CN203012745U - Human abnormal behavior detecting and early-warning system based on motion identification - Google Patents

Human abnormal behavior detecting and early-warning system based on motion identification Download PDF

Info

Publication number
CN203012745U
CN203012745U CN 201220605613 CN201220605613U CN203012745U CN 203012745 U CN203012745 U CN 203012745U CN 201220605613 CN201220605613 CN 201220605613 CN 201220605613 U CN201220605613 U CN 201220605613U CN 203012745 U CN203012745 U CN 203012745U
Authority
CN
China
Prior art keywords
warning system
human body
host
processing unit
dsp
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN 201220605613
Other languages
Chinese (zh)
Inventor
陈拥权
王略志
刘思杨
胡翀豪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei Huanjing Information Technology Co Ltd
Original Assignee
Hefei Huanjing Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hefei Huanjing Information Technology Co Ltd filed Critical Hefei Huanjing Information Technology Co Ltd
Priority to CN 201220605613 priority Critical patent/CN203012745U/en
Application granted granted Critical
Publication of CN203012745U publication Critical patent/CN203012745U/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Landscapes

  • Alarm Systems (AREA)

Abstract

The utility model discloses a human abnormal behavior detecting and early-warning system based on motion identification. The system comprises a host, a display connected to the host, a wristlet worn on the wrist and image acquiring boxes arranged in multiple positions in an activity space, wherein each image acquiring box is mounted on a liftable tripod; an FPGA (Field Programmable Gate Array) and a DSP (Digital Signal Processor) in bidirectional communication are arranged in the image acquiring box, and a pair of cameras orientated to the human body is arranged on the sidewall of the image acquiring box; the two cameras are respectively connected with the FPGA via signal lines, and the DSP is respectively connected with the two cameras via I2C/SPI buses, and communicated with the host via a USB bus; and a central processing unit and an inertia measuring unit and a wireless module respectively connected with the central processing unit are arranged in the wristlet, the central processing unit is in communication connection with the host via the wireless module, and the host is also connected with an external early-warning system. The human abnormal behavior detecting and early-warning system based on motion identification can detect human abnormal behaviors as well as carry out alarming.

Description

A kind of human body abnormal behaviour based on action recognition detects and early warning system
Technical field
The utility model relates to the field of human-computer interaction based on video, is specially a kind of human body abnormal behaviour based on action recognition and detects and early warning system.
Background technology
Consisted of by the handle of built-in sensitive device, main frame, display, action recognition module etc. based on the motion identification device of video, can be by the moving image of the camera collection human body in motion identification device, and by integrated image algorithm chip, moving image is resolved, form the Three-Dimensional Dynamic coordinate of human motion, synthetic and the emulation through the image of main frame, show at last corresponding action in display, therefore can be used as the equipment of human body abnormal behaviour based on the motion identification device of video.Still do not have the ripe human body abnormal behaviour based on action recognition to detect and early warning system in prior art.
The utility model content
The purpose of this utility model is to provide a kind of human body abnormal behaviour based on action recognition and detects and early warning system, to solve prior art not based on the human body abnormal behaviour detection of action recognition and the problem of early warning system.
In order to achieve the above object, the technical scheme that adopts of the utility model is:
a kind of human body abnormal behaviour based on action recognition detects and early warning system, include main frame, the display of access host, it is characterized in that: also include the muffetee that human hands is worn, and the image acquisition box that in human body movable space, many places arrange, the image acquisition box is built-in with the FPGA of both-way communication connection each other, DSP, be provided with the camera of a pair of aligning human body on image acquisition box sidewall, two cameras access FPGA by signal wire respectively, DSP is connected with two cameras by the I2C/SPI bus respectively, DSP also connects by usb bus and host communication, muffetee is built-in with center processing unit, and the Inertial Measurement Unit that accesses respectively center processing unit, wireless module, center processing unit is connected with host communication by wireless module, main frame also is circumscribed with early warning system.
Described a kind of human body abnormal behaviour based on action recognition detects and early warning system, and it is characterized in that: described Inertial Measurement Unit comprises three dimension acceleration sensor, three-axis gyroscope, magnetic sensor.
Described a kind of human body abnormal behaviour based on action recognition detects and early warning system, and it is characterized in that: described each image acquisition box is arranged on respectively on a liftable tripod.
The utility model can be applicable in old man or child's bedroom, by the camera collection human motion image, gather human body movement data by Inertial Measurement Unit in muffetee, and be sent to respectively main frame, simulate the relevant action picture on display in conjunction with human body movement data according to human motion image by the main frame internal program, and, when having abnormal behaviour to occur, can report to the police by early warning system.The utility model can detect the abnormal behaviour of human body, can also report to the police.
Description of drawings
Fig. 1 is the utility model structural representation.
Fig. 2 is the utility model image acquisition box theory diagram.
Fig. 3 is the utility model muffetee inner structure theory diagram.
Embodiment
As Fig. 1, Fig. 2 and shown in Figure 3.a kind of human body abnormal behaviour based on action recognition detects and early warning system, include main frame 1, the display 2 of access host 1, also include the muffetee 3 that human hands is worn, and the image acquisition box 4 that in human body movable space, many places arrange, each image acquisition box 4 is arranged on respectively on a liftable tripod 5, image acquisition box 4 is built-in with the FPGA of both-way communication connection each other, DSP, be provided with the camera 6 of a pair of aligning human body on image acquisition box 4 sidewalls, two cameras 6 access FPGA by signal wire respectively, DSP is connected with two cameras 6 by the I2C/SPI bus respectively, DSP also connects by usb bus and main frame 1 communication, muffetee 3 is built-in with center processing unit, and the Inertial Measurement Unit that accesses respectively center processing unit, wireless module, center processing unit is connected with main frame 1 communication by wireless module, main frame 1 also is circumscribed with early warning system 7.
Inertial Measurement Unit comprises three dimension acceleration sensor, three-axis gyroscope, magnetic sensor.

Claims (3)

1. the human body abnormal behaviour based on action recognition detects and early warning system, include main frame, the display of access host, it is characterized in that: also include the muffetee that human hands is worn, and the image acquisition box that in human body movable space, many places arrange, the image acquisition box is built-in with the FPGA of both-way communication connection each other, DSP, be provided with the camera of a pair of aligning human body on image acquisition box sidewall, two cameras access FPGA by signal wire respectively, DSP is connected with two cameras by the I2C/SPI bus respectively, DSP also connects by usb bus and host communication, muffetee is built-in with center processing unit, and the Inertial Measurement Unit that accesses respectively center processing unit, wireless module, center processing unit is connected with host communication by wireless module, main frame also is circumscribed with early warning system.
2. a kind of human body abnormal behaviour based on action recognition according to claim 1 detects and early warning system, and it is characterized in that: described Inertial Measurement Unit comprises three dimension acceleration sensor, three-axis gyroscope, magnetic sensor.
3. a kind of human body abnormal behaviour based on action recognition according to claim 1 detects and early warning system, and it is characterized in that: described each image acquisition box is arranged on respectively on a liftable tripod.
CN 201220605613 2012-11-15 2012-11-15 Human abnormal behavior detecting and early-warning system based on motion identification Expired - Fee Related CN203012745U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201220605613 CN203012745U (en) 2012-11-15 2012-11-15 Human abnormal behavior detecting and early-warning system based on motion identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201220605613 CN203012745U (en) 2012-11-15 2012-11-15 Human abnormal behavior detecting and early-warning system based on motion identification

Publications (1)

Publication Number Publication Date
CN203012745U true CN203012745U (en) 2013-06-19

Family

ID=48604318

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201220605613 Expired - Fee Related CN203012745U (en) 2012-11-15 2012-11-15 Human abnormal behavior detecting and early-warning system based on motion identification

Country Status (1)

Country Link
CN (1) CN203012745U (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104463090A (en) * 2013-11-25 2015-03-25 安徽寰智信息科技股份有限公司 Method for recognizing actions of human body skeleton of man-machine interactive system
CN106599849A (en) * 2016-12-16 2017-04-26 合肥寰景信息技术有限公司 Human gait analyzing system based on action recognition technologies
CN106781273A (en) * 2016-12-16 2017-05-31 合肥寰景信息技术有限公司 A kind of human body unusual checking and early warning system based on action recognition

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104463090A (en) * 2013-11-25 2015-03-25 安徽寰智信息科技股份有限公司 Method for recognizing actions of human body skeleton of man-machine interactive system
CN106599849A (en) * 2016-12-16 2017-04-26 合肥寰景信息技术有限公司 Human gait analyzing system based on action recognition technologies
CN106781273A (en) * 2016-12-16 2017-05-31 合肥寰景信息技术有限公司 A kind of human body unusual checking and early warning system based on action recognition

Similar Documents

Publication Publication Date Title
US10342464B2 (en) 3D camera system for infant monitoring
CN205898143U (en) Robot navigation system based on machine vision and laser sensor fuse
CN203012745U (en) Human abnormal behavior detecting and early-warning system based on motion identification
CN105243787B (en) A kind of Falls in Old People warning system, alarm method and alarm
US10959646B2 (en) Image detection method and image detection device for determining position of user
CN203000939U (en) Human gait analytical system based on gesture recognition technology
CN203000938U (en) Human body falling recognizing and early warning system based on video monitoring
CN203634173U (en) Human-body three-dimensional posture and behavior state sensory monitoring device
CN204931656U (en) A kind of wearable intelligent equipment
Zhen et al. Wearable preimpact fall detector using SVM
CN104586401A (en) Method for tracking gesture of human body
CN102989156B (en) A kind of training of the archery based on action recognition technology accessory system
CN206300937U (en) A kind of Wearable air quality intelligent monitoring and controlling device
CN106527692B (en) A kind of virtual reality all-in-one machine for supporting external equipment
Ye et al. Research of fall detection and alarm applications for the elderly
CN203001823U (en) Health promotion system based on Internet of Things and action recognition technology
CN104680753A (en) Human body falling detection system based on wireless sensing technology
CN203139506U (en) Sit-up training assistant system on basis of action identification technology
CN202961778U (en) Indoor-exercise warm-up system based on action recognition technology
CN202961801U (en) Exercise prescription system based on action recognition technology
CN203012746U (en) Gait analysis identity identification system applicable to bank
CN209607117U (en) A kind of Intelligent earthquake alarm
CN202960483U (en) Physical constitution detecting system based on action recognition technology
CN112466090A (en) Intelligent rescue bracelet
CN102989121B (en) Action recognition-based Alzheimer's disease preventing and rehabilitation training system

Legal Events

Date Code Title Description
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20130619

Termination date: 20181115