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

Foreign matter inspection system and method for rail transit

A foreign object inspection and rail transit technology, applied in the field of computer vision, can solve problems such as increased erection and maintenance costs, difficulty in classifying foreign objects and targeted processing, complex scenes, etc., so as to save erection and maintenance costs, and avoid processing queues. Chaos, the effect of improving processing efficiency

Inactive Publication Date: 2019-08-02
复钧智能科技(苏州)有限公司
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The protection of the railway includes hardware protection and software protection: the hardware protection mainly adopts double-cable protection net to isolate the intrusion of wild animals and abnormal pedestrians, etc., but it has no protective effect on pedestrians and railway construction personnel appearing at railway crossings; Camera shooting video is mainly combined with manual monitoring. This method is a great test for the energy of security personnel. Railway security needs more intelligent solutions.
[0004] Therefore, the railway systems in some countries have adopted the method of adding additional sensors such as infrared rays and radars to judge foreign objects. This method increases the cost of erection and maintenance, and also loses the characteristics of foreign objects. It is difficult to classify foreign objects and make targeted Relying on the camera for intelligent video surveillance is of great significance for railway security
[0005] Existing video-based railway foreign object detection mostly uses traditional methods such as inter-frame difference and grayscale transformation. However, since railways mostly operate around the clock, the scene is complex, and the lighting conditions vary greatly, the recognition accuracy of these railway foreign object detection methods is low. There are many false positives and missed negatives, and the effect is not satisfactory

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
  • Foreign matter inspection system and method for rail transit
  • Foreign matter inspection system and method for rail transit
  • Foreign matter inspection system and method for rail transit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In recent years, with the rapid development of machine learning, especially deep learning technology, breakthroughs have been made in computer vision, natural language processing, and speech recognition. It has also been greatly improved, achieving an effect far exceeding that of the traditional method, and performing well in the public data set. Therefore, the present invention aims at the scene of rail transit and uses the advantages of deep learning methods to improve the detection of foreign objects in rail transit. The performance in the task, so as to solve the detection problem of foreign object intrusion in the railway security scene.

[0023] In order to make the technical means, creative features, goals and effects of the present invention easy to understand, the rail transit-oriented foreign object inspection system and method of the present invention will be described in detail below in conjunction with the embodiments and accompanying drawings.

[0024]

...

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 provides a foreign matter inspection system for rail transit. The method is used for detecting a border crossing event on a railway and judging whether foreign matters cross the border or not. The system is characterized in that the system comprises at least one induction camera device which is used for shooting the position where the border-crossing event occurs on the railway to obtain a border-crossing video image when the border-crossing event occurs is inducted, and a plurality of clearer video frames in the border-crossing video image are used as a group of event video frames to be sent to an image processing device. The system also comprises an image processing apparatus, wherein the image processing module is used for performing image processing on an event video frame to obtain corresponding border crossing event information and sending the border crossing event information to security personnel responsible for railway maintenance; the image processing apparatusincludes an image-side communication unit, an image-side control unit, a video frame processing unit, a video frame temporary storage unit, an image analysis and generation unit, a foreign matter determination unit, and an event information acquisition unit.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a foreign object detection system and method in a railway scene. Background technique [0002] With the rapid development of my country's rail transit industry, the mileage of railways is increasing, and the transportation capacity has been further improved. However, due to the many outdoor scenes in the operation of railways, foreign objects intrude into the railway boundary from time to time, threatening the railway safe operation. Therefore, it is necessary to protect the railway during the operation of the railway so as to ensure the safety on the railway. [0003] The protection of the railway includes hardware protection and software protection: the hardware protection mainly adopts double-cable protection net to isolate the intrusion of wild animals and abnormal pedestrians, etc., but it has no protective effect on pedestrians and railway construction personnel a...

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
IPC IPC(8): G08B13/196
CPCG08B13/19602G08B13/19647
Inventor 吕铄冯瑞
Owner 复钧智能科技(苏州)有限公司
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