, high traffic density, large passenger flow, and closed envi...

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): G06T7/00G06K9/46
Inventor 张振江刘云吴晓阳熊菲
Owner BEIJING 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
Eureka Blog
Learn More
PatSnap group products