Rail safety detection method based on first-order direction gradient operator

A directional gradient, detection method technology, applied in computing, image data processing, instruments, etc., can solve problems such as loss, prone to failure, detection system paralysis, etc., to avoid losses, reduce accidents, and avoid overall paralysis.

Pending Publication Date: 2019-09-27
黑龙江御林湾科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention solves the problem that the existing rail position detection system cannot perform all-weather and independent detection on the running trajectory of the train, and is prone to failure. When there is no stable network signal or in a harsh natural environment, a full set of detection can be caused The system is paralyzed, resulting in dangerous factors, serious problems that can lead to train accidents and irreparable losses, and a rail safety detection method based on the first-order directional gradient operator is proposed

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
  • Rail safety detection method based on first-order direction gradient operator

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0023] Specific implementation mode one: combine figure 1 Describe this embodiment, a kind of rail safety detection method based on the first-order directional gradient operator described in this embodiment, its specific algorithm process is as follows:

[0024] Step 1: Acquire the optical image I with the rails, trim and adjust it according to the deviation of the installation position, and first perform Gaussian filtering to remove noise;

[0025] Step 2: Use the pre-set three first-order directional gradient operators, f 1 , f 2 and f 3 Both convolve the acquired optical image containing railroad tracks to obtain the feature map f mp1 , f mp2 and f mp3 ;

[0026] Step 3: Flip the eigenvalues ​​in the obtained three feature maps f mn =f mp ×-1, get the reverse complementary feature map, f mn1 , f mn2 and f mn3 , and merge the feature maps to get the positive channel feature map

[0027] f p =f mp1 + f mp2 + f mp3 (1)

[0028] where f mp1 , f mp2 and f mp...

specific Embodiment approach 2

[0036] Specific implementation mode two: combination figure 1 Describe this embodiment, this embodiment is a further limitation of the position detection algorithm described in the first specific embodiment, a rail safety detection method based on a first-order directional gradient operator described in this embodiment, the described The method for obtaining the optical image with the rail in step 1 is to use a camera to take pictures of the environment near the rail.

specific Embodiment approach 3

[0037] Specific implementation mode three: combination figure 1 Describe this embodiment, this embodiment is a further limitation of the position detection algorithm described in the second specific embodiment, a rail safety detection method based on a first-order directional gradient operator described in this embodiment, the described In step 1, the camera is used to acquire the optical image. The camera gives priority to ensuring the shutter speed, and the obtained original image has certain noise. After the original image is obtained, the image is first denoised by Gaussian filtering to eliminate noise interference.

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 safety detection method based on a first-order direction gradient operator, and relates to the field of rail position detection algorithms. The invention discloses a rail position detection system. According to the method, the problems that the running track of the train cannot be detected in an all-weather and autonomous mode, faults occur easily, when no stable network signal exists or the train is in a severe natural environment, a whole set of detection system can be paralyzed, dangerous factors are contained, accidents of the train can be caused seriously, and irreparable losses are caused are solved. The image has a part which is not a rail but also conforms to the data distribution rule. Therefore, more false detection points exist on the three edge feature maps. By filtering the fused feature map and using an isolated point removal method, a morphological processing method and the like to remove the detection result except the rail target to the maximum extent. A first derivative is calculated for the edge of the contour detection result, and a judgment is made whether the contour detection result contains curve information or not according to the first derivative result. The method is suitable for detecting the track position.

Description

technical field [0001] The invention relates to the field of rail position detection algorithms, in particular to a rail safety detection method based on a first-order directional gradient operator. Background technique [0002] With the rapid development of my country's railway construction, the speed of trains continues to increase, and the requirements for driving safety continue to increase. The existing train control and ATP systems use signal blocking and proximity response methods to ensure driving safety, but the train control system can only Guarantee the cooperative goal of monitoring the moving train, and cannot give early warning for the occurrence of sudden, unpredictable and other non-cooperative target violation events. In particular, it needs to be explained that the ground signal system of the public service machinery vehicles used for railway construction operations is usually in a closed or invalid state under construction conditions, and cannot play the ro...

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): G06T7/00G06T7/13G06T5/20G06T5/00
CPCG06T7/0008G06T5/002G06T5/20G06T7/13G06T2207/20024G06T2207/30252
Inventor 段智文郑晓凯
Owner 黑龙江御林湾科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap