Face recognition security alarm method based on embedded artificial intelligence chip

A face recognition and artificial intelligence technology, applied in the field of intelligent recognition, can solve problems such as long delay, data loss, push, etc., to solve the problem of real-time security, low cost, and reduce the effect of intermediate processes

Pending Publication Date: 2019-12-03
YANGTZE UNIVERSITY
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (1) The existing technology cannot preserve the intrusion evidence for a long time
[0007] (2) The face recognition process of the existing technology is not perfect, and there are problems such as delay, security, and data loss
[0008] (3) Most of the existing technologies rely on third-party server resources for face recognition, which leads to the fact that the recognition process needs to go through a network channel, so there must be long delays, data loss and other problems, and the real-time performance is not good
[0009] (4) The existing technology cannot realize intelligent extraction of intrusion evidence and save it, only the collected surveillance video can be saved, which makes it more troublesome to find evidence
[0010] (5) The existing technology cannot push the video evidence of the intrusion to the client in real time, which is convenient for the user to view and report to the police in time
[0011] (6) The existing alarm methods cannot make real-time judgments and perform real-time alarms based on the judgment results. The results need to be determined with the help of external multi-level judgments, which often miss the best time to solve the case

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
  • Face recognition security alarm method based on embedded artificial intelligence chip
  • Face recognition security alarm method based on embedded artificial intelligence chip
  • Face recognition security alarm method based on embedded artificial intelligence chip

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0110] opencv library: an image processing module open sourced by the computer, used to obtain camera data. TCP / IP protocol: network communication protocol, Internet communication infrastructure. Deep Learning: Using computer artificial neural networks to extract features from input data, in order to achieve the machine's ability to learn similarly to the human brain.

[0111] Matrix convolution operation: the underlying calculation method of artificial neural network in computer deep learning, which exists in CNN neural network. Face recognition model: a black box used for face recognition calculations. The model is actually a set of very complicated mathematical formulas, which are only learned by computers. After the image is calculated through the mathematical formulas, another set of data is obtained. This Group data can be used as the basis for classification. RTMP protocol: Real Time Messaging Protocol (Real Time Message Transmission Protocol) is a streaming media tra...

Embodiment 2

[0113] The following are five sets of test results of the face recognition accuracy of embedded smart chips based on real surveillance videos in life. Each set contains about 1,000 frames of data, and each set is first recognized by a machine and then manually Identify the results of judgments. In the table below, the first column represents the label of any person that will appear in life (here is only the person who appears in the experiment, with the initials of the name as the label); the second column indicates whether the smart chip can recognize this person (know This person); the third column is the number of times the person actually appears in this set of frame data; the fourth column indicates the number of times the person is actually detected by the recognition algorithm, and the fifth column is the recognition accuracy rate of the corresponding label. Because there must be frames with no faces in each set of frame data, the frames without faces are represented by...

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 technical field of intelligent recognition, and discloses a face recognition security alarm method based on an embedded artificial intelligence chip, which can perform video acquisition, transmission, storage, face positioning, face recognition and sending of alarm information and video information based on the embedded artificial intelligence chip. Specifically, the method comprises: collecting video information through the video data collection module, transferring uploaded data through the data transfer module, judging whether someone invades or not through facerecognition conducted by the recognition and judgment module through the local development board, judging and starting an alarm after recognition, issuing alarm information to a user, and the user can obtain an alarm result in time and process the alarm result. According to the invention, real-time face recognition is directly carried out on a transmitted video without sending data to a third-party server for recognition, so that real-time monitoring alarm and evidence storage can be realized, and a user can directly use a mobile phone APP to play and display a real-time picture.

Description

technical field [0001] The invention belongs to the technical field of intelligent recognition, and in particular relates to a face recognition security alarm method based on an embedded artificial intelligence chip. It specifically relates to a face recognition security alarm method based on an embedded artificial intelligence chip that can perform video acquisition, transmission, and storage; face positioning, face recognition, alarm information, and video information transmission. Background technique [0002] Currently, the closest prior art: [0003] Security issues have always been a prominent issue in life. Whether it is access control or monitoring methods, there are some unsolvable problems, such as: real-time alarm, evidence video preservation, machine active identification, etc. In today's big environment, there are many problems whether it is home security, store security, or company security. Although there are endless security products on the market, the means...

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): G06K9/00G06K9/62H04N7/18
CPCH04N7/18G06V40/172G06F18/241
Inventor 熊杰马博涂俊峰刘华祠刘建杜峰马兰芳
Owner YANGTZE UNIVERSITY
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