CN104537361A - Lie detection method and system based on video - Google Patents
Lie detection method and system based on video Download PDFInfo
- Publication number
- CN104537361A CN104537361A CN201510021412.8A CN201510021412A CN104537361A CN 104537361 A CN104537361 A CN 104537361A CN 201510021412 A CN201510021412 A CN 201510021412A CN 104537361 A CN104537361 A CN 104537361A
- Authority
- CN
- China
- Prior art keywords
- data
- measurand
- video
- lie
- carry out
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a lie detection method based on a video. The lie detection method includes the steps of detecting vision behavior characteristics of a detected object according to video images, detecting physiological parameter characteristics of the detected object according to the video images, and obtaining lying probability data by combining the vision behavior characteristics with the physiological parameter characteristics. According to the lie detection method, the vision behavior characteristics and the physiological parameter characteristics of a person are combined with the psychological principle, and the detection accuracy and the detection reliability are improved; in addition, the lie detection method has the advantage that the non-contact aim is achieved, and the defect that a traditional contact-type lie detection method is easily bewared is overcome.
Description
Technical field
The invention belongs to lie-detection technology field, particularly relate to a kind of lie detecting method based on video and lie detection system thereof.
Background technology
A lie detector has important effect when investigating the case, interrogating convict, although its can not 100% ensure detect accuracy, but its test data provides important reference to the mechanism such as public security organ, law court, law enfrocement official can be understood rapidly by the psychology of investigator, accelerate speed of solving a case.Whether therefore how to use technological means easily and fast and detect tested personnel exactly tells a lie significant.
Traditional lie detecting method is generally contact, is easily watched out for by measured, causes testing result inaccurate.
Summary of the invention
Based on this, for above-mentioned technical matters, provide a kind of lie detecting method based on video and lie detection system thereof.
For solving the problems of the technologies described above, the present invention adopts following technical scheme:
Based on a lie detecting method for video, comprising:
Visual behaviour feature according to video images detection measurand:
A, in described video image, identified the little trick of described measurand by algorithm for pattern recognition, and calculate the frequency that little trick occurs, this frequency is set to A;
B, the head detecting described measurand, hand and leg rock information: in described video image, be partitioned into head, hand and leg area, respectively feature point detection carried out to each region; In continuous print frame of video, unique point is followed the tracks of; Calculate the motion vector of each unique point, use I IR wave filter to carry out time-domain filtering to described motion vector, what obtain each region rocks information, is set to B, and formula is
b (n) is the unique point motion vector after the n-th frame calculates, and λ is weight coefficient;
Physiological parameter feature according to video images detection measurand: carry out Face datection and human eye location, extract the region of below eyes as area-of-interest; The RGB passage of described area-of-interest is split, gets the data of the G passage of multi-frame video image, calculate its mean value, be designated as Avg
g, the data value of the G passage of each frame is deducted Avg
gobtain Value
facei (), i is frame number, to the Value of multiframe
facei () data carry out gaussian filtering process, Removing Random No, carry out independent component analysis to the data sequence after gaussian filtering process, finally carry out Fourier transform, get the maximum frequency of amplitude spectrum as hrv parameter, are set to C;
The probability data Rate that lies by following formulae discovery measurand:
Rate=αA+βB+δC
, α, β and δ are weight factor.
This programme also relates to a kind of lie detection system based on video, comprising:
Video acquisition module, for gathering the video image of measurand, and by this transmission of video images to module and the data memory module of detecting a lie;
Detecting a lie module, for detecting described video image, obtain the probability data of lying of measurand, and probability data of this being lied sending to data storage cell; The described video image of described detection, the probability data of lying obtaining measurand comprises:
Visual behaviour feature according to video images detection measurand:
A, in described video image, identified the little trick of described measurand by algorithm for pattern recognition, and calculate the frequency that little trick occurs, this frequency is set to A;
B, the head detecting described measurand, hand and leg rock information: in described video image, be partitioned into head, hand and leg area, respectively feature point detection carried out to each region; In continuous print frame of video, unique point is followed the tracks of; Calculate the motion vector of each unique point, use iir filter to carry out time-domain filtering to described motion vector, what obtain each region rocks information, is set to B, and formula is
b (n) is the unique point motion vector after the n-th frame calculates, and λ is weight coefficient;
Physiological parameter feature according to video images detection measurand: carry out Face datection and human eye location, extract the region of below eyes as area-of-interest; The RGB passage of described area-of-interest is split, gets the data of the G passage of multi-frame video image, calculate its mean value, be designated as Avg
g, the data value of the G passage of each frame is deducted Avg
gobtain Value
facei (), i is frame number, to the Value of multiframe
facei () data carry out gaussian filtering process, Removing Random No, carry out independent component analysis to the data sequence after gaussian filtering process, finally carry out Fourier transform, get the maximum frequency of amplitude spectrum as hrv parameter, are set to C;
The probability data Rate that lies by following formulae discovery measurand:
Rate=αA+βB+δC
, α, β and δ are weight factor;
Data memory module, for storing the data from described video acquisition module and module of detecting a lie;
Network transmitting unit, for by the data of described video acquisition module, described in the detect a lie data of module and data of described data memory module be transferred to client terminal;
Client terminal, for showing the data from described video acquisition module and module of detecting a lie, and for showing and downloading the data from described data memory module.
Described client terminal is smart mobile phone, computing machine or PAD.
The visual behaviour characteristic sum physiological parameter feature of people combines with psychologic principle by the present invention, improve accuracy and the reliability of detection, and the method has contactless feature, avoids the mode of detecting a lie of conventional contact easily by the shortcoming of watching out for.
Accompanying drawing explanation
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail:
Fig. 1 is the process flow diagram of a kind of lie detecting method based on video of the present invention;
Fig. 2 is the structural representation of a kind of lie detection system based on video of the present invention.
Embodiment
As shown in Figure 1, a kind of lie detecting method based on video, comprising:
S101, visual behaviour feature according to video images detection measurand:
A, in video image, identified the little trick of measurand by algorithm for pattern recognition, as cried, blinking, grab ear etc., and calculate the frequency that little trick occurs, this frequency is set to A.
As: the sampling rate of video is 25 frames/second, touches nose 5 times in a second, and blinking is 9 times, then A=(5+9)/25.
B, detect the head of measurand, hand and leg rock information:
In video image, be partitioned into head, hand and leg area, respectively feature point detection carried out to each region.
In continuous print frame of video, unique point is followed the tracks of.
Calculate the motion vector of each unique point, use iir filter to carry out time-domain filtering to motion vector, what obtain each region rocks information, is set to B, and formula is
b (n) is the unique point motion vector after the n-th frame calculates, and λ is weight coefficient, and its span is 0 to 1.
Preferably, λ value is 0.3.
S102, physiological parameter feature according to video images detection measurand:
Carry out Face datection and human eye location, extract the region of below eyes as area-of-interest, particularly, opencv can be adopted to realize Face datection and human eye location.
The RGB passage of area-of-interest is split, gets the data of the G passage of multi-frame video image, calculate its mean value, be designated as Avg
g, the data value of the G passage of each frame is deducted Avg
gobtain Value
facei (), i is frame number, to the Value of multiframe
facei () data carry out gaussian filtering process, Removing Random No, carry out independent component analysis to the data sequence after gaussian filtering process, finally carry out Fourier transform, get the maximum frequency of amplitude spectrum as hrv parameter, are set to C.
S103, the probability data Rate that lies by following formulae discovery measurand:
Rate=αA+βB+δC
, α, β and δ are weight factor.
Wherein, the span of α, β and δ is 0 to 1, and meets constraint condition alpha+beta+δ=1, preferably, and α=0.4, β=0.3, δ=0.3; Be judged as lying when the probability data Rate that lies reaches 60.
The visual behaviour characteristic sum physiological parameter feature of people combines with psychologic principle by lie detecting method of the present invention; usually physiological parameter changes such as palpitating quickly can be produced when people is nervous; and touch chin, touch nose, smooth out with the fingers hair, the little trick such as eyes disorderly turn, both hands friction, by this little trick can calm oneself mood and calm down heart by the sense of touch of health and temperature.Therefore, the inventive method improves accuracy and the reliability of detection, and the method has contactless feature, avoids the lie detecting method of conventional contact easily by the shortcoming of watching out for.
As shown in Figure 2, this programme also relates to a kind of lie detection system based on video, comprises video acquisition module 11, module of detecting a lie 12, data memory module 13, network transmitting unit 14 and client terminal 15.
Video acquisition module 11 for gathering the video image of measurand, and by this transmission of video images to module 12 and the data memory module 13 of detecting a lie.
Module of detecting a lie 12, for detecting video image, obtain the probability data of lying of measurand, and probability data of this being lied sends to data storage cell.
Wherein, detect video image, the process obtaining the probability data of lying of measurand is as follows:
Visual behaviour feature according to video images detection measurand:
A, in video image, identified the little trick of measurand by algorithm for pattern recognition, as cried, blinking, grab ear etc., and calculate the frequency that little trick occurs, this frequency is set to A.
As: the sampling rate of video is 25 frames/second, touches nose 5 times in a second, and blinking is 9 times, then A=(5+9)/25.
B, detect the head of measurand, hand and leg rock information:
In video image, be partitioned into head, hand and leg area, respectively feature point detection carried out to each region.
In continuous print frame of video, unique point is followed the tracks of.
Calculate the motion vector of each unique point, use iir filter to carry out time-domain filtering to motion vector, what obtain each region rocks information, is set to B, and formula is
b (n) is the unique point motion vector after the n-th frame calculates, and λ is weight coefficient, and its span is 0 to 1.
Preferably, λ value is 0.3.
S102, physiological parameter feature according to video images detection measurand:
Carry out Face datection and human eye location, extract the region of below eyes as area-of-interest, particularly, opencv can be adopted to realize Face datection and human eye location.
The RGB passage of area-of-interest is split, gets the data of the G passage of multi-frame video image, calculate its mean value, be designated as Avg
g, the data value of the G passage of each frame is deducted Avg
gobtain Value
facei (), i is frame number, to the Value of multiframe
facei () data carry out gaussian filtering process, Removing Random No, carry out independent component analysis to the data sequence after gaussian filtering process, finally carry out Fourier transform, get the maximum frequency of amplitude spectrum as hrv parameter, are set to C.
S103, according to visual behaviour feature and physiological parameter feature, and by the probability data Rate that lies of following formulae discovery measurand:
Rate=αA+βB+δC
, α, β and δ are weight factor.
Wherein, the span of α, β and δ is 0 to 1, and meets constraint condition alpha+beta+δ=1, preferably, and α=0.4, β=0.3, δ=0.3; Be judged as lying when the probability data Rate that lies reaches 60.
Data memory module 13 is for storing the data from video acquisition module 11 and module 12 of detecting a lie.
Network transmitting unit 14 is for being transferred to client terminal 15 by the data of the data of video acquisition module 11, module of detecting a lie 12 and the data of data memory module 13.
Client terminal 15 for showing the data from video acquisition module 11 and module 12 of detecting a lie, and for showing and downloading the data from data memory module 13, is inquired about and downloading data for user.
Particularly, client terminal 15 is smart mobile phone, computing machine or PAD.
The visual behaviour characteristic sum physiological parameter feature of people combines with psychologic principle by lie detection system of the present invention, improve accuracy and the reliability of detection, and the method has contactless feature, avoid the lie detection system of conventional contact easily by the shortcoming of watching out for.
But, those of ordinary skill in the art will be appreciated that, above embodiment is only used to the present invention is described, and be not used as limitation of the invention, as long as in spirit of the present invention, all will drop in Claims scope of the present invention the change of the above embodiment, modification.
Claims (3)
1. based on a lie detecting method for video, it is characterized in that, comprising:
Visual behaviour feature according to video images detection measurand:
A, in described video image, identified the little trick of described measurand by algorithm for pattern recognition, and calculate the frequency that little trick occurs, this frequency is set to A;
B, the head detecting described measurand, hand and leg rock information: in described video image, be partitioned into head, hand and leg area, respectively feature point detection carried out to each region; In continuous print frame of video, unique point is followed the tracks of; Calculate the motion vector of each unique point, use iir filter to carry out time-domain filtering to described motion vector, what obtain each region rocks information, is set to B, and formula is
b (n) is the unique point motion vector after the n-th frame calculates, and λ is weight coefficient;
Physiological parameter feature according to video images detection measurand: carry out Face datection and human eye location, extract the region of below eyes as area-of-interest; The RGB passage of described area-of-interest is split, gets the data of the G passage of multi-frame video image, calculate its mean value, be designated as Avg
g, the data value of the G passage of each frame is deducted Avg
gobtain Value
facei (), i is frame number, to the Value of multiframe
facei () data carry out gaussian filtering process, Removing Random No, carry out independent component analysis to the data sequence after gaussian filtering process, finally carry out Fourier transform, get the maximum frequency of amplitude spectrum as hrv parameter, are set to C;
The probability data Rate that lies by following formulae discovery measurand:
Rate=αA+βB+δC
, α, β and δ are weight factor.
2. based on a lie detection system for video, it is characterized in that, comprising:
Video acquisition module, for gathering the video image of measurand, and by this transmission of video images to module and the data memory module of detecting a lie;
Detecting a lie module, for detecting described video image, obtain the probability data of lying of measurand, and probability data of this being lied sending to data storage cell; The described video image of described detection, the probability data of lying obtaining measurand comprises:
Visual behaviour feature according to video images detection measurand:
A, in described video image, identified the little trick of described measurand by algorithm for pattern recognition, and calculate the frequency that little trick occurs, this frequency is set to A;
B, the head detecting described measurand, hand and leg rock information: in described video image, be partitioned into head, hand and leg area, respectively feature point detection carried out to each region; In continuous print frame of video, unique point is followed the tracks of; Calculate the motion vector of each unique point, use iir filter to carry out time-domain filtering to described motion vector, what obtain each region rocks information, is set to B, and formula is
b (n) is the unique point motion vector after the n-th frame calculates, and λ is weight coefficient;
Physiological parameter feature according to video images detection measurand: carry out Face datection and human eye location, extract the region of below eyes as area-of-interest; The RGB passage of described area-of-interest is split, gets the data of the G passage of multi-frame video image, calculate its mean value, be designated as Avg
g, the data value of the G passage of each frame is deducted Avg
gobtain Value
facei (), i is frame number, to the Value of multiframe
facei () data carry out gaussian filtering process, Removing Random No, carry out independent component analysis to the data sequence after gaussian filtering process, finally carry out Fourier transform, get the maximum frequency of amplitude spectrum as hrv parameter, are set to C;
The probability data Rate that lies by following formulae discovery measurand:
Rate=αA+βB+δC
, α, β and δ are weight factor;
Data memory module, for storing the data from described video acquisition module and module of detecting a lie;
Network transmitting unit, for by the data of described video acquisition module, described in the detect a lie data of module and data of described data memory module be transferred to client terminal;
Client terminal, for showing the data from described video acquisition module and module of detecting a lie, and for showing and downloading the data from described data memory module.
3. a kind of lie detection system based on video according to claim 2, is characterized in that, described client terminal is smart mobile phone, computing machine or PAD.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510021412.8A CN104537361A (en) | 2015-01-15 | 2015-01-15 | Lie detection method and system based on video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510021412.8A CN104537361A (en) | 2015-01-15 | 2015-01-15 | Lie detection method and system based on video |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104537361A true CN104537361A (en) | 2015-04-22 |
Family
ID=52852881
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510021412.8A Pending CN104537361A (en) | 2015-01-15 | 2015-01-15 | Lie detection method and system based on video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104537361A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
CN106529453A (en) * | 2016-10-28 | 2017-03-22 | 深圳市唯特视科技有限公司 | Reinforcement patch and multi-tag learning combination-based expression lie test method |
CN107480577A (en) * | 2016-06-07 | 2017-12-15 | 深圳市珍爱网信息技术有限公司 | A kind of face sincerity recognition methods and device |
CN107625527A (en) * | 2016-07-19 | 2018-01-26 | 杭州海康威视数字技术股份有限公司 | A kind of lie detecting method and device |
CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
CN108632502A (en) * | 2017-03-17 | 2018-10-09 | 深圳开阳电子股份有限公司 | A kind of method and device of image sharpening |
CN109190556A (en) * | 2018-08-31 | 2019-01-11 | 法信公证云(厦门)科技有限公司 | A kind of notarization wish authenticity discrimination method |
WO2020128999A1 (en) | 2018-12-20 | 2020-06-25 | Cm Profiling Sàrl | System and method for reading and analysing behaviour including verbal, body language and facial expressions in order to determine a person's congruence |
CN111507124A (en) * | 2019-01-30 | 2020-08-07 | 北京入思技术有限公司 | Non-contact video lie detection method and system based on deep learning |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070270659A1 (en) * | 2006-05-03 | 2007-11-22 | Giegerich Gary D | Apparatus and Method for Remotely Detecting Deception |
CN102657521A (en) * | 2012-05-07 | 2012-09-12 | 复旦大学 | Full optical fiber heart rate measuring equipment |
US20130139258A1 (en) * | 2011-11-30 | 2013-05-30 | Elwha Llc | Deceptive indicia profile generation from communications interactions |
CN103181768A (en) * | 2011-12-29 | 2013-07-03 | 大连文森特软件科技有限公司 | Mobile phone facial recognition-based lie detection method |
-
2015
- 2015-01-15 CN CN201510021412.8A patent/CN104537361A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070270659A1 (en) * | 2006-05-03 | 2007-11-22 | Giegerich Gary D | Apparatus and Method for Remotely Detecting Deception |
US20130139258A1 (en) * | 2011-11-30 | 2013-05-30 | Elwha Llc | Deceptive indicia profile generation from communications interactions |
CN103181768A (en) * | 2011-12-29 | 2013-07-03 | 大连文森特软件科技有限公司 | Mobile phone facial recognition-based lie detection method |
CN102657521A (en) * | 2012-05-07 | 2012-09-12 | 复旦大学 | Full optical fiber heart rate measuring equipment |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
CN107480577A (en) * | 2016-06-07 | 2017-12-15 | 深圳市珍爱网信息技术有限公司 | A kind of face sincerity recognition methods and device |
CN107625527A (en) * | 2016-07-19 | 2018-01-26 | 杭州海康威视数字技术股份有限公司 | A kind of lie detecting method and device |
CN107625527B (en) * | 2016-07-19 | 2021-04-20 | 杭州海康威视数字技术股份有限公司 | Lie detection method and device |
CN106529453A (en) * | 2016-10-28 | 2017-03-22 | 深圳市唯特视科技有限公司 | Reinforcement patch and multi-tag learning combination-based expression lie test method |
CN108632502A (en) * | 2017-03-17 | 2018-10-09 | 深圳开阳电子股份有限公司 | A kind of method and device of image sharpening |
CN108632502B (en) * | 2017-03-17 | 2021-04-30 | 深圳开阳电子股份有限公司 | Image sharpening method and device |
CN107704834B (en) * | 2017-10-13 | 2021-03-30 | 深圳壹账通智能科技有限公司 | Micro-surface examination assisting method, device and storage medium |
CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
WO2019071903A1 (en) * | 2017-10-13 | 2019-04-18 | 深圳壹账通智能科技有限公司 | Auxiliary method, device and storage medium for micro-expression face examination |
CN109190556A (en) * | 2018-08-31 | 2019-01-11 | 法信公证云(厦门)科技有限公司 | A kind of notarization wish authenticity discrimination method |
WO2020128999A1 (en) | 2018-12-20 | 2020-06-25 | Cm Profiling Sàrl | System and method for reading and analysing behaviour including verbal, body language and facial expressions in order to determine a person's congruence |
CN111507124A (en) * | 2019-01-30 | 2020-08-07 | 北京入思技术有限公司 | Non-contact video lie detection method and system based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104537361A (en) | Lie detection method and system based on video | |
Plews et al. | Comparison of heart-rate-variability recording with smartphone photoplethysmography, polar H7 chest strap, and electrocardiography | |
KR101535432B1 (en) | Contents valuation system and contents valuating method using the system | |
CN113420624B (en) | Non-contact fatigue detection method and system | |
CN104054038B (en) | Individual identification device and individual discrimination method | |
Huang et al. | Your glasses know your diet: Dietary monitoring using electromyography sensors | |
CN104049761B (en) | Eye electro-detection method and eye electric detection means | |
CN106659392A (en) | Unobtrusive skin tissue hydration determining device and related method | |
CN106137130B (en) | A kind of sleep period recognition methods based on audio processing | |
CN110072438A (en) | Use thermal sensation and visible light wear-type phase machine testing physiological responses | |
US20120083675A1 (en) | Measuring affective data for web-enabled applications | |
CN106999062A (en) | The method that heart information is extracted based on human body fine motion | |
CN103070682B (en) | Extraction method and extraction device for direction of eye movement based on electro-oculogram signals | |
CN108898079A (en) | A kind of monitoring method and device, storage medium, camera terminal | |
CN108882853A (en) | Measurement physiological parameter is triggered in time using visual context | |
CN109008964A (en) | A kind of method and device that physiological signal extracts | |
Ohtsuki et al. | Biometrie authentication using hand movement information from wrist-worn PPG sensors | |
JP6344254B2 (en) | Sleepiness detection device | |
US10631727B2 (en) | Method and system for detecting time domain cardiac parameters by using pupillary response | |
CN104793743A (en) | Virtual social contact system and control method thereof | |
JP2022042304A (en) | Stress estimation device, method, and program | |
KR102608633B1 (en) | Electronic device and control method thereof | |
Qin et al. | Consumer Wi‐Fi device based action quality recognition: An illustrative example of seated dumbbell press action | |
Poli et al. | Identification issues associated with the use of wearable accelerometers in lifelogging | |
Zhang et al. | A hybrid emotion recognition on android smart phones |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150422 |
|
WD01 | Invention patent application deemed withdrawn after publication |