CN107122704A - A kind of gait recognition method based on motion sensor - Google Patents
A kind of gait recognition method based on motion sensor Download PDFInfo
- Publication number
- CN107122704A CN107122704A CN201710155546.8A CN201710155546A CN107122704A CN 107122704 A CN107122704 A CN 107122704A CN 201710155546 A CN201710155546 A CN 201710155546A CN 107122704 A CN107122704 A CN 107122704A
- Authority
- CN
- China
- Prior art keywords
- gait
- mrow
- data
- candidate
- matching
- 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
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of gait recognition method based on motion sensor, comprise the following steps：Obtained by motion sensor collection and wear the gait data that user produces in the process of walking；Gait cycle estimation is carried out to gait data, positional dissection is carried out to gait data, the characteristics extraction of gait data is realized；The matching for continuing length and time span by the rising edge of gait data eigenvalue graph is compared, the candidate that matching degree is higher than decision threshold is filtered out from matching library, gait data characteristic value is carried out error intergal and obtain matching degree to each candidate to be identified with the gait data after the Fourier transformation of each candidate to be identified respectively in frequency domain, the maximum candidate of matching degree is regarded as into identities match success.Identification of this method to user identity is the gait feature based on people, is more difficult to be copied compared with the conventional arts such as fingerprint recognition, security is higher, and verification process is completed in user walks naturally, and usage experience is more smooth.
Description
Technical field
The present invention relates to the technical field of human-body biological identification, and in particular to a kind of Gait Recognition based on motion sensor
Method.
Background technology
The world today, information technology innovation is maked rapid progress, with digitlization, networking, the intelligent informationization wave being characterized
Tide is surging forward.Wearable device has come into the life of people, on the carry-on object of people, is integrated with intelligent chip etc. and sets
It is standby, the physiology and use habit related data of user can be collected, and the record of custom, experience can be realized by means such as networks
Improvement, the extension of function etc..But while rapid development of information technology, also the personal data safety to user brings wind
Danger, this causes personal data safety and equipment ease of use to there is contradiction to a certain extent.
Currently the research to Gait Recognition, is substantially based on machine vision and deep learning, it is necessary to while have multiple take the photograph
Data analysis is carried out as head obtains gait video, the cost of Gait Recognition realization can be so significantly greatly increased.At present, it would be highly desirable to propose one
Kind cost of implementation is relatively low, and amount of calculation is small, and ordinary terminal just can be realized, the wider gait recognition method of application.
The content of the invention
The invention aims to solve drawbacks described above of the prior art, there is provided a kind of step based on motion sensor
State recognition methods, the gait recognition method is believed using the gait of the motion sensor collection wearer on pin, shank, or thigh
Breath, the mobile phone that these sensors include but is not limited in pocket, intelligent shoe moves pin ring.Then handled by low-power consumption
The purpose for having reached checking wearer identity is compared with the data that are collected in advance in database after device analysis.
The purpose of the present invention can be reached by adopting the following technical scheme that：
A kind of gait recognition method based on motion sensor, the gait recognition method comprises the following steps：
S1, by motion sensor collection obtain wear the gait data that user produces in the process of walking；
S2, to gait data carry out gait cycle estimation, then gait data is determined by the gait cycle of estimation
Position cutting, realizes the characteristics extraction of gait data；
S3, the matching for continuing length and time span by the rising edge of gait data eigenvalue graph are compared, from matching
Storehouse filters out the candidate that matching degree is higher than decision threshold, and gait data characteristic value is to be identified with each respectively in frequency domain
Gait data after the Fourier transformation of candidate carries out error intergal and obtains the matching to each candidate to be identified
Degree, identities match success is regarded as by the maximum candidate of matching degree.
Further, the step S2 includes：
S201, gait data identification carried out by different cycle Algorithm for gait recognition, the cycle of calculating evaluated,
And confidence level is returned to, the gait cycle value estimated using confidence level highest cycle Algorithm for gait recognition；
S202, the data of each step are accurately positioned and cut according to the gait cycle value of estimation individually extract
It is used as characteristic value.
Further, the step S3 includes：
S301, carry out rising edge to gait data eigenvalue graph and continue the matching of length and time span comparing, from
Go out the candidate that matching degree is higher than decision threshold with storehouse preliminary screening first；
S302, gait data of the candidate in matching library is compressed or stretched, realize that gait cycle is standardized,
Gait data eigenvalue graph after being standardized to gait cycle carries out Fourier transformation, by the unconspicuous data of feature in time domain
It is mapped on frequency domain, by gait data characteristic value after the frequency domain respectively Fourier transformation of the candidate to be identified with each
Gait data carry out error intergal and obtain matching degree to each candidate to be identified, by the candidate that matching degree is maximum
Regard as identities match success.
Further, the gait cycle is standardized as 400 points, and the gait discrete data obtained from matching library is connected
Continuousization, then the gait data of serialization is separated by 400 points, obtains best discrete of correlation between each consecutive points
The formula of data, wherein data compression or stretching conversion is as follows：
Wherein XIThe i-th point of data after representation transformation, YIThe i-th point of original gait data is represented, PER is original
The cycle of gait data, INT () is bracket function.
Further, the calculation formula of the matching degree is as follows：
Wherein, s (n) is gait data to be identified, and c (n) is candidate's gait data.
Further, the motion sensor is the wearable smart machine being worn on pin, shank, or thigh, wherein,
The gait data is to wear the acceleration information that user produces in the process of walking.
Further, the matching library is set up in advance, the gait data for the user that is stored with the matching library, can be automatic
The gait data of unwritten user is identified, and is automatically stored in matching library.
The present invention has the following advantages and effect relative to prior art：
1st, simple, convenient popularization is realized, it is with low cost, it can be assembled in theory existing all with acceleration sensing
On the smart machine of device.
2nd, easy to use, identification of the present invention to people's identity is the gait feature based on people, and the process of checking can make
User completes during walking naturally, so usage experience is more smooth.
3rd, security is higher, and what the present invention was gathered is gait data, is more difficult to be imitated compared with the conventional arts such as fingerprint recognition
Make.
4th, compared with other Gait Recognition schemes based on camera, cost of implementation of the invention is lower, and amount of calculation is small, should
It is more extensive with scope.
Brief description of the drawings
Fig. 1 is the process step figure of the gait recognition method disclosed by the invention based on motion sensor.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Embodiment
Present embodiment discloses a kind of gait recognition method based on motion sensor, this method is small using pin is worn on
Wearable smart machine (mobile phone included but is not limited in pocket, intelligent shoe, motion pin ring) on leg, or thigh, is adopted
Collect the gait information of wearer, compared after then being analyzed by low power processor with the data that are collected in advance in database
Checking wearer identity is reached.
When user wears intelligent wearable device walking, the step disclosed by the invention based on motion sensor is utilized
State recognition methods just can voluntarily collect the gait information of user and confirm whether wearer is holder in due course.Entirely recognized
Journey does not need the participation of user, therefore very convenient.
As shown in Figure 1, the gait recognition method based on motion sensor disclosed in the present embodiment comprises the following steps：
S1, by motion sensor collection obtain wear the gait data that user produces in the process of walking, wherein, gait
Data are to wear the acceleration information that user produces in the process of walking, wherein, motion sensor is to be worn on pin, shank, or
Wearable smart machine on thigh, the including but not limited to mobile phone in pocket, intelligent shoe move pin ring.
S2, to gait data carry out gait cycle estimation, then gait data is determined by the gait cycle of estimation
Position cutting, realizes the characteristics extraction of gait data；
In embodiment, the step is specifically included：
S201, gait data identification carried out by different cycle Algorithm for gait recognition, the cycle of calculating evaluated,
And confidence level is returned to, the gait cycle value estimated using confidence level highest cycle Algorithm for gait recognition.
S202, the data of each step are accurately positioned according to the gait cycle value of estimation and cut individually extract conduct
Characteristic value.
The cycle size that the step is estimated before, the data of each step are accurately positioned and are segmented single after cutting
Solely extract, deeper data processing is laid a solid foundation after being.
Meanwhile, during segmentation, the periodicity power to data is analyzed, if periodically unobvious, that
This segment data will be interpreted as to be wrong data and abandon, to save the computing resource of preciousness.
S3, the matching for continuing length and time span by the rising edge of gait data eigenvalue graph are compared, from matching
Storehouse filters out the candidate that matching degree is higher than decision threshold, and gait data characteristic value is to be identified with each respectively in frequency domain
Gait data after the Fourier transformation of candidate carries out error intergal and obtains the matching to each candidate to be identified
Degree, identities match success is regarded as by the maximum candidate of matching degree.
Wherein, matching library is set up in advance, and be stored with user's gait data in the matching library, and can automatically identify does not have
The gait data of the user of record, and be automatically stored in matching library.
Therefore, matching library in the gait data of the new stranger of typing without individually progress, can identification process
There is no the user of typing in middle discovery database and record automatically, this greatly facilitates the collection of data.
Appraisement system is using double-deck evaluation structure in the matching step.First layer is substantially carried out rough ratio when matching
Compared with, it would be possible to correct people picks out, and incoming matches next time.Due to first time, the amount of calculation of matching is smaller, therefore can be with
It is effective to save computing resource.Second of matching accurately judges that candidate to be evaluated passes through with each using accurate matching
The matching degree of the people of first round screening.Matching degree highest that personal accomplishment recognition result is chosen more afterwards.
Step S3 detailed processes are as follows：
S301, carry out rising edge to gait data eigenvalue graph and continue the matching of length and time span comparing, from
Go out the candidate that matching degree is higher than decision threshold with storehouse preliminary screening first；
First layer recognizer:Curve rising edge continues the comparison of length and time span.
The data and curves of substantial amounts of different people are obtained by testing, are found after analysis, the curve of different people is specific
Position have more obvious ascendant trend, and keep this trend within a certain period of time.And found after further contrasting, no
With the curve rising edge of people continuity length and time span be also with more apparent difference, therefore can using this it is specific carry out compared with
Rough authentication.
S302, gait data of the candidate in matching library is compressed or stretched, realize that gait cycle is standardized,
Gait data eigenvalue graph after being standardized to gait cycle carries out Fourier transformation, by the unconspicuous data of feature in time domain
It is mapped on frequency domain, by gait data characteristic value after the frequency domain respectively Fourier transformation of the candidate to be identified with each
Gait data carry out error intergal and obtain matching degree to each candidate to be identified, by the candidate that matching degree is maximum
Regard as identities match success.
Second layer recognizer:The extraction of indicatrix and compare.
In view of being just same person, data cycle of different time typing may somewhat difference.At this moment
Data compression or stretching are employed, a cycle is reached accurate 400 points.By obtained discrete data serialization, then will
The data of serialization are separated by 400, obtain the best discrete data of correlation between each consecutive points.Data compression is converted
Core algorithm part it is as follows
Wherein XIThe i-th point of gait data after representation transformation, YIThe i-th point of original gait data is represented, PER is
The cycle of initial data, INT () is bracket function.The initial data that cycle is PER can be transformed to by this formula by week
Phase is fixed as 400 normal data, so can conveniently compare.
Eigenvalue graph after being standardized to gait cycle carries out the Fourier transformation that sample frequency is 256 points, by when
The unconspicuous data of feature are mapped on frequency domain on domain, make its characteristic value is more obvious to be easy to compare.
The gait data after the Fourier transformation of the candidate to be identified with each carries out error intergal respectively.So as to
Obtain the matching degree to each candidate to be identified.Ideally matched when sample rate interval dx is infinitely small to be obtained
Spend formula as follows：
But in actual calculating process, such precision cannot be reached.Therefore approximate formula can be used：
Wherein, s (n) is gait data to be identified, and c (n) is candidate's gait data, and the maximum candidate of matching degree is recognized
It is set to identities match success, i.e., the maximum candidate of the value of matching degree is regarded as into identities match success.
In summary, a kind of gait recognition method based on motion sensor disclosed in the present embodiment, this method utilizes pendant
The wearable smart machine being worn on pin, shank, or thigh gathers the gait information of wearer, then passes through low power processor
It is compared after analysis with the data that are collected in advance in database and has reached checking wearer identity.This method realization is simple,
Convenient popularization, it is with low cost, it can be assembled in theory on existing all smart machines with acceleration transducer.Together
When, the present invention is the gait feature based on people to the identification of people's identity, the mistake that the process of checking can naturally walk in user
Completed in journey, so usage experience is more smooth.Moreover, security of the present invention is higher, collection is gait data, is known with fingerprint
Not Deng conventional art compared to being more difficult to be copied.
Above-described embodiment is preferably embodiment, but embodiments of the present invention are not by above-described embodiment of the invention
Limitation, other any Spirit Essences without departing from the present invention and the change made under principle, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (7)
1. a kind of gait recognition method based on motion sensor, it is characterised in that the gait recognition method includes following step
Suddenly：
S1, by motion sensor collection obtain wear the gait data that user produces in the process of walking；
S2, gait cycle estimation is carried out to gait data, then carrying out positioning to gait data by the gait cycle of estimation cuts
Cut, realize the characteristics extraction of gait data；
S3, the matching for continuing length and time span by the rising edge of gait data eigenvalue graph are compared, from matching library sieve
The candidate that matching degree is higher than decision threshold is selected, by gait data characteristic value in the frequency domain candidate to be identified with each respectively
Gait data progress error intergal after the Fourier transformation of people obtains the matching degree to each candidate to be identified, will
The maximum candidate of matching degree regards as identities match success.
2. a kind of gait recognition method based on motion sensor according to claim 1, it is characterised in that the step
S2 includes：
S201, gait data identification carried out by different cycle Algorithm for gait recognition, the cycle of calculating is evaluated, and
Confidence level is returned to, the gait cycle value estimated using confidence level highest cycle Algorithm for gait recognition；
S202, the data of each step are accurately positioned and cut according to the gait cycle value of estimation individually extract conduct
Characteristic value.
3. a kind of gait recognition method based on motion sensor according to claim 1, it is characterised in that the step
S3 includes：
S301, the matching to gait data eigenvalue graph progress rising edge continuity length and time span are compared, from matching library
Preliminary screening goes out the candidate that matching degree is higher than decision threshold first；
S302, gait data of the candidate in matching library is compressed or stretched, realize that gait cycle is standardized, to step
Gait data eigenvalue graph after state cycle criterion carries out Fourier transformation, and the unconspicuous data of feature in time domain are mapped
Onto frequency domain, by step of the gait data characteristic value after the frequency domain respectively Fourier transformation of the candidate to be identified with each
State data progress error intergal obtains the matching degree to each candidate to be identified, and the maximum candidate of matching degree is assert
For identities match success.
4. a kind of gait recognition method based on motion sensor according to claim 3, it is characterised in that the gait
Cycle criterion turns to 400 points, by the gait discrete data serialization obtained from matching library, then by the gait data of serialization
Separated by 400 points, obtain the best discrete data of correlation between each consecutive points, wherein data compression or stretching
The formula of conversion is as follows：
<mrow>
<msub>
<mi>X</mi>
<mi>I</mi>
</msub>
<mo>=</mo>
<msub>
<mi>Y</mi>
<mrow>
<mi>I</mi>
<mi>N</mi>
<mi>T</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>P</mi>
<mi>E</mi>
<mi>R</mi>
<mo>/</mo>
<mn>400</mn>
<mo>*</mo>
<mi>I</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</msub>
<mo>*</mo>
<mrow>
<mo>(</mo>
<mrow>
<mfrac>
<mrow>
<mi>P</mi>
<mi>E</mi>
<mi>R</mi>
</mrow>
<mn>400</mn>
</mfrac>
<mo>*</mo>
<mi>I</mi>
<mo>-</mo>
<mi>I</mi>
<mi>N</mi>
<mi>T</mi>
<mrow>
<mo>(</mo>
<mrow>
<mfrac>
<mrow>
<mi>P</mi>
<mi>E</mi>
<mi>R</mi>
</mrow>
<mn>400</mn>
</mfrac>
<mo>*</mo>
<mi>I</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>Y</mi>
<mrow>
<mfrac>
<mrow>
<mi>P</mi>
<mi>E</mi>
<mi>R</mi>
</mrow>
<mn>400</mn>
</mfrac>
<mo>*</mo>
<mi>I</mi>
</mrow>
</msub>
<mo>*</mo>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mfrac>
<mrow>
<mi>P</mi>
<mi>E</mi>
<mi>R</mi>
</mrow>
<mn>400</mn>
</mfrac>
<mo>*</mo>
<mi>I</mi>
<mo>+</mo>
<mi>I</mi>
<mi>N</mi>
<mi>T</mi>
<mrow>
<mo>(</mo>
<mrow>
<mfrac>
<mrow>
<mi>P</mi>
<mi>E</mi>
<mi>R</mi>
</mrow>
<mn>400</mn>
</mfrac>
<mo>*</mo>
<mi>I</mi>
</mrow>
<mo>)</mo>
</mrow>
<mo>,</mo>
</mrow>
Wherein XIThe i-th point of data after representation transformation, YIThe i-th point of original gait data is represented, PER is original gait
The cycle of data, INT () is bracket function.
5. a kind of gait recognition method based on motion sensor according to claim 4, it is characterised in that the matching
The calculation formula of degree is as follows：
Wherein, s (n) is gait data to be identified, and c (n) is candidate's gait data.
6. according to a kind of any described gait recognition method based on motion sensor of claim 1 to 5, it is characterised in that
The motion sensor is the wearable smart machine being worn on pin, shank, or thigh, wherein, the gait data is pendant
Wear the acceleration information that user produces in the process of walking.
7. according to a kind of any described gait recognition method based on motion sensor of claim 1 to 5, it is characterised in that
The matching library is set up in advance, the gait data for the user that is stored with the matching library, can be automatically identified unwritten
The gait data of user, and be automatically stored in matching library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710155546.8A CN107122704A (en) | 2017-03-16 | 2017-03-16 | A kind of gait recognition method based on motion sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710155546.8A CN107122704A (en) | 2017-03-16 | 2017-03-16 | A kind of gait recognition method based on motion sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107122704A true CN107122704A (en) | 2017-09-01 |
Family
ID=59718014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710155546.8A Pending CN107122704A (en) | 2017-03-16 | 2017-03-16 | A kind of gait recognition method based on motion sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107122704A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107831907A (en) * | 2017-12-07 | 2018-03-23 | 深圳先进技术研究院 | Identity identifying method and device based on Gait Recognition |
| CN108710788A (en) * | 2018-05-22 | 2018-10-26 | 上海众人网络安全技术有限公司 | A kind of safety certifying method, device, terminal and storage medium |
| CN108932504A (en) * | 2018-07-24 | 2018-12-04 | 中国科学院深圳先进技术研究院 | Identity identifying method, device, electronic equipment and storage medium |
| CN109035513A (en) * | 2018-07-20 | 2018-12-18 | 中新国际电子有限公司 | A kind of intelligent door lock method for unlocking, device, system and readable storage medium storing program for executing |
| CN109286499A (en) * | 2018-09-21 | 2019-01-29 | 武汉大学 | A kind of authentication method on the scene of Behavior-based control feature |
| CN109447128A (en) * | 2018-09-29 | 2019-03-08 | 中国科学院自动化研究所 | Walking based on micro- inertial technology and the classification of motions method and system that remains where one is |
| CN109492362A (en) * | 2017-09-13 | 2019-03-19 | 腾讯科技（深圳）有限公司 | Verification method, device, mobile terminal and the computer storage medium of sensitive operation |
| CN110263514A (en) * | 2019-01-31 | 2019-09-20 | 南京邮电大学 | Personal identification method based on human body behavior in a kind of Internet of Things wearable device |
| CN110537921A (en) * | 2019-08-28 | 2019-12-06 | 华南理工大学 | Portable gait multi-sensing data acquisition system |
| CN110619253A (en) * | 2018-06-19 | 2019-12-27 | 北京京东尚科信息技术有限公司 | Identity recognition method and device |
| CN113626469A (en) * | 2020-05-08 | 2021-11-09 | 中国电信股份有限公司 | Internet of things equipment matching method and device |
| CN114012742A (en) * | 2022-01-05 | 2022-02-08 | 北京动思创新科技有限公司 | Control system of hip joint power assisting device |
| CN117059227A (en) * | 2023-10-13 | 2023-11-14 | 华南师范大学 | Motion monitoring method and device based on gait data and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101695445B (en) * | 2009-10-29 | 2011-11-23 | 浙江大学 | Acceleration transducer-based gait identification method |
| US20140066816A1 (en) * | 2008-12-07 | 2014-03-06 | Apdm, Inc | Method, apparatus, and system for characterizing gait |
-
2017
- 2017-03-16 CN CN201710155546.8A patent/CN107122704A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140066816A1 (en) * | 2008-12-07 | 2014-03-06 | Apdm, Inc | Method, apparatus, and system for characterizing gait |
| CN101695445B (en) * | 2009-10-29 | 2011-11-23 | 浙江大学 | Acceleration transducer-based gait identification method |
Non-Patent Citations (2)
| Title |
|---|
| 周海明: "一种基于形心距离序列的频域的曲线描述和匹配方法", 《中国优秀硕士学位论文全文数据库》 * |
| 王奎: "一种基于特征曲线匹配的快速步态识别方法研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492362A (en) * | 2017-09-13 | 2019-03-19 | 腾讯科技（深圳）有限公司 | Verification method, device, mobile terminal and the computer storage medium of sensitive operation |
| CN107831907A (en) * | 2017-12-07 | 2018-03-23 | 深圳先进技术研究院 | Identity identifying method and device based on Gait Recognition |
| WO2019109433A1 (en) * | 2017-12-07 | 2019-06-13 | 深圳先进技术研究院 | Identity authentication method and device based on gait recognition |
| CN108710788A (en) * | 2018-05-22 | 2018-10-26 | 上海众人网络安全技术有限公司 | A kind of safety certifying method, device, terminal and storage medium |
| CN110619253A (en) * | 2018-06-19 | 2019-12-27 | 北京京东尚科信息技术有限公司 | Identity recognition method and device |
| CN110619253B (en) * | 2018-06-19 | 2022-06-07 | 北京京东尚科信息技术有限公司 | Identity recognition method and device |
| CN109035513A (en) * | 2018-07-20 | 2018-12-18 | 中新国际电子有限公司 | A kind of intelligent door lock method for unlocking, device, system and readable storage medium storing program for executing |
| CN108932504A (en) * | 2018-07-24 | 2018-12-04 | 中国科学院深圳先进技术研究院 | Identity identifying method, device, electronic equipment and storage medium |
| CN109286499A (en) * | 2018-09-21 | 2019-01-29 | 武汉大学 | A kind of authentication method on the scene of Behavior-based control feature |
| CN109286499B (en) * | 2018-09-21 | 2020-08-07 | 武汉大学 | Behavior feature-based presence authentication method |
| CN109447128A (en) * | 2018-09-29 | 2019-03-08 | 中国科学院自动化研究所 | Walking based on micro- inertial technology and the classification of motions method and system that remains where one is |
| CN110263514B (en) * | 2019-01-31 | 2022-03-15 | 南京邮电大学 | Identity recognition method based on human body behaviors in wearable device of Internet of things |
| CN110263514A (en) * | 2019-01-31 | 2019-09-20 | 南京邮电大学 | Personal identification method based on human body behavior in a kind of Internet of Things wearable device |
| CN110537921A (en) * | 2019-08-28 | 2019-12-06 | 华南理工大学 | Portable gait multi-sensing data acquisition system |
| CN113626469A (en) * | 2020-05-08 | 2021-11-09 | 中国电信股份有限公司 | Internet of things equipment matching method and device |
| CN113626469B (en) * | 2020-05-08 | 2023-10-13 | 中国电信股份有限公司 | Internet of things equipment matching method and device |
| CN114012742A (en) * | 2022-01-05 | 2022-02-08 | 北京动思创新科技有限公司 | Control system of hip joint power assisting device |
| CN114012742B (en) * | 2022-01-05 | 2022-03-29 | 北京动思创新科技有限公司 | Control system of hip joint power assisting device |
| CN117059227A (en) * | 2023-10-13 | 2023-11-14 | 华南师范大学 | Motion monitoring method and device based on gait data and electronic equipment |
| CN117059227B (en) * | 2023-10-13 | 2024-01-30 | 华南师范大学 | Motion monitoring method and device based on gait data and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107122704A (en) | A kind of gait recognition method based on motion sensor | |
| CN101695445B (en) | Acceleration transducer-based gait identification method | |
| Ailisto et al. | Identifying people from gait pattern with accelerometers | |
| WO2018040757A1 (en) | Wearable device and method of using same to monitor motion state | |
| CN101558996B (en) | Gait recognition method based on orthogonal projection three-dimensional reconstruction of human motion structure | |
| CN102542281B (en) | Non-contact biometric feature identification method and system | |
| CN105868613A (en) | Biometric feature recognition method, biometric feature recognition device and mobile terminal | |
| WO2019192235A1 (en) | User identity authentication method and system based on mobile device | |
| CN106899968A (en) | A kind of active noncontact identity identifying method based on WiFi channel condition informations | |
| CN107016346A (en) | gait identification method and system | |
| CN103970271A (en) | Daily activity identifying method with exercising and physiology sensing data fused | |
| CN111178155B (en) | Gait feature extraction and gait recognition method based on inertial sensor | |
| CN1152340C (en) | Fingerprint image enhancement method based on knowledge | |
| CN101246543A (en) | Examiner identity appraising system based on bionic and biological characteristic recognition | |
| CN110730473B (en) | WiFi activity recognition-oriented signal feature extraction method | |
| CN108171278A (en) | A kind of recognizing model of movement method and system based on training data | |
| CN106503691A (en) | A kind of identity mask method of face picture and device | |
| Oshin et al. | ERSP: An energy-efficient real-time smartphone pedometer | |
| CN108932504A (en) | Identity identifying method, device, electronic equipment and storage medium | |
| CN111262637B (en) | Human body behavior identification method based on Wi-Fi channel state information CSI | |
| CN103020636B (en) | A kind of upper method of action recognition downstairs based on 3 d human motion energy consumption instrument | |
| CN107169334B (en) | The user authen method based on straight punch motion detection for hand wearable device | |
| Cola et al. | Personalized gait detection using a wrist-worn accelerometer | |
| Bi et al. | SmartGe: identifying pen-holding gesture with smartwatch | |
| CN107103219A (en) | Wearable device user identification method and system based on gait |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170901 |