CN103377366A - Gait recognition method and system - Google Patents
Gait recognition method and system Download PDFInfo
- Publication number
- CN103377366A CN103377366A CN2012101260007A CN201210126000A CN103377366A CN 103377366 A CN103377366 A CN 103377366A CN 2012101260007 A CN2012101260007 A CN 2012101260007A CN 201210126000 A CN201210126000 A CN 201210126000A CN 103377366 A CN103377366 A CN 103377366A
- Authority
- CN
- China
- Prior art keywords
- gait
- video sequence
- recognition
- algorithm
- module
- 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
Images
Abstract
The invention discloses a gait recognition method and system. The method comprises the steps that a monitoring terminal collects gaits of a person in real time to form a gait video sequence, and preprocessing is carried out on the obtained gait video sequence; the monitoring terminal sends the gait video sequence to a cloud server through a network; the cloud server carries out processing on the received gait video sequence based on a preset gait recognition algorithm to extract gait characteristics, and the extracted gait characteristics have the identical pattern with gait data prestored in a database; the cloud server carries out comparison and recognition on the extracted gait characteristics and the gait data in the database and sends a user name corresponding to the corresponding gait data in the database to a cloud terminal if the extracted gait characteristics match the gait data in the database; the cloud terminal receives and displays the corresponding user name. According to the technical scheme, gait recognition can be carried out accurately in real time by the utilization of the strong computing power of the cloud server, therefore, the cost of the monitoring terminal is greatly reduced, and the popularization of the gait recognition is further promoted.
Description
Technical field
The present invention relates to the biometrics identification technology field, relate in particular to a kind of gait recognition method and system.
Background technology
Biometrics identification technology is a kind of method of firm individual identity, it comprises the multiple recognition technologies such as recognition of face, fingerprint recognition, iris recognition and Gait Recognition by high-tech information monitoring technology, identification next day of utilizing the intrinsic physiology of kicking a player or behavioural characteristic to carry out.Because everyone biological characteristic has uniqueness and ubiquity, be difficult for forging and personation, therefore utilize biometrics identification technology to carry out authentication and have the advantages such as safe, reliable, correct.The first generation biometrics identification technologies such as now widely used recognition of face, fingerprint recognition, iris recognition, mostly need the cooperation of detected object, sometimes need detected object to finish specific action and just can identify, the unavoidable like this passivity that can cause some authentication.
Gait Recognition is intended to its identity of gesture recognition of walking according to people, as second generation biometrics identification technology, Gait Recognition is unique biometrics identification technology that can carry out authentication in remote situation, has good concealment, to less demanding, the remote noncontact of video quality and be difficult to the advantage such as camouflage.Even in the situation that other biometrics identification technology all lost efficacy, Gait Recognition still can be brought into play powerful effect.Based on above-mentioned advantage, Gait Recognition receives much concern in recent years, has broad application prospects in the vision monitoring field.Yet, basically all be on the terminals such as single PC, sequence of pictures to be processed to the research of Gait Recognition at present, and gait that may a more than people in the sequence of pictures, if the gait video sequence that a plurality of cameras are obtained carries out Gait Recognition, to be very high to the requirement of terminal so, this will limit the popularization and application of Gait Recognition.
Summary of the invention
The technical problem to be solved in the present invention is, the defective high to the configuration requirement of terminal when carrying out Gait Recognition for the above-mentioned gait video sequence in that a plurality of cameras are obtained of prior art provides a kind of gait recognition method low to the configuration requirement of terminal.
The technical solution adopted for the present invention to solve the technical problems is: construct a kind of gait recognition method, comprising:
S1. monitor terminal Real-time Collection people's gait to be forming the gait video sequence, and the gait video sequence that obtains is carried out pre-service;
S2. monitor terminal is sent to Cloud Server with pretreated gait video sequence by network;
S3. Cloud Server receives pretreated gait video sequence, and by default Algorithm for gait recognition the gait video sequence that receives is processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database;
S4. Cloud Server compares identification with the gait feature that extracts and the gait data in the database, if coupling then is sent to the cloud terminal with the corresponding corresponding user name of gait data in the database;
S5. the cloud terminal receives and shows corresponding user name.
In gait recognition method of the present invention, described pre-service comprises denoising and profile extraction process.
In gait recognition method of the present invention, described step S3 comprises:
S31. Cloud Server receives pretreated gait video sequence;
S32. Cloud Server detects whether continuous whole of the gait video sequence receive, if, execution in step S35 then; If not, execution in step S33 then;
S33. Cloud Server requires monitor terminal again to send out pretreated gait video sequence described;
S34. monitor terminal resends described pretreated gait video sequence, then execution in step S32;
S35. Cloud Server processes to extract gait feature by default Algorithm for gait recognition to the gait video sequence that receives, and the gait feature that extracts has identical pattern with pre-stored gait data in database.
In gait recognition method of the present invention, default Algorithm for gait recognition is in following: the Algorithm for gait recognition of analyzing based on the two-dimentional Algorithm for gait recognition of pivot analysis, based on Statistical Shape, based on the Algorithm for gait recognition of space-time profile analysis, based on the Algorithm for gait recognition of model, based on the Method of Gait Feature Extraction of Hough conversion, based on the Algorithm for gait recognition of 3 D wavelet square theory.
In gait recognition method of the present invention, if monitor terminal is without the gait picture that collects the people, then to the signal of Cloud Server transmission without the gait video sequence.
The present invention also constructs a kind of Gait Recognition system, comprising: be arranged at least one monitor terminal, the Cloud Server that is arranged on far-end and the cloud terminal in monitoring place, and each monitor terminal comprises acquisition module, pretreatment module and the first sending module; Cloud Server comprises the second receiver module, extraction module, identification module and the second sending module; The cloud terminal comprises display module; Wherein,
Acquisition module is used for Real-time Collection people's gait to form the gait video sequence;
Pretreatment module is used for the gait video sequence that obtains is carried out pre-service;
The first sending module is used for pretreated gait video sequence is sent to Cloud Server by network;
The second receiver module is used for receiving pretreated gait video sequence;
Extraction module be used for by default Algorithm for gait recognition the gait video sequence that receives being processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database;
Identification module compares identification for the gait feature that will extract and the gait data of database;
The second sending module is used for when the gait data coupling of the gait feature that extracts and database the corresponding corresponding user name of gait data in the database being sent to the cloud terminal;
Display module is used for receiving and showing corresponding user name.
In Gait Recognition of the present invention system, described pre-service comprises denoising and profile extraction process.
In Gait Recognition of the present invention system, described Cloud Server also comprises detection module and retransmit module, and
Described detection module is for detection of the gait video sequence that receives continuous whole whether;
Described extraction module, be used for when detecting the gait video sequence continuous whole that receives, by default Algorithm for gait recognition the gait video sequence that receives is processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database;
Described retransmit module is used for detecting the gait video sequence that receives when discontinuous, requires monitor terminal again to send out pretreated gait video sequence described.
In Gait Recognition of the present invention system, default Algorithm for gait recognition is in following: the Algorithm for gait recognition of analyzing based on the two-dimentional Algorithm for gait recognition of pivot analysis, based on Statistical Shape, based on the Algorithm for gait recognition of space-time profile analysis, based on the Algorithm for gait recognition of model, based on the Method of Gait Feature Extraction of Hough conversion, based on the Algorithm for gait recognition of 3 D wavelet square theory.
In Gait Recognition of the present invention system, described the first sending module also is used at acquisition module when collecting people's gait picture, sends signal without the gait video sequence to Cloud Server.
Implement technical scheme of the present invention, because monitor terminal is only simply processed the gait video sequence that gathers, and the main calculating of Gait Recognition (extraction of gait feature) is finished in Cloud Server, utilize the Cloud Server powerful calculating ability can carry out in real time, exactly Gait Recognition, this will save the cost of monitor terminal greatly, and then promote popularizing of Gait Recognition.In addition, because monitor terminal had carried out simple processing before sending the gait video sequence to Cloud Server, can greatly reduce the size of gait video sequence, make things convenient for transmission.
Description of drawings
The invention will be further described below in conjunction with drawings and Examples, in the accompanying drawing:
Fig. 1 is the process flow diagram of gait recognition method embodiment one of the present invention;
Fig. 2 is the process flow diagram of step S3 preferred embodiment among Fig. 1;
Fig. 3 is the logical diagram of Gait Recognition system embodiment one of the present invention.
Embodiment
As shown in Figure 1, in the process flow diagram of gait recognition method embodiment one of the present invention, this gait recognition method comprises:
S1. monitor terminal Real-time Collection people's gait to be forming the gait video sequence, and the gait video sequence that obtains is carried out pre-service, and in this step, pre-service comprises that denoising and profile extraction process etc. are simple and processes;
S2. monitor terminal is sent to Cloud Server with pretreated gait video sequence by network;
S3. Cloud Server receives pretreated gait video sequence, and by default Algorithm for gait recognition the gait video sequence that receives is processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database, in this step, should be noted that, pre-stored user name and the gait data that a plurality of users are arranged of database, and the incidence relation of user name and gait data;
S4. Cloud Server compares identification with the gait feature that extracts and the gait data in the database, if coupling then is sent to the cloud terminal with the corresponding corresponding user name of gait data in the database;
S5. the cloud terminal receives and shows corresponding user name.
Implement this technical scheme, because monitor terminal has only carried out simple processing to the gait video sequence that gathers, and the main calculating of Gait Recognition (extraction of gait feature) is to finish in Cloud Server, utilize the Cloud Server powerful calculating ability can carry out in real time, exactly Gait Recognition, this will save the cost of monitor terminal greatly, and then promote popularizing of Gait Recognition.In addition, because monitor terminal had carried out simple processing before sending the gait video sequence, can greatly reduce the size of gait video sequence, make things convenient for transmission.
Fig. 2 is the process flow diagram of step S3 preferred embodiment among Fig. 1, and in this embodiment, step S3 comprises:
S31. Cloud Server receives pretreated gait video sequence;
S32. Cloud Server detects whether continuous whole of the gait video sequence receive, if, execution in step S35 then; If not, execution in step S33 then;
S33. Cloud Server requires monitor terminal again to send out pretreated gait video sequence described;
S34. monitor terminal resends described pretreated gait video sequence, then execution in step S32;
S35. Cloud Server processes to extract gait feature by default Algorithm for gait recognition to the gait video sequence that receives, and the gait feature that extracts has identical pattern with pre-stored gait data in database.
In the preferred embodiment, after receiving the gait video sequence, judge first whether continuous whole of gait video sequence, only when continuous whole, Cloud Server is just processed the gait video sequence that receives by default Algorithm for gait recognition, can improve like this significance arithmetic of Cloud Server.
In another preferred embodiment of the present invention, if personnel are not namely identified or monitor to monitor terminal without the gait picture that collects the people, this moment, then to the signal of Cloud Server transmission without the gait video sequence.
In another preferred embodiment of the present invention, mentioned default Algorithm for gait recognition is in following: the Algorithm for gait recognition of analyzing based on the two-dimentional Algorithm for gait recognition of pivot analysis, based on Statistical Shape, based on the Algorithm for gait recognition of space-time profile analysis, based on the Algorithm for gait recognition of model, based on the Method of Gait Feature Extraction of Hough conversion, based on the Algorithm for gait recognition of 3 D wavelet square theory.The below illustrates every kind of algorithm one by one:
1. based on the two-dimentional Algorithm for gait recognition of pivot analysis
In the two-dimentional Algorithm for gait recognition based on pivot analysis, for each gait video sequence, a kind of improved background subtraction technique is used for extracting people's space profiles.The edge of these profiles, by counterclockwise expand into a series of with respect to barycenter apart from template.These template characteristic are by training with the Principal Component Statistics analytical approach, thereby the track of changing pattern in feature space that draws the gait shape expressed.During identification, adopted temporal and spatial correlations matching process and regular based on the arest neighbors of normalization Euclidean distance, and introduced the fusion corresponding to individual's the physiological characteristics such as the bodily form, to be used for necessary gait classification verification.
2. the Algorithm for gait recognition of analyzing based on Statistical Shape
This algorithm derives from the viewpoint of " display model that can learn human body from the spatiotemporal mode of walking movement ".For each gait video sequence, the background subtraction process is used for extracting pedestrian's motion outline, and these profiles attitude in time changes in two-dimensional space by the corresponding plural number configuration (Complex Configuration) that is described as a sequence.Utilize Procrustes shape analysis method, from this sequence configuration, obtain the main outline model as the static appearance feature of human body.
3. based on the Algorithm for gait recognition of space-time profile analysis
This algorithm derives from the idea directly perceived of " the human body walking motion depends on the change of shape of profile along with the time to a great extent ".For each gait video sequence, background subtraction and profile correlation technique for detection of with the motion outline of tracking pedestrians, these the time two-dimensional contour shape that becomes be converted into corresponding one-dimensional distance signal, extract the low-dimensional gait feature by Feature Space Transformation simultaneously.Based on temporal and spatial correlations or normalization euclidean distance metric, and the pattern classification technology of standard is used for final identification.
4. based on the Algorithm for gait recognition of model
This algorithm derives from the thought of " the joint angles variation of walking movement is comprising abundant individual identification information ".At first, in conjunction with prioris such as manikin, motion model and kinematic constraints, utilize the Condensation algorithm to carry out pedestrian's tracking.Then, from tracking results, obtain the angle variation track in the main joint of human body.After these tracks process structures and the time normalization, be used for identification as behavioral characteristics.
5. based on the Method of Gait Feature Extraction of Hough conversion
This algorithm only carries out identification from the motion of shank.For each gait video sequence, detect Moving Objects with a kind of background subtraction algorithm based on the image chroma deviation.Through in the bianry image sequence of aftertreatment, utilize edge following algorithm to obtain object bounds, on the object bounds image, the straight line of topical application Hough change detection thigh and shank, thus obtain the pitch angle of thigh and shank.With the pitch angle sequence in the one-period, fit to 5 rank polynomial expressions with least square method, the product of the phase place that obtains after the Fourier expansion and amplitude, be defined as low-dimensional gait feature vector.
6. based on the Algorithm for gait recognition of 3 D wavelet square theory
This algorithm is theoretical based on the broad sense multiscale analysis, for different application images or signal library, obtains optimal wavelet and decomposes, and be combined with the 2-d wavelet square in body gait identification and use.Aspect the expression of three-dimensional body, as a kind of break-even description and the recognition methods of three-dimensional body, it is theoretical to have proposed the 3 D wavelet square.Compare with said method, it not only has translation scaling and rotation invariant, has also increased diametrically the characteristic of multiscale analysis.Can provide multi-level Feature Descriptor according to different needs, introduce simultaneously the Mallat algorithm of spherical harmonic function accelerating algorithm and small echo after, make the dual acceleration of having calculated of wavelet moment.
Fig. 3 is the logical diagram of Gait Recognition system embodiment one of the present invention, this Gait Recognition system comprises: be arranged at least one monitor terminal 10 (only showing among the figure) of monitoring the place, Cloud Server 20 and the cloud terminal 30 that is arranged on far-end, wherein, each monitor terminal 10 comprises acquisition module 11, pretreatment module 12 and the first sending module 13; Cloud Server 20 comprises the second receiver module 21, extraction module 22, identification module 23 and the second sending module 24; Cloud terminal 30 comprises display module 31.And acquisition module 11 is used for Real-time Collection people's gait to form the gait video sequence.Pretreatment module 12 is used for the gait video sequence that obtains is carried out pre-service, and this pre-service can comprise denoising and profile extraction process.The first sending module 13 is used for pretreated gait video sequence is sent to Cloud Server by network.The second receiver module 21 is used for receiving pretreated gait video sequence.Extraction module 22 is used for by default Algorithm for gait recognition the gait video sequence that receives being processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database.Identification module 23 compares identification for the gait feature that will extract and the gait data of database.The second sending module 24 is used for when the gait data coupling of the gait feature that extracts and database the corresponding corresponding user name of gait data in the database being sent to the cloud terminal.Display module 31 is used for receiving and showing corresponding user name.
In a preferred embodiment, Cloud Server 20 also comprises detection module and retransmit module, and this detection module is for detection of the gait video sequence that receives continuous whole whether; Extraction module 22 is used for when detecting the gait video sequence continuous whole that receives, by default Algorithm for gait recognition the gait video sequence that receives is processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database.This retransmit module is used for detecting the gait video sequence that receives when discontinuous, requires monitor terminal again to send out pretreated gait video sequence described.
In a further advantageous embodiment, extraction module 23 employed default Algorithm for gait recognitions can be in following one: the Algorithm for gait recognition of analyzing based on the two-dimentional Algorithm for gait recognition of pivot analysis, based on Statistical Shape, based on the Algorithm for gait recognition of space-time profile analysis, based on the Algorithm for gait recognition of model, based on the Method of Gait Feature Extraction of Hough conversion, based on the Algorithm for gait recognition of 3 D wavelet square theory.
In another preferred embodiment of the present invention, the first sending module also is used at acquisition module when collecting people's gait picture, sends signal without the gait video sequence to Cloud Server.
The above is the preferred embodiments of the present invention only, is not limited to the present invention, and for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., all should be included within the claim scope of the present invention.
Claims (10)
1. a gait recognition method is characterized in that, comprising:
S1. monitor terminal Real-time Collection people's gait to be forming the gait video sequence, and the gait video sequence that obtains is carried out pre-service;
S2. monitor terminal is sent to Cloud Server with pretreated gait video sequence by network;
S3. Cloud Server receives pretreated gait video sequence, and by default Algorithm for gait recognition the gait video sequence that receives is processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database;
S4. Cloud Server compares identification with the gait feature that extracts and the gait data in the database, if coupling then is sent to the cloud terminal with the corresponding corresponding user name of gait data in the database;
S5. the cloud terminal receives and shows corresponding user name.
2. gait recognition method according to claim 1 is characterized in that, described pre-service comprises denoising and profile extraction process.
3. gait recognition method according to claim 1 is characterized in that, described step S3 comprises:
S31. Cloud Server receives pretreated gait video sequence;
S32. Cloud Server detects whether continuous whole of the gait video sequence receive, if, execution in step S35 then; If not, execution in step S33 then;
S33. Cloud Server requires monitor terminal again to send out pretreated gait video sequence described;
S34. monitor terminal resends described pretreated gait video sequence, then execution in step S32;
S35. Cloud Server processes to extract gait feature by default Algorithm for gait recognition to the gait video sequence that receives, and the gait feature that extracts has identical pattern with pre-stored gait data in database.
4. gait recognition method according to claim 1, it is characterized in that default Algorithm for gait recognition is in following: the Algorithm for gait recognition of analyzing based on the two-dimentional Algorithm for gait recognition of pivot analysis, based on Statistical Shape, based on the Algorithm for gait recognition of space-time profile analysis, based on the Algorithm for gait recognition of model, based on the Method of Gait Feature Extraction of Hough conversion, based on the Algorithm for gait recognition of 3 D wavelet square theory.
5. gait recognition method according to claim 1 is characterized in that, if monitor terminal is without the gait picture that collects the people, then to the signal of Cloud Server transmission without the gait video sequence.
6. a Gait Recognition system is characterized in that, comprising: be arranged at least one monitor terminal, the Cloud Server that is arranged on far-end and the cloud terminal in monitoring place, and each monitor terminal comprises acquisition module, pretreatment module and the first sending module; Cloud Server comprises the second receiver module, extraction module, identification module and the second sending module; The cloud terminal comprises display module; Wherein,
Acquisition module is used for Real-time Collection people's gait to form the gait video sequence;
Pretreatment module is used for the gait video sequence that obtains is carried out pre-service;
The first sending module is used for pretreated gait video sequence is sent to Cloud Server by network;
The second receiver module is used for receiving pretreated gait video sequence;
Extraction module be used for by default Algorithm for gait recognition the gait video sequence that receives being processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database;
Identification module compares identification for the gait feature that will extract and the gait data of database;
The second sending module is used for when the gait data coupling of the gait feature that extracts and database the corresponding corresponding user name of gait data in the database being sent to the cloud terminal;
Display module is used for receiving and showing corresponding user name.
7. Gait Recognition according to claim 6 system is characterized in that described pre-service comprises denoising and profile extraction process.
8. Gait Recognition according to claim 6 system is characterized in that described Cloud Server also comprises detection module and retransmit module, and
Described detection module is for detection of the gait video sequence that receives continuous whole whether;
Described extraction module, be used for when detecting the gait video sequence continuous whole that receives, by default Algorithm for gait recognition the gait video sequence that receives is processed to extract gait feature, and the gait feature that extracts has identical pattern with pre-stored gait data in database;
Described retransmit module is used for detecting the gait video sequence that receives when discontinuous, requires monitor terminal again to send out pretreated gait video sequence described.
9. Gait Recognition according to claim 6 system, it is characterized in that default Algorithm for gait recognition is in following: the Algorithm for gait recognition of analyzing based on the two-dimentional Algorithm for gait recognition of pivot analysis, based on Statistical Shape, based on the Algorithm for gait recognition of space-time profile analysis, based on the Algorithm for gait recognition of model, based on the Method of Gait Feature Extraction of Hough conversion, based on the Algorithm for gait recognition of 3 D wavelet square theory.
10. Gait Recognition according to claim 6 system is characterized in that, described the first sending module also is used at acquisition module when collecting people's gait picture, sends signal without the gait video sequence to Cloud Server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101260007A CN103377366A (en) | 2012-04-26 | 2012-04-26 | Gait recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101260007A CN103377366A (en) | 2012-04-26 | 2012-04-26 | Gait recognition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103377366A true CN103377366A (en) | 2013-10-30 |
Family
ID=49462453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101260007A Pending CN103377366A (en) | 2012-04-26 | 2012-04-26 | Gait recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103377366A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106850955A (en) * | 2016-12-20 | 2017-06-13 | 陕西尚品信息科技有限公司 | A kind of mobile phone identity verification method based on Gait Recognition |
| CN107122718A (en) * | 2017-04-05 | 2017-09-01 | 西北工业大学 | A kind of new target pedestrian's trace tracking method based on Kinect |
| CN107247957A (en) * | 2016-12-16 | 2017-10-13 | 广州中国科学院先进技术研究所 | A kind of intelligent agricultural product sorting technique and system based on deep learning and cloud computing |
| CN107411750A (en) * | 2017-06-02 | 2017-12-01 | 郑翔光 | A kind of intelligence step appearance antidote and system |
| CN107506684A (en) * | 2016-06-14 | 2017-12-22 | 中兴通讯股份有限公司 | Gait recognition method and device |
| CN108304757A (en) * | 2017-06-16 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Personal identification method and device |
| CN109171740A (en) * | 2018-07-26 | 2019-01-11 | 深圳市嘉乐医疗科技有限公司 | Intelligent physical examination machine and its gait detection method with gait detection |
| CN109635776A (en) * | 2018-12-23 | 2019-04-16 | 广东腾晟信息科技有限公司 | Pass through the method for procedure identification human action |
| CN110147712A (en) * | 2019-03-27 | 2019-08-20 | 苏州书客贝塔软件科技有限公司 | A kind of intelligent cloud platform of pedestrian's analysis |
| CN111353477A (en) * | 2020-04-16 | 2020-06-30 | 银河水滴科技（北京）有限公司 | Gait recognition system and method |
| CN111476198A (en) * | 2020-04-24 | 2020-07-31 | 广西安良科技有限公司 | Gait recognition method, device and system based on artificial intelligence, storage medium and server |
| CN112214783A (en) * | 2020-11-18 | 2021-01-12 | 西北大学 | Gait recognition platform and method based on trusted execution environment |
| CN113657169A (en) * | 2021-07-19 | 2021-11-16 | 浙江大华技术股份有限公司 | Gait recognition method, device, system and computer readable storage medium |
| CN117421605A (en) * | 2023-10-27 | 2024-01-19 | 绍兴清研微科技有限公司 | Gait recognition method and system based on block chain technology |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122360A (en) * | 2011-03-01 | 2011-07-13 | 华南理工大学 | Cloud computing-based mobile terminal handwriting identification method |
-
2012
- 2012-04-26 CN CN2012101260007A patent/CN103377366A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122360A (en) * | 2011-03-01 | 2011-07-13 | 华南理工大学 | Cloud computing-based mobile terminal handwriting identification method |
Non-Patent Citations (2)
| Title |
|---|
| CHEWYEAN YAM等: "Automated person recognition by walking and running via model-based approaches", 《PATTERN RECOGNITION》 * |
| 王立: "步态识别及其在智能视频监控中的应用", 《淮北煤炭师范学院学报(自然科学版)》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506684A (en) * | 2016-06-14 | 2017-12-22 | 中兴通讯股份有限公司 | Gait recognition method and device |
| CN107247957A (en) * | 2016-12-16 | 2017-10-13 | 广州中国科学院先进技术研究所 | A kind of intelligent agricultural product sorting technique and system based on deep learning and cloud computing |
| CN106850955B (en) * | 2016-12-20 | 2019-07-02 | 陕西尚品信息科技有限公司 | A kind of mobile phone identity verification method based on Gait Recognition |
| CN106850955A (en) * | 2016-12-20 | 2017-06-13 | 陕西尚品信息科技有限公司 | A kind of mobile phone identity verification method based on Gait Recognition |
| CN107122718A (en) * | 2017-04-05 | 2017-09-01 | 西北工业大学 | A kind of new target pedestrian's trace tracking method based on Kinect |
| CN107411750A (en) * | 2017-06-02 | 2017-12-01 | 郑翔光 | A kind of intelligence step appearance antidote and system |
| CN108304757A (en) * | 2017-06-16 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Personal identification method and device |
| CN109171740A (en) * | 2018-07-26 | 2019-01-11 | 深圳市嘉乐医疗科技有限公司 | Intelligent physical examination machine and its gait detection method with gait detection |
| CN109635776A (en) * | 2018-12-23 | 2019-04-16 | 广东腾晟信息科技有限公司 | Pass through the method for procedure identification human action |
| CN110147712A (en) * | 2019-03-27 | 2019-08-20 | 苏州书客贝塔软件科技有限公司 | A kind of intelligent cloud platform of pedestrian's analysis |
| CN111353477B (en) * | 2020-04-16 | 2024-04-19 | 公安部物证鉴定中心 | Gait recognition system and method |
| CN111353477A (en) * | 2020-04-16 | 2020-06-30 | 银河水滴科技（北京）有限公司 | Gait recognition system and method |
| CN111476198A (en) * | 2020-04-24 | 2020-07-31 | 广西安良科技有限公司 | Gait recognition method, device and system based on artificial intelligence, storage medium and server |
| CN111476198B (en) * | 2020-04-24 | 2023-09-26 | 广西安良科技有限公司 | Gait recognition method, device, system, storage medium and server based on artificial intelligence |
| CN112214783B (en) * | 2020-11-18 | 2023-08-25 | 西北大学 | Gait recognition platform and recognition method based on trusted execution environment |
| CN112214783A (en) * | 2020-11-18 | 2021-01-12 | 西北大学 | Gait recognition platform and method based on trusted execution environment |
| CN113657169A (en) * | 2021-07-19 | 2021-11-16 | 浙江大华技术股份有限公司 | Gait recognition method, device, system and computer readable storage medium |
| CN117421605A (en) * | 2023-10-27 | 2024-01-19 | 绍兴清研微科技有限公司 | Gait recognition method and system based on block chain technology |
| CN117421605B (en) * | 2023-10-27 | 2024-04-30 | 绍兴清研微科技有限公司 | Gait recognition method and system based on block chain technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103377366A (en) | Gait recognition method and system | |
| Yang et al. | Relative distance features for gait recognition with Kinect | |
| Wang et al. | Silhouette analysis-based gait recognition for human identification | |
| Li et al. | Classification of gait anomalies from kinect | |
| Jeevan et al. | Gait recognition based on gait pal and pal entropy image | |
| CN110555412B (en) | End-to-end human body gesture recognition method based on combination of RGB and point cloud | |
| Patruno et al. | People re-identification using skeleton standard posture and color descriptors from RGB-D data | |
| Yao et al. | Robust gait recognition using hybrid descriptors based on skeleton gait energy image | |
| CN104200200B (en) | Fusion depth information and half-tone information realize the system and method for Gait Recognition | |
| CN101609507A (en) | Gait recognition method | |
| Kusakunniran et al. | Automatic gait recognition using weighted binary pattern on video | |
| CN105138995A (en) | Time-invariant and view-invariant human action identification method based on skeleton information | |
| Deng et al. | Human gait recognition based on deterministic learning and data stream of microsoft kinect | |
| CN103955680A (en) | Action recognition method and device based on shape context | |
| CN103955682A (en) | Behavior recognition method and device based on SURF interest points | |
| CN105354856A (en) | Human matching and positioning method and system based on MSER and ORB | |
| Bedagkar-Gala et al. | Gait-assisted person re-identification in wide area surveillance | |
| Naiel et al. | Multi-view human action recognition system employing 2DPCA | |
| Yan et al. | Human-object interaction recognition using multitask neural network | |
| CN110909612A (en) | Gait recognition method and system based on deep neural network and machine vision | |
| Jia et al. | View-invariant gait authentication based on silhouette contours analysis and view estimation | |
| CN111582036A (en) | Cross-view-angle person identification method based on shape and posture under wearable device | |
| CN112183184A (en) | Motion capture method based on asynchronous video | |
| Cai et al. | Hybrid silhouette-skeleton body representation for gait recognition | |
| Huang et al. | Viewpoint insensitive action recognition using envelop shape |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131030 |
|
| RJ01 | Rejection of invention patent application after publication |