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

Electronic fence risk early warning method based on deep learning

An electronic fence and deep learning technology, applied in the field of deep learning, can solve problems such as the difficulty in forming a unified integrated platform, the inability to provide open protocols and interfaces, and the control and management of the perimeter alarm system, so as to achieve the effect of avoiding impact

Pending Publication Date: 2021-11-02
北京京能电力股份有限公司 +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most of the perimeter alarm systems still stay on the front-end alarm and the control and management of a single device. If you want to achieve cross-regional remote control and management, you must rely on a third-party alarm system for integration
However, manufacturers that provide alarm systems may not be able to provide open protocols and interfaces, and it is difficult to form a unified integrated platform, resulting in a "decentralized management" system for the security system that should have been planned in a unified manner. At the same time, the existing electronic fence is inconvenient Difficult to change and adjust in real time according to demand

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
  • Electronic fence risk early warning method based on deep learning
  • Electronic fence risk early warning method based on deep learning
  • Electronic fence risk early warning method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described are only used to explain the present invention, but not to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative efforts shall fall within the protection scope of the present invention.

[0040] Refer to attached figure 1 , the present invention provides a method for early warning of electronic fence risks based on deep learning, including:

[0041] Obtain an image containing a cone and mark its position, construct a cone detection model, and input the image of the marked cone position into the cone detection model for training;

[0042] Through the trained cone detection model, ...

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 relates to an electronic fence risk early warning method based on deep learning, and the method comprises the steps of constructing a conical barrel detection model based on deep learning, carrying out the training, recognizing a conical barrel in an image collected in real time through the conical barrel detection model after the training is completed, selecting a recognition point after the recognition is completed, carrying out the calculation and determination of an electronic fence range, and further identifying a moving target in the image, judging whether the moving target is within the coverage range of the electronic fence, and if so, sending out an alarm signal. According to the invention, it can be judged that an electronic fence is established at an accident occurrence site through image recognition, and whether an obstacle hindering accident investigation exists in the range of the electronic fence is judged, so that the influence on accident elimination is avoided.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a method for early warning of electronic fence risks based on deep learning. Background technique [0002] The electronic fence is currently the most advanced perimeter anti-theft alarm system. Usually, the electronic fence is set outdoors and installed along the original wall (such as a brick wall, cement wall, iron fence or tapered barrel), and the alarm signal is transmitted through the signal transmission device. It is sent to the back-end control center to display the working status of the defense zone. Most electronic fencing today is used for agricultural fencing and other forms of animal management, but is also often used to enhance security in sensitive areas such as military installations, prisons and other security-sensitive locations, where lethal voltages are present. [0003] At present, most of the perimeter alarm systems still stay on the front-end alarm an...

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): G06K9/00G06N3/08G08B13/194
CPCG06N3/08G08B13/194
Inventor 廉旭刚杜虎君李勇景杰潘作为和雄伟梁志刚赵路佳胡小强宋国宏
Owner 北京京能电力股份有限公司
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