CN106778678A - A kind of Human bodys' response system - Google Patents
A kind of Human bodys' response system Download PDFInfo
- Publication number
- CN106778678A CN106778678A CN201611272104.3A CN201611272104A CN106778678A CN 106778678 A CN106778678 A CN 106778678A CN 201611272104 A CN201611272104 A CN 201611272104A CN 106778678 A CN106778678 A CN 106778678A
- Authority
- CN
- China
- Prior art keywords
- module
- human
- identification
- pretreatment
- response system
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Abstract
The invention discloses a kind of Human bodys' response system, including module of target detection, target tracking module, pretreatment module, characteristic extracting module, identification sort module, judge module, wireless transport module, handheld client end, display and printer;The module of target detection, target tracking module, pretreatment module, characteristic extracting module, identification sort module, judge module, wireless transport module, handheld client end are sequentially connected, and the judge module is connected with display and printer respectively.The system have discrimination it is high, it is easy to operate the characteristics of, be adapted to popularization and application.
Description
Technical field
The invention belongs to field of computer technology, specifically, it is related to a kind of Human bodys' response system.
Background technology
Computer is deeply welcomed by the people with arithmetic speed by the superpower memory of itself, both abilities of computer
Also the abundant utilization of people has been obtained.Video image has become the important means that people obtain visual information, particularly video
Stream is combined with computer disposal, and people are referred to as computer vision.The mankind obtain objective world letter by eye, ear, nose, mouth, hand
During breath, 80% information comes from vision, it can be seen that, it is extremely important that human visual system obtains information to the mankind.As people
The simulation of class vision, computer vision is played an important role in computer obtains objective world information.
For the deficiency of current Human bodys' response system, a kind of labour intensity that can reduce manual identified is developed,
And energy real-time tracking human body target, and then its behavior is recognized, make up the error of manual identified.With image, figure, Video processing
Theoretical reaches its maturity, the high speed development of computer science and technology so that computer has powerful computing capability with storage energy
Power.It is badly in need of a kind of Human bodys' response system in currently available technology.
The content of the invention
In order to overcome defect present in prior art, the present invention to provide a kind of discrimination human body row high, easy to operate
It is identifying system.
Its technical scheme is as follows:
A kind of Human bodys' response system, including module of target detection, target tracking module, pretreatment module, feature are carried
Modulus block, identification sort module, judge module, wireless transport module, handheld client end, display and printer;The target
Detection module, target tracking module, pretreatment module, characteristic extracting module, identification sort module, judge module, be wirelessly transferred
Module, handheld client end are sequentially connected, and the judge module is connected with display and printer respectively;
The module of target detection is used for the extraction to movement human profile and obtains accurate human body contour outline;
The target tracking module is used to determine the process of same moving target position in different frame, calculates motion rail
Mark;
The pretreatment module to signal for being filtered, the pretreatment of denoising;
The characteristic extracting module is used to excavate reaction human motion by signal transacting in acceleration signal feature
The information of state;
The identification sort module carries out Classification and Identification for reference model to acceleration signal feature set;
The judge module is used to carry out final judged result to the acceleration signal feature set of Classification and Identification;
The wireless transport module is used to will determine that result is transferred to handheld client end;
The display is used to show judged result;
The printer is used to print judged result.
Further, the acceleration signal feature includes temporal signatures, frequency domain character and time-frequency characteristics.
Further, the handheld client end includes mobile phone, panel computer.
Further, the display is LED electronic consoles.
Beneficial effects of the present invention:
The Human bodys' response system identification efficiency high of technical solution of the present invention, and with preferable real-time, can be with
Grasp the judged result of Human bodys' response at any time by handheld client end, can will determine that result is shown and printed, can
It is strong depending on property.The system have recognition efficiency it is high, it is easy to operate the characteristics of, be adapted to popularization and application.
Brief description of the drawings
Fig. 1 is the schematic diagram of Human bodys' response system.
Specific embodiment
Technical scheme is described in more detail with reference to the accompanying drawings and detailed description.
Reference picture 1, a kind of Human bodys' response system, including module of target detection, target tracking module, pretreatment mould
Block, characteristic extracting module, identification sort module, judge module, wireless transport module, handheld client end, display and printer;
The module of target detection, target tracking module, pretreatment module, characteristic extracting module, identification sort module, judge module,
Wireless transport module, handheld client end are sequentially connected, and the judge module is connected with display and printer respectively;
The module of target detection is used for the extraction to movement human profile and obtains accurate human body contour outline;
The target tracking module is used to determine the process of same moving target position in different frame, calculates motion rail
Mark;
The pretreatment module to signal for being filtered, the pretreatment of denoising;
The characteristic extracting module is used to excavate reaction human motion by signal transacting in acceleration signal feature
The information of state;
The identification sort module carries out Classification and Identification for reference model to acceleration signal feature set;
The judge module is used to carry out final judged result to the acceleration signal feature set of Classification and Identification;
The wireless transport module is used to will determine that result is transferred to handheld client end;
The display is used to show judged result;
The printer is used to print judged result.
The acceleration signal feature includes temporal signatures, frequency domain character and time-frequency characteristics.
The handheld client end includes mobile phone, panel computer.
The display is LED electronic consoles.
The present invention is initialized during concrete application to background image;Using background subtraction method and time difference
The method that method is combined, extracts the changing unit in video sequence;After extracting the region for producing change, binaryzation is made to it
Treatment;Then morphology processing is carried out to binaryzation region of variation, the small noise module for existing is removed, while filling up motion
Target internal cavity and connection breakpoint;Result is counted, if its area is less than certain threshold value, then it is assumed that be noise, this
Region retains as background process, area more than the region of threshold value;Human body contour outline in piece image should be a connection
Region.If result is a connected region more than threshold value, as the result for extracting human body contour outline.Target tracking module
Determine the process of same moving target position in different frame, calculate movement locus;Pretreatment module is filtered to signal, goes
The pretreatment made an uproar;Characteristic extracting module excavates reaction human motion state in acceleration signal feature by signal transacting
Information;Identification sort module reference model carries out Classification and Identification to acceleration signal feature set;Judge module is to Classification and Identification
Acceleration signal feature set carries out final judged result;Wireless transport module will determine that result is transferred to handheld client end.People
Body Activity recognition system identification efficiency high, and with preferable real-time, human body can at any time be grasped by handheld client end
The judged result of Activity recognition, can will determine that result is shown and printed, visual strong.The system has recognition efficiency
High, easy to operate the characteristics of, it is adapted to popularization and application.
The above, preferably specific embodiment only of the invention, protection scope of the present invention not limited to this are any ripe
Those skilled in the art are known in the technical scope of present disclosure, the letter of the technical scheme that can be become apparent to
Altered or equivalence replacement are each fallen within protection scope of the present invention.
Claims (4)
1. a kind of Human bodys' response system, it is characterised in that:Including module of target detection, target tracking module, pretreatment mould
Block, characteristic extracting module, identification sort module, judge module, wireless transport module, handheld client end, display and printer;
The module of target detection, target tracking module, pretreatment module, characteristic extracting module, identification sort module, judge module,
Wireless transport module, handheld client end are sequentially connected, and the judge module is connected with display and printer respectively;
The module of target detection is used for the extraction to movement human profile and obtains accurate human body contour outline;
The target tracking module is used to determine the process of same moving target position in different frame, calculates movement locus;
The pretreatment module to signal for being filtered, the pretreatment of denoising;
The characteristic extracting module is used to excavate reaction human motion state by signal transacting in acceleration signal feature
Information;
The identification sort module carries out Classification and Identification for reference model to acceleration signal feature set;
The judge module is used to carry out final judged result to the acceleration signal feature set of Classification and Identification;
The wireless transport module is used to will determine that result is transferred to handheld client end;
The display is used to show judged result;
The printer is used to print judged result.
2. Human bodys' response system according to claim 1, it is characterised in that:When the acceleration signal feature includes
Characteristic of field, frequency domain character and time-frequency characteristics.
3. Human bodys' response system according to claim 1, it is characterised in that:The handheld client end include mobile phone,
Panel computer.
4. Human bodys' response system according to claim 1, it is characterised in that:The display is LED electronical displays
Device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611272104.3A CN106778678A (en) | 2016-12-29 | 2016-12-29 | A kind of Human bodys' response system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611272104.3A CN106778678A (en) | 2016-12-29 | 2016-12-29 | A kind of Human bodys' response system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106778678A true CN106778678A (en) | 2017-05-31 |
Family
ID=58951875
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611272104.3A Pending CN106778678A (en) | 2016-12-29 | 2016-12-29 | A kind of Human bodys' response system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106778678A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289672A (en) * | 2011-06-03 | 2011-12-21 | 天津大学 | Infrared gait identification method adopting double-channel feature fusion |
CN102663452A (en) * | 2012-04-14 | 2012-09-12 | 中国人民解放军国防科学技术大学 | Suspicious act detecting method based on video analysis |
CN103020596A (en) * | 2012-12-05 | 2013-04-03 | 华北电力大学 | Method for identifying abnormal human behaviors in power production based on block model |
CN103324177A (en) * | 2013-06-10 | 2013-09-25 | 中山市拓维电子科技有限公司 | Dynamic quality remote monitoring system and method in production of cement concrete |
-
2016
- 2016-12-29 CN CN201611272104.3A patent/CN106778678A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289672A (en) * | 2011-06-03 | 2011-12-21 | 天津大学 | Infrared gait identification method adopting double-channel feature fusion |
CN102663452A (en) * | 2012-04-14 | 2012-09-12 | 中国人民解放军国防科学技术大学 | Suspicious act detecting method based on video analysis |
CN103020596A (en) * | 2012-12-05 | 2013-04-03 | 华北电力大学 | Method for identifying abnormal human behaviors in power production based on block model |
CN103324177A (en) * | 2013-06-10 | 2013-09-25 | 中山市拓维电子科技有限公司 | Dynamic quality remote monitoring system and method in production of cement concrete |
Non-Patent Citations (1)
Title |
---|
魏文华: "智能视频监控系统中人异常行为识别研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104504856A (en) | Fatigue driving detection method based on Kinect and face recognition | |
CN104134060B (en) | Sign language interpreter and display sonification system based on electromyographic signal and motion sensor | |
CN102831380A (en) | Body action identification method and system based on depth image induction | |
CN105787442B (en) | A kind of wearable auxiliary system and its application method of the view-based access control model interaction towards disturbance people | |
CN105469073A (en) | Kinect-based call making and answering monitoring method of driver | |
CN103426025B (en) | A kind of contactless push-up method of counting based on intelligent mobile phone platform | |
CN104468981B (en) | A kind of campus despot based on intelligent mobile phone platform insults detection method | |
CN101853399A (en) | Method for realizing blind road and pedestrian crossing real-time detection by utilizing computer vision technology | |
CN102509085A (en) | Pig walking posture identification system and method based on outline invariant moment features | |
CN105185118A (en) | Vehicle peccancy detection device and method based on video detection | |
CN109460704A (en) | A kind of fatigue detection method based on deep learning, system and computer equipment | |
CN104616002A (en) | Facial recognition equipment used for judging age groups | |
CN105989694A (en) | Human body falling-down detection method based on three-axis acceleration sensor | |
CN106648078A (en) | Multimode interaction method and system applied to intelligent robot | |
CN104298964A (en) | Human body behavior action fast recognition method and device | |
CN102749993B (en) | Motion recognition method based on skeleton node data | |
CN106408877A (en) | Rail traffic driver fatigue state monitoring method | |
CN105976675A (en) | Intelligent information exchange device and method for deaf-mute and average person | |
CN105913034B (en) | Vehicle identification method and device and vehicle | |
CN111709365A (en) | Automatic human motion posture detection method based on convolutional neural network | |
CN105590084A (en) | Robot human face detection tracking emotion detection system | |
CN108108651B (en) | Method and system for detecting driver non-attentive driving based on video face analysis | |
CN206152348U (en) | Intelligent toys control system based on gesture detects | |
CN202584048U (en) | Smart mouse based on DSP image location and voice recognition | |
CN106529460A (en) | Object classification identification system and identification method based on robot side |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |
|
RJ01 | Rejection of invention patent application after publication |