The invention relates to a prison abnormal condition monitoring method and a monitoring system based on depth learning

An abnormal situation and deep learning technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as the inability to automatically identify abnormal behaviors, and achieve the effects of improving recognition accuracy, fast recognition, and reducing costs.

Pending Publication Date: 2019-03-22
AEROSPACE INFORMATION
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development of science and technology, intelligent security has been widely used, especially prison intelligent security, but the dynamic face/body deployment control system currently used can only realize real-time 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
  • The invention relates to a prison abnormal condition monitoring method and a monitoring system based on depth learning
  • The invention relates to a prison abnormal condition monitoring method and a monitoring system based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] figure 1 A flow chart of a method for monitoring abnormal conditions in prisons based on deep learning according to an embodiment of the present invention is shown. figure 2 It shows the working principle diagram of the prison abnormality monitoring method based on deep learning according to one embodiment of the present invention.

[0046] combine figure 1 and figure 2As shown, the prison abnormal situation monitoring method based on deep learning includes: S102: Based on the first sub-network, generate time series information of key points of the human body;

[0047] Step S102 includes steps S1021-S1023:

[0048] S1021: Using a convolutional neural network model to extract feature points of video information;

[0049] S1022: Determine the key point information of the human body according to the feature points;

[0050] S1023: Generate time-series information of key points of the human body according to the key point information of the human body;

[0051] Wher...

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 prison abnormal condition monitoring method and monitoring system based on depth learning. Generating a sequence feature vector for the audio information based on the secondsub-network; Based on the third sub-network, human behavior is recognized according to the time sequence information of human key points and the sequence eigenvector. Based on the recognized human behavior, abnormal alarm is output when the behavior is abnormal. The prison abnormal condition monitoring method based on depth learning of the invention comprises the following steps of: forming a whole network by three interrelated sub-networks, The training and in-depth learning of the three sub-networks can improve the training speed and recognition accuracy, identify potential abnormal events faster, reduce the cost of human monitoring, eliminate the security risks, and lay a quantitative foundation for the implementation of artificial intelligence to assist the supervision of penalty change and the necessity of detention review and evaluation.

Description

technical field [0001] The invention belongs to the field of intelligent alert technology, and more specifically, relates to a method and system for monitoring abnormal conditions in prisons based on deep learning. Background technique [0002] With the development of science and technology, intelligent security has been widely used, especially prison intelligent security, but the dynamic face / body deployment control system currently used can only realize real-time detection, tracking and identification of a single individual in the surveillance video. The tracking records before, during and after the event cannot realize automatic identification of abnormal behavior, intelligent analysis and intelligent alarm. Therefore, there is an urgent need for a method that can automatically identify, intelligently analyze, and intelligently warn behaviors such as abnormal collisions between prisoners and supervisors, which can effectively eliminate hidden safety hazards such as cell b...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2413G06F18/25
Inventor 朱宁莉邓海李根代合鹏李素莹关大英
Owner AEROSPACE INFORMATION
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