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

Artificial intelligence CNN and LSTM neural network dynamic identification system

A neural network and artificial intelligence technology, applied in biological neural network models, transmission systems, neural architectures, etc., can solve problems such as affecting the accuracy of results, incompleteness, and unreasonable design, and achieve the effect of highlighting substantive characteristics.

Pending Publication Date: 2020-12-11
JIANGSU VOCATIONAL INST OF ARCHITECTURAL TECH
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (1) The patented shooting terminal The shooting collection terminal (100) is used to collect video streams containing facial features, voice features, and behavioral feature information, and automatically detect and track information on human face, voice, and behavioral features in the image, and then Perform a series of behavior-related technical processing on the detected face features, voice features and behavior feature information, including face recognition, voice recognition, behavior feature information recognition and abnormal behavior recognition (including fighting, theft, falling of the elderly, event, intrusion, etc.), and send the image sequence to the server (200) through wireless communication. The network includes a local area network, the Internet or a wireless network. As we all know, in real life, the shooting terminal (100) can only use Cameras used to serve the public to take pictures and then transmit data are particularly limited in this way: if abnormal behaviors cannot be collected in all directions, if there are no corresponding surveillance cameras in many places, this will cause inability to collect comprehensively Abnormal behavior, how to realize comprehensive information and data collection on the basis of it, this patent cannot be realized, so the limitation is small;
[0007] (2) The convolutional network neural network (300) in this patent is unreasonably designed, which will affect the accuracy of subsequent results

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
  • Artificial intelligence CNN and LSTM neural network dynamic identification system
  • Artificial intelligence CNN and LSTM neural network dynamic identification system
  • Artificial intelligence CNN and LSTM neural network dynamic identification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] see Figure 1-6 , an artificial intelligence CNN, LSTM neural network dynamic recognition system, including sequentially connected shooting acquisition terminal 100, server 200, convolutional neural network 300, long short-term memory neural network 400, early warning system 500, elimination system 600, cloud server 700 , the screening system 900, the confirmation module 1000 and the local data module 800, the output end of the elimination system 600 is also connected to the input end of the local data module 800, and the shooting collection terminal 100 is used to collect information containing facial features, voice features and behavioral features Videos or images, and automatically detect and track information about human faces, voices, and behavioral features in the videos or images;

[0036] Shooting collection terminal 100 comprises public camera 110 in the area, private camera 120 in the area, driving recorder 130 in the area and mobile phone terminal 140 in the...

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 an artificial intelligence CNN and LSTM neural network dynamic identification system, which belongs to the field of intelligent security early warning, and comprises a shootingacquisition terminal, a server, a convolutional neural network, a long-short-term memory neural network, an early warning system, a rejection system, a cloud server, a screening system, a confirmation module and a local data module which are connected in sequence, the output end of the elimination system is also connected with the input end of the local data module; the shooting acquisition terminal comprises an intra-area public camera, an intra-area private camera, an intra-area automobile data recorder and an intra-area mobile phone terminal, and authority acquisition APPs are arranged inthe intra-area public camera, the intra-area private camera, the intra-area automobile data recorder and the intra-area mobile phone terminal. The shooting acquisition terminal is connected with the server through the wireless communication unit to realize transmission; according to the system, comprehensive information data acquisition is facilitated, the application range is wide, and the accuracy is high.

Description

technical field [0001] The present invention relates to the field of intelligent security early warning, more specifically, relates to an artificial intelligence CNN, LSTM neural network dynamic identification system. Background technique [0002] Artificial intelligence CNN, LSTM neural network dynamic recognition system is a combination of advanced shooting terminal technology, central processing unit CPU, image processor GPU, neural network processor NPU, heterogeneous / reconfigurable processor technology, convolutional neural network technology, Effective integration of long and short-term memory neural network technology, AI computer early warning processing technology, AI artificial intelligence early warning operation technology, risk factor collection technology, risk factor identification technology, big data analysis technology, cloud computing technology, cloud storage technology, cloud database technology, etc. It is applied to the entire artificial intelligence C...

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): G06N3/04G06N3/08H04L29/08H04M1/725H04N7/18G06K9/00
CPCG06N3/049G06N3/08H04L67/025H04L67/12H04N7/181G06V20/52G06N3/044G06N3/045
Inventor 郭扬袁涛殷粉芳
Owner JIANGSU VOCATIONAL INST OF ARCHITECTURAL TECH
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