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

A video-based automatic detection method for falling objects from railway freight cars

A railway freight car, automatic detection technology, applied in the field of video processing and pattern recognition, can solve the problems of destroying the stability of the running part, brake failure, easy to miss detection, etc., to reduce the risk of manual inspection, improve the safety prevention ability, reduce The effect of security incidents

Active Publication Date: 2019-06-28
中关村科技租赁股份有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the dynamic state of the train running, if the loaded goods are spilled, it will corrode the rails and pollute the environment, and at the worst, it will damage the stability of the running part, causing problems such as brakes and brake failure, which will lead to major safety accidents
At this stage, the detection and recognition of whether there are objects spilled in the compartment can only be carried out by human eyes, so not only the workload is heavy, but also it is difficult to observe when the vehicle is far away from people, and when the distance is close and the speed is fast, the human eyes The resolution ability is poor, which makes it easy to miss detection

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 video-based automatic detection method for falling objects from railway freight cars
  • A video-based automatic detection method for falling objects from railway freight cars
  • A video-based automatic detection method for falling objects from railway freight cars

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] With reference to accompanying drawing, a kind of video-based method for automatic detection of railway wagon spills, its moving target detection based on background modeling and target recognition algorithm based on neural network, comprises the steps:

[0041] Step 1 to get the video;

[0042] Use high-speed high-definition network cameras to obtain high-definition video with a resolution of 1280*720 at the railway site, and the central axis of the video is 30 degrees from the direction of the train;

[0043] Step 2 establishes the histogram gradient feature model of the train running part;

[0044] Step a. Collect and mark the walking part samples and non-walking part samples, and all samples are intercepted to a size of 64*64;

[0045] Step b, calculating the histogram gradient feature of each sample;

[0046] The calculation method of the histogram gradient feature is as follows:

[0047] The image horizontal gradient and vertical gradient are calculated as (1) ...

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 field of video processing and pattern recognition, and in particular relates to a video-based automatic detection method for railway wagon spills, which is based on background modeling-based moving target detection and neural network-based target recognition algorithms. Its background modeling-based moving target detection and neural network-based target recognition algorithm include the following steps: Step 1. Acquire video; Step 2. Establish the histogram gradient feature model of the train running part; Step 3. Use background modeling technology to extract Suspected spills; Step 4. Recognition of suspected spills based on neural network (ANN). The invention realizes the automatic detection and recognition of the spilled objects of the truck under the state of the train running at high speed, has high detection accuracy and low misclassification rate, and the fast detection speed also satisfies the actual engineering needs.

Description

technical field [0001] The invention belongs to the field of video processing and pattern recognition, and in particular relates to a video-based automatic detection method for railway wagon spills, which is based on background modeling-based moving target detection and neural network-based target recognition algorithms. Background technique [0002] During the operation of trains, especially freight cars and ordinary passenger cars, it is required to seal the compartments. When the train is running in a dynamic state, if the loaded goods are spilled, it will corrode the rails and pollute the environment, and at the worst, it will damage the stability of the running part, causing problems such as brakes and brake failure, which will lead to major safety accidents. At this stage, the detection and recognition of whether there are objects spilled in the compartment can only be carried out by human eyes, so not only the workload is heavy, but also it is difficult to observe whe...

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): G06K9/00G06N3/08
CPCG06N3/084G06V20/44G06V20/41
Inventor 俞大海李均李飞单玉堂
Owner 中关村科技租赁股份有限公司
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