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
- module
- cloud server
- database
- 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
- 230000005021 gait Effects 0.000 title claims abstract description 292
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 67
- 238000012544 monitoring process Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000000605 extraction Methods 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 9
- 238000000513 principal component analysis Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 244000309466 calf Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 210000000689 upper leg Anatomy 0.000 description 2
- 206010034719 Personality change Diseases 0.000 description 1
- 241000228740 Procrustes Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000002414 leg Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
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 invention relates to the technical field of biological feature recognition, in particular to a gait recognition method and a gait recognition system.
Background
The biological characteristic recognition technology is a method for identifying individual identity, and carries out identity recognition every other day by using the intrinsic physiological or behavior characteristics of kickers through a high-tech information monitoring technology, and comprises various recognition technologies such as face recognition, fingerprint recognition, iris recognition, gait recognition and the like. Because the biological characteristics of each person have uniqueness and universality and are not easy to forge and counterfeit, the identity authentication by utilizing the biological characteristic identification technology has the advantages of safety, reliability, correctness and the like. At present, the widely used first-generation biometric identification technologies such as face identification, fingerprint identification, iris identification and the like mostly need to be matched with detected objects, and sometimes the detected objects need to complete specific actions to be identified, so that certain identity authentication passivity is inevitably caused.
Gait recognition aims at recognizing the identity of people according to the walking posture of people, serves as a second generation biological feature recognition technology, is the only biological feature recognition technology capable of performing identity authentication under the remote condition, and has the advantages of being good in concealment, low in requirement on video quality, remote in non-contact, difficult to disguise and the like. Gait recognition can still play a strong and powerful role even in the case of failure of other biometric recognition techniques. Based on the advantages, gait recognition attracts much attention in recent years, and has a wide application prospect in the field of visual monitoring. However, in the current gait recognition research, basically, a picture sequence is processed on a terminal such as a single PC, and there may be more than one person's gait in the picture sequence, if gait recognition is performed on a gait video sequence acquired by a plurality of cameras, the requirement on the terminal is high, which will limit the popularization and application of the gait recognition.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a gait recognition method with low configuration requirement on a terminal, aiming at the defect of high configuration requirement on the terminal when gait recognition is performed on gait video sequences acquired by a plurality of cameras in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: constructing a gait recognition method comprising:
s1, a monitoring terminal collects human gait in real time to form a gait video sequence and preprocesses the obtained gait video sequence;
s2, the monitoring terminal sends the preprocessed gait video sequence to a cloud server through a network;
s3, the cloud server receives the preprocessed gait video sequence, processes the received gait video sequence through a preset gait recognition algorithm to extract gait features, and the extracted gait features have the same mode as the gait data stored in the database in advance;
s4, the cloud server compares the extracted gait features with gait data in a database for identification, and if the extracted gait features are matched with the gait data in the database, a user name corresponding to the corresponding gait data in the database is sent to the cloud terminal;
and S5, the cloud terminal receives and displays the corresponding user name.
In the gait recognition method, the preprocessing includes a denoising process and a contour extraction process.
In the gait recognition method according to the present invention, the step S3 includes:
s31, the cloud server receives the preprocessed gait video sequence;
s32, the cloud server detects whether the received gait video sequence is continuous and complete, and if so, the step S35 is executed; if not, go to step S33;
s33, the cloud server requires the monitoring terminal to retransmit the preprocessed gait video sequence;
s34, the monitoring terminal resends the preprocessed gait video sequence and then executes the step S32;
and S35, the cloud server processes the received gait video sequence through a preset gait recognition algorithm to extract gait features, and the extracted gait features and the gait data pre-stored in the database have the same mode.
In the gait recognition method of the invention, the preset gait recognition algorithm is one of the following: the gait recognition method comprises a two-dimensional gait recognition algorithm based on principal component analysis, a gait recognition algorithm based on statistical shape analysis, a gait recognition algorithm based on space-time contour analysis, a gait recognition algorithm based on a model, gait feature extraction based on Hough transformation and a gait recognition algorithm based on a three-dimensional wavelet moment theory.
In the gait recognition method, if the monitoring terminal does not acquire the gait picture of the person, a signal without a gait video sequence is sent to the cloud server.
The present invention also constructs a gait recognition system comprising: the system comprises at least one monitoring terminal arranged in a monitoring place, a cloud server arranged at a far end and cloud terminals, wherein each monitoring terminal comprises an acquisition module, a preprocessing module and a first sending module; the cloud server comprises a second receiving module, an extracting module, an identifying module and a second sending module; the cloud terminal comprises a display module; wherein,
the system comprises an acquisition module, a video processing module and a video processing module, wherein the acquisition module is used for acquiring human gaits in real time to form a gaits video sequence;
the preprocessing module is used for preprocessing the acquired gait video sequence;
the first sending module is used for sending the preprocessed gait video sequence to a cloud server through a network;
the second receiving module is used for receiving the preprocessed gait video sequence;
the extraction module is used for processing the received gait video sequence through a preset gait recognition algorithm to extract gait features, and the extracted gait features have the same mode as the gait data stored in the database in advance;
the identification module is used for comparing and identifying the extracted gait features with the gait data in the database;
the second sending module is used for sending the user name corresponding to the corresponding gait data in the database to the cloud terminal when the extracted gait features are matched with the gait data in the database;
and the display module is used for receiving and displaying the corresponding user name.
In the gait recognition system of the invention, the preprocessing includes a denoising processing and a contour extraction processing.
In the gait recognition system of the invention, the cloud server further comprises a detection module and a retransmission module, and
the detection module is used for detecting whether the received gait video sequence is continuous and complete;
the extraction module is used for processing the received gait video sequence through a preset gait recognition algorithm to extract gait features when the received gait video sequence is detected to be continuous and complete, and the extracted gait features have the same mode with gait data stored in a database in advance;
and the retransmission module is used for requiring the monitoring terminal to retransmit the preprocessed gait video sequence when the received gait video sequence is detected to be discontinuous.
In the gait recognition system of the invention, the preset gait recognition algorithm is one of the following: the gait recognition method comprises a two-dimensional gait recognition algorithm based on principal component analysis, a gait recognition algorithm based on statistical shape analysis, a gait recognition algorithm based on space-time contour analysis, a gait recognition algorithm based on a model, gait feature extraction based on Hough transformation and a gait recognition algorithm based on a three-dimensional wavelet moment theory.
In the gait recognition system of the invention, the first sending module is further configured to send a signal of the gait-free video sequence to the cloud server when the acquiring module does not acquire a gait picture of the person.
By implementing the technical scheme of the invention, the monitoring terminal only simply processes the collected gait video sequence, and the main calculation (gait feature extraction) of gait recognition is completed in the cloud server, so that the gait recognition can be accurately carried out in real time by utilizing the strong calculation capability of the cloud server, the cost of the monitoring terminal is greatly saved, and the popularization of the gait recognition is further promoted. In addition, the monitoring terminal performs simple processing before sending the gait video sequence to the cloud server, so that the size of the gait video sequence can be greatly reduced, and the transmission is facilitated.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a first embodiment of a gait recognition method of the invention;
FIG. 2 is a flowchart of a preferred embodiment of step S3 of FIG. 1;
fig. 3 is a logic diagram of a first embodiment of a gait recognition system according to the invention.
Detailed Description
As shown in fig. 1, in a flowchart of a first embodiment of a gait recognition method according to the present invention, the gait recognition method includes:
s1, a monitoring terminal collects human gait in real time to form a gait video sequence and preprocesses the obtained gait video sequence, wherein the preprocessing comprises simple processing such as denoising processing and contour extraction processing;
s2, the monitoring terminal sends the preprocessed gait video sequence to a cloud server through a network;
s3, the cloud server receives the preprocessed gait video sequence, processes the received gait video sequence through a preset gait recognition algorithm to extract gait characteristics, and the extracted gait characteristics and gait data stored in a database in advance have the same mode;
s4, the cloud server compares the extracted gait features with gait data in a database for identification, and if the extracted gait features are matched with the gait data in the database, a user name corresponding to the corresponding gait data in the database is sent to the cloud terminal;
and S5, the cloud terminal receives and displays the corresponding user name.
By implementing the technical scheme, the monitoring terminal only carries out simple processing on the collected gait video sequence, the main calculation (gait feature extraction) of gait recognition is completed in the cloud server, and the gait recognition can be accurately carried out in real time by utilizing the strong calculation capacity of the cloud server, so that the cost of the monitoring terminal is greatly saved, and the popularization of the gait recognition is further promoted. In addition, the monitoring terminal carries out simple processing before sending the gait video sequence, so that the size of the gait video sequence can be greatly reduced, and the transmission is convenient.
FIG. 2 is a flowchart of a preferred embodiment of step S3 of FIG. 1, in which step S3 includes:
s31, the cloud server receives the preprocessed gait video sequence;
s32, the cloud server detects whether the received gait video sequence is continuous and complete, and if so, the step S35 is executed; if not, go to step S33;
s33, the cloud server requires the monitoring terminal to retransmit the preprocessed gait video sequence;
s34, the monitoring terminal resends the preprocessed gait video sequence and then executes the step S32;
and S35, the cloud server processes the received gait video sequence through a preset gait recognition algorithm to extract gait features, and the extracted gait features and the gait data pre-stored in the database have the same mode.
In the preferred embodiment, after receiving the gait video sequence, the gait video sequence is judged whether to be continuous and complete, and only when the gait video sequence is continuous and complete, the cloud server processes the received gait video sequence through a preset gait recognition algorithm, so that the effective operation of the cloud server can be improved.
In another preferred embodiment of the present invention, if the monitoring terminal does not acquire a human gait picture, that is, does not recognize or monitor a human, a signal of a gait-free video sequence is sent to the cloud server.
In a further preferred embodiment of the invention, the predetermined gait recognition algorithm is one of the following: the gait recognition method comprises a two-dimensional gait recognition algorithm based on principal component analysis, a gait recognition algorithm based on statistical shape analysis, a gait recognition algorithm based on space-time contour analysis, a gait recognition algorithm based on a model, gait feature extraction based on Hough transformation and a gait recognition algorithm based on a three-dimensional wavelet moment theory. Each algorithm is described individually below:
1. two-dimensional gait recognition algorithm based on principal component analysis
In two-dimensional gait recognition algorithms based on principal component analysis, an improved background subtraction technique is used to extract the spatial contour of a person for each gait video sequence. The edges of these contours are spread out counterclockwise as a series of distance templates relative to the centroid. These template features are trained using a principal component statistical analysis method to derive a trajectory expression of the change pattern of the gait shape in the feature space. During identification, a space-time correlation matching method and a nearest neighbor rule based on normalized Euclidean distance are adopted, and fusion of physiological characteristics corresponding to individual body shapes and the like is introduced for necessary gait classification check.
2. Gait recognition algorithm based on statistical shape analysis
The algorithm comes from the idea that "an appearance model of a human body can be learned from spatiotemporal patterns of walking motion". For each gait video sequence, the background subtraction process is used to extract the motion profiles of the pedestrian, and the attitude changes of the profiles with time are correspondingly described as a sequence of Complex configurations in a two-dimensional space. And acquiring a main contour model from the sequence configuration as the static appearance characteristic of the human body by using a Procrustes shape analysis method.
3. Gait recognition algorithm based on space-time contour analysis
The algorithm derives from the intuitive idea that "human walking motion relies heavily on shape changes of contours over time". For each gait video sequence, a background subtraction and contour correlation method is used for detecting and tracking the motion contour of a pedestrian, and the time-varying two-dimensional contour shapes are converted into corresponding one-dimensional distance signals, and low-dimensional gait features are extracted through feature space transformation. Based on spatio-temporal correlation or normalized euclidean distance metrics, and standard pattern classification techniques are used for final identification.
4. Gait recognition algorithm based on model
The algorithm is derived from the idea that the joint angle change of the walking motion contains abundant individual identification information. Firstly, the pedestrian tracking is carried out by utilizing a Condensation algorithm in combination with the prior knowledge of a human body model, a motion model, motion constraint and the like. Then, the angle change trajectory of the main joints of the human body is obtained from the tracking result. These traces are normalized by structure and time and used as dynamic features for identification.
5. Gait feature extraction based on Hough transformation
The algorithm only identifies from the motion of the leg. For each gait video sequence, a background subtraction algorithm based on image chroma deviation is used to detect moving objects. In the post-processed binary image sequence, an object boundary is obtained by using a boundary tracking algorithm, and on an object boundary image, Hough transformation is locally applied to detect straight lines of thighs and calves, so that the inclination angles of the thighs and the calves are obtained. Fitting the inclination angle sequence in one period into a 5-order polynomial by using a least square method, and defining the product of the phase and the amplitude obtained after Fourier series expansion as a low-dimensional gait feature vector.
6. Gait recognition algorithm based on three-dimensional wavelet moment theory
The algorithm is based on the generalized multi-scale analysis theory, obtains the optimal wavelet decomposition aiming at different application images or signal libraries, and is combined with the two-dimensional wavelet moment for application in human gait recognition. In the aspect of representation of three-dimensional objects, a three-dimensional wavelet moment theory is provided as a non-redundant description and identification method of the three-dimensional objects. Compared with the method, the method not only has the invariance of translation, scaling and rotation, but also adds the characteristic of multi-scale analysis in the radial direction. According to different requirements, a multi-level feature descriptor can be provided, and after a spherical harmonic function acceleration algorithm and a wavelet Mallat algorithm are introduced, the calculation of wavelet moments is doubly accelerated.
Fig. 3 is a logic diagram of a first embodiment of the gait recognition system of the invention, which comprises: at least one monitoring terminal 10 (only one is shown in the figure) arranged at a monitoring place, a cloud server 20 arranged at a far end and a cloud terminal 30, wherein each monitoring terminal 10 comprises an acquisition module 11, a preprocessing module 12 and a first sending module 13; the cloud server 20 comprises a second receiving module 21, an extracting module 22, a recognizing module 23 and a second sending module 24; the cloud terminal 30 includes a display module 31. Furthermore, the acquisition module 11 is used to acquire human gait in real time to form a gait video sequence. The preprocessing module 12 is used for preprocessing the acquired gait video sequence, and the preprocessing may include denoising processing and contour extraction processing. The first sending module 13 is configured to send the preprocessed gait video sequence to a cloud server through a network. The second receiving module 21 is configured to receive the preprocessed gait video sequence. The extraction module 22 is configured to process the received gait video sequence through a preset gait recognition algorithm to extract gait features, where the extracted gait features have the same pattern as the gait data pre-stored in the database. The identification module 23 is used for comparing and identifying the extracted gait features with the gait data in the database. The second sending module 24 is configured to send the user name corresponding to the gait data in the database to the cloud terminal when the extracted gait feature matches the gait data in the database. The display module 31 is used for receiving and displaying the corresponding user name.
In a preferred embodiment, the cloud server 20 further includes a detection module and a retransmission module, and the detection module is configured to detect whether the received gait video sequence is continuously complete; the extraction module 22 is configured to, when it is detected that the received gait video sequence is continuous and complete, process the received gait video sequence through a preset gait recognition algorithm to extract gait features, where the extracted gait features have the same pattern as the gait data pre-stored in the database. The retransmission module is used for requiring the monitoring terminal to retransmit the preprocessed gait video sequence when the received gait video sequence is detected to be discontinuous.
In another preferred embodiment, the preset gait recognition algorithm used by the extraction module 23 may be one of the following: the gait recognition method comprises a two-dimensional gait recognition algorithm based on principal component analysis, a gait recognition algorithm based on statistical shape analysis, a gait recognition algorithm based on space-time contour analysis, a gait recognition algorithm based on a model, gait feature extraction based on Hough transformation and a gait recognition algorithm based on a three-dimensional wavelet moment theory.
In a further preferred embodiment of the present invention, the first sending module is further configured to send a signal of the gait-free video sequence to the cloud server when the capturing module does not capture a gait picture of the person.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. A gait recognition method, characterized by comprising:
s1, a monitoring terminal collects human gait in real time to form a gait video sequence and preprocesses the obtained gait video sequence;
s2, the monitoring terminal sends the preprocessed gait video sequence to a cloud server through a network;
s3, the cloud server receives the preprocessed gait video sequence, processes the received gait video sequence through a preset gait recognition algorithm to extract gait features, and the extracted gait features have the same mode as the gait data stored in the database in advance;
s4, the cloud server compares the extracted gait features with gait data in a database for identification, and if the extracted gait features are matched with the gait data in the database, a user name corresponding to the corresponding gait data in the database is sent to the cloud terminal;
and S5, the cloud terminal receives and displays the corresponding user name.
2. The gait recognition method according to claim 1, wherein the preprocessing includes a denoising process and a contour extraction process.
3. The gait recognition method according to claim 1, characterized in that the step S3 includes:
s31, the cloud server receives the preprocessed gait video sequence;
s32, the cloud server detects whether the received gait video sequence is continuous and complete, and if so, the step S35 is executed; if not, go to step S33;
s33, the cloud server requires the monitoring terminal to retransmit the preprocessed gait video sequence;
s34, the monitoring terminal resends the preprocessed gait video sequence and then executes the step S32;
and S35, the cloud server processes the received gait video sequence through a preset gait recognition algorithm to extract gait features, and the extracted gait features and the gait data pre-stored in the database have the same mode.
4. The gait recognition method according to claim 1, characterized in that the preset gait recognition algorithm is one of the following: the gait recognition method comprises a two-dimensional gait recognition algorithm based on principal component analysis, a gait recognition algorithm based on statistical shape analysis, a gait recognition algorithm based on space-time contour analysis, a gait recognition algorithm based on a model, gait feature extraction based on Hough transformation and a gait recognition algorithm based on a three-dimensional wavelet moment theory.
5. The gait recognition method according to claim 1, characterized in that if the monitor terminal does not acquire a human gait picture, a signal of the gait-free video sequence is sent to the cloud server.
6. A gait recognition system, characterized by comprising: the system comprises at least one monitoring terminal arranged in a monitoring place, a cloud server arranged at a far end and cloud terminals, wherein each monitoring terminal comprises an acquisition module, a preprocessing module and a first sending module; the cloud server comprises a second receiving module, an extracting module, an identifying module and a second sending module; the cloud terminal comprises a display module; wherein,
the system comprises an acquisition module, a video processing module and a video processing module, wherein the acquisition module is used for acquiring human gaits in real time to form a gaits video sequence;
the preprocessing module is used for preprocessing the acquired gait video sequence;
the first sending module is used for sending the preprocessed gait video sequence to a cloud server through a network;
the second receiving module is used for receiving the preprocessed gait video sequence;
the extraction module is used for processing the received gait video sequence through a preset gait recognition algorithm to extract gait features, and the extracted gait features have the same mode as the gait data stored in the database in advance;
the identification module is used for comparing and identifying the extracted gait features with the gait data in the database;
the second sending module is used for sending the user name corresponding to the corresponding gait data in the database to the cloud terminal when the extracted gait features are matched with the gait data in the database;
and the display module is used for receiving and displaying the corresponding user name.
7. The gait recognition system of claim 6, wherein the preprocessing includes a denoising process and a contour extraction process.
8. The gait recognition system of claim 6, wherein the cloud server further comprises a detection module and a retransmission module, and
the detection module is used for detecting whether the received gait video sequence is continuous and complete;
the extraction module is used for processing the received gait video sequence through a preset gait recognition algorithm to extract gait features when the received gait video sequence is detected to be continuous and complete, and the extracted gait features have the same mode with gait data stored in a database in advance;
and the retransmission module is used for requiring the monitoring terminal to retransmit the preprocessed gait video sequence when the received gait video sequence is detected to be discontinuous.
9. The gait recognition system of claim 6, wherein the preset gait recognition algorithm is one of: the gait recognition method comprises a two-dimensional gait recognition algorithm based on principal component analysis, a gait recognition algorithm based on statistical shape analysis, a gait recognition algorithm based on space-time contour analysis, a gait recognition algorithm based on a model, gait feature extraction based on Hough transformation and a gait recognition algorithm based on a three-dimensional wavelet moment theory.
10. The gait recognition system of claim 6, wherein the first sending module is further configured to send a signal of the gait-free video sequence to a cloud server when the capturing module does not capture a human gait picture.
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 | |
| Cheng et al. | Custom pictorial structures for re-identification. | |
| Chen et al. | Contour matching for 3D ear recognition | |
| Kusakunniran et al. | Recognizing gaits across views through correlated motion co-clustering | |
| Kusakunniran et al. | A new view-invariant feature for cross-view gait recognition | |
| Jeevan et al. | Gait recognition based on gait pal and pal entropy image | |
| Bedagkar-Gala et al. | Multiple person re-identification using part based spatio-temporal color appearance model | |
| Kusakunniran et al. | Automatic gait recognition using weighted binary pattern on video | |
| CN108537181A (en) | A kind of gait recognition method based on the study of big spacing depth measure | |
| CN108171138B (en) | Biological characteristic information acquisition method and device | |
| Cippitelli et al. | Evaluation of a skeleton-based method for human activity recognition on a large-scale RGB-D dataset | |
| Verlekar et al. | Gait recognition in the wild using shadow silhouettes | |
| Rida | Towards human body-part learning for model-free gait recognition | |
| Gawali et al. | 3d face recognition using geodesic facial curves to handle expression, occlusion and pose variations | |
| CN110909612A (en) | Gait recognition method and system based on deep neural network and machine vision | |
| Verlekar et al. | View-invariant gait recognition exploiting spatio-temporal information and a dissimilarity metric | |
| CN104615992A (en) | Long-distance fingerprint dynamic authentication method | |
| Ferrara et al. | On the use of the Kinect sensor for human identification in smart environments | |
| Xu et al. | Pedestrian detection based on motion compensation and HOG/SVM classifier | |
| Sadeghzadehyazdi et al. | GlidarCo: gait recognition by 3D skeleton estimation and biometric feature correction of flash lidar data | |
| Ahmed et al. | Survey: gait recognition based on image energy | |
| Sheth et al. | Gait Recognition Using Convolutional Neural Network. | |
| Hermosilla et al. | Thermal face recognition using local interest points and descriptors for HRI applications | |
| Anusha et al. | An approach to speed invariant gait analysis for human recognition using mutual information | |
| Gervei et al. | 3D face recognition using modified PCA methods |
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 |