Supercharge Your Innovation With Domain-Expert AI Agents!

A rail foreign matter detection method based on low-rank matrix factorization

A low-rank matrix, foreign object detection technology, applied in the field of computer vision, can solve problems such as train safety hazards, throwing out of the window, etc., and achieve good robustness.

Active Publication Date: 2019-06-25
BEIHANG UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to the relevant regulations on the safe running of trains in our country, in the railway line safety protection zone and its adjacent areas, there must be no foreign objects that endanger the normal running of the train within the railway limits stipulated by the state, so as not to cause the driver to see the foreign objects at a relatively short distance. Braking treatment, but the braking is not timely, the braking distance is too long and the collision with foreign objects causes property damage and safety accidents
[0003] When inspectors enter the railroad tracks without trains for maintenance, due to the nature of their work, they may leave their helmets, work wrenches and other items between the railroad tracks, or train passengers throw garbage and other foreign objects out of the window, causing train accidents. Security risks

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 rail foreign matter detection method based on low-rank matrix factorization
  • A rail foreign matter detection method based on low-rank matrix factorization
  • A rail foreign matter detection method based on low-rank matrix factorization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0041] In this embodiment, a representative rail foreign object image taken based on a space-based platform is taken as an example, such as figure 2 shown. Line detection is performed on the source image, and the result is as follows image 3 As shown in , and filter the calculated straight line to extract the railway track area of ​​interest.

[0042]Extract the pixel vector of the region of interest and perform clustering processing, divide it into two subsets of sleepers and stones, and perform low-rank matrix decomposition on the matrix formed by the two subsets to obtain the low-rank matrix D, and make the difference between the original matrix and the low-rank matrix to obtain The foreground matrix E and the foreground matrix are filtered and thresholded to determine the position of the foreign object and marked in the source image. The experimental results are as follows Figure 4 shown.

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 rail foreign matter detection method based on low-rank matrix factorization, and belongs to the technical field of computer vision. The implementation process comprises the following steps: 1) carrying out straight line detection on an unmanned aerial vehicle aerial photography railway image, screening a straight line group, finding a rail edge straight line, and determining an area needing to be detected and processed; 2) extracting a pixel vector from the rail area and clustering the pixel vector, wherein the pixel vector can be divided into two subsets of sleepersand stones; 3) performing low-rank matrix decomposition on a matrix formed by the two subsets, and subtracting the obtained low-rank matrix with background information to obtain a foreground matrix; According to the method, the rail foreign matter is detected through an algorithm based on low-rank matrix decomposition, the foreign matter is quickly confirmed through images transmitted back in realtime through space-based monitoring, and the method can be used for the fields of railway safety monitoring and the like.

Description

technical field [0001] The invention belongs to the technical field of computer vision, relates to digital image processing technology and target detection technology, and specifically refers to a method for detecting foreign objects on rails based on low-rank matrix decomposition. Background technique [0002] Rail foreign object detection refers to the measures to check the rail area for foreign objects in order to ensure the safety of trains. According to the relevant regulations on the safe running of trains in our country, in the railway line safety protection zone and its adjacent areas, there must be no foreign objects that endanger the normal running of the train within the railway limits stipulated by the state, so as not to cause the driver to see the foreign objects at a relatively short distance. Braking treatment, but the braking is not timely, the braking distance is too long and the collision with foreign objects causes property damage and safety accidents. ...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/46G06K9/62
Inventor 罗晓燕曹先彬张可昕胡宇韬王帅
Owner BEIHANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More