CN103065125A - Remote personal identification method based on instantaneous gait energy diagram - Google Patents
Remote personal identification method based on instantaneous gait energy diagram Download PDFInfo
- Publication number
- CN103065125A CN103065125A CN2012105869207A CN201210586920A CN103065125A CN 103065125 A CN103065125 A CN 103065125A CN 2012105869207 A CN2012105869207 A CN 2012105869207A CN 201210586920 A CN201210586920 A CN 201210586920A CN 103065125 A CN103065125 A CN 103065125A
- Authority
- CN
- China
- Prior art keywords
- gait
- phase
- instantaneous
- energygram
- profile
- 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
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a remote personal identification method based on an instantaneous gait energy diagram. The remote personal identification method sequentially comprises the steps of gait feature extraction and identification, calculation of gait circles, calculation of the instantaneous gait energy diagram, and calculation of feature vectors of an object. Compared with biological identification technology, the remote personal identification method based on the instantaneous gait energy diagram is simple, good in adaptability for side outline with low quality, and helpful in crime resistance.
Description
Technical field
The present invention relates to human body limb movement measuring method field, be specially a kind of far distance identity identifying method based on instantaneous gait energygram.
Background technology
Biological identification technology utilizes the feature of human body to carry out authentication, these features comprise fingerprint, sound, facial, iris, DNA, the action of signature, the gait of walking etc., different from the other biological recognition technology, Gait Recognition can carried out at a distance, although people's face is smudgy on certain distance, but gait is high-visible, Gait Recognition also has unforced property, do not need the identified person specially to cooperate, make the identified person be difficult for discovering, and have characteristics such as being difficult for hiding imitation, so the research of gait there is certain help for apprehend this criminal, but at present domestic research to Gait Recognition is also few, does not also have what new progress.
Summary of the invention
The purpose of this invention is to provide a kind of far distance identity identifying method based on instantaneous gait energygram, to solve prior art not based on the problem of the personal identification method of gait.
In order to achieve the above object, the technical solution adopted in the present invention is:
A kind of far distance identity identifying method of phase decomposition and instantaneous gait energygram during based on gait is characterized in that: may further comprise the steps:
(1), Method of Gait Feature Extraction and identification: the position of video camera is fixed, and shooting angle is vertical with the direction of travel of subject, extracts subject standard side profile image from a series of walking images that video is taken continuously.Be divided into for three steps in this step: the methods such as use background subtraction extract preliminary profile, reduce noise effect by Morphology Algorithm again, at last the contour images that extracts are carried out size criteria.
(2), calculate gait cycle: each width of cloth side profile figure in the walking image is calculated swinging distance, namely in the profile distance of the profile barycenter of having a few with.Swinging distance is larger when taking a step, and swinging distance was less when two legs were overlapping, and in the walking image of a series, swinging distance presents approximate periodic character.Because maximum value is usually clearer and more definite, be subjected to noise less, get the odd number maximum point averaging time difference as gait cycle;
(3), calculate instantaneous gait energygram: first according to the swinging distance extreme point that obtains in (2), phase when gait cycle is decomposed into gait, in biological gait time phase dividing, both feet are divided separately, to each pin, support and account for mutually 60%, swing and account for mutually 40%, and the swing of a pin overlaps mutually with the support of another pin, in the outboard profile of walking image, can think that both feet are symmetrical, not distinguish, phase when therefore gait cycle being decomposed into two, be dual-gripper phase and single phase that supports, the former supports simultaneously for both feet, and corresponding both feet support the lap of phase, occur twice in a gait cycle, approximately respectively account for 10% of gait cycle, centered by the maximum point of swinging distance, to each maximum value get gait cycle 10% as the dual-gripper phase, all the other are single phase that supports, phase during to every class, calculate according to the following steps respectively instantaneous gait energygram:
A. the time interval specifies s constantly to be crucial moment equably, and the image at each crucial moment is called ifm diagram.Get in all gait datas, this time the minimum frame number that comprises mutually as s, to obtain ifm diagram as much as possible;
B. phase in the time of to same subject, the ifm diagram at each crucial moment averages, and obtains in the gait cycle, and each average ifm diagram constantly is as the basis of calculating instantaneous gait energygram;
C. calculate instantaneous gait energygram on the ifm diagram basis.To each constantly, this instantaneous gait energygram constantly is defined as the ifm diagram in this moment, with the ifm diagram in other moment by with the decay result of rear stack of the time interval in this moment.In calculating, need a decay factor, determine according to experiment, generally get 0.8;
(4), can extract proper vector with distinct methods by instantaneous gait energygram, represent the gait characteristic of subject, according to proper vector subject is done Classification and Identification, identify its different identity.Use in the method two feature vectors, the one, the difference of instantaneous gait energygram and profile diagram is got s maximum difference constantly, is called the gait deflection graph; Dual-gripper phase and single the support are drawn respectively a gait deflection graph mutually, have two; The 2nd, gait energygram itself, i.e. ifm diagram mean value in gait cycle; Obtain classifying after the proper vector, because the emphasis of Research on Gait Recognition generally only uses simple nearest neighbor classification at sorting phase in feature extraction and expression.
The present invention is more more simple and practical than biological identification technology, and low-quality side profile is had good adaptability, and can carry out rapidly identification, for crime prevention good help is arranged.
Embodiment
A kind of far distance identity identifying method of phase decomposition and instantaneous gait energygram during based on gait may further comprise the steps:
(1), Method of Gait Feature Extraction and identification: the position of video camera is fixed, and shooting angle is vertical with the direction of travel of subject, extracts subject standard side profile image from a series of walking images that video is taken continuously.Be divided into for three steps in this step: the methods such as use background subtraction extract preliminary profile, reduce noise effect by Morphology Algorithm again, at last the contour images that extracts are carried out size criteria.
(2), calculate gait cycle: each width of cloth side profile figure in the walking image is calculated swinging distance, namely in the profile distance of the profile barycenter of having a few with.Swinging distance is larger when taking a step, and swinging distance was less when two legs were overlapping, and in the walking image of a series, swinging distance presents approximate periodic character.Because maximum value is usually clearer and more definite, be subjected to noise less, get the odd number maximum point averaging time difference as gait cycle;
(3), calculate instantaneous gait energygram: first according to the swinging distance extreme point that obtains in (2), phase when gait cycle is decomposed into gait, in biological gait time phase dividing, both feet are divided separately, to each pin, support and account for mutually 60%, swing and account for mutually 40%, and the swing of a pin overlaps mutually with the support of another pin, in the outboard profile of walking image, can think that both feet are symmetrical, not distinguish, phase when therefore gait cycle being decomposed into two, be dual-gripper phase and single phase that supports, the former supports simultaneously for both feet, and corresponding both feet support the lap of phase, occur twice in a gait cycle, approximately respectively account for 10% of gait cycle, centered by the maximum point of swinging distance, to each maximum value get gait cycle 10% as the dual-gripper phase, all the other are single phase that supports, phase during to every class, calculate according to the following steps respectively instantaneous gait energygram:
A. the time interval specifies s constantly to be crucial moment equably, and the image at each crucial moment is called ifm diagram.Get in all gait datas, this time the minimum frame number that comprises mutually as s, to obtain ifm diagram as much as possible;
B. phase in the time of to same subject, the ifm diagram at each crucial moment averages, and obtains in the gait cycle, and each average ifm diagram constantly is as the basis of calculating instantaneous gait energygram;
C. calculate instantaneous gait energygram on the ifm diagram basis.To each constantly, this instantaneous gait energygram constantly is defined as the ifm diagram in this moment, with the ifm diagram in other moment by with the decay result of rear stack of the time interval in this moment.In calculating, need a decay factor, determine according to experiment, generally get 0.8;
(4), can extract proper vector with distinct methods by instantaneous gait energygram, represent the gait characteristic of subject, according to proper vector subject is done Classification and Identification, identify its different identity.Use in the method two feature vectors, the one, the difference of instantaneous gait energygram and profile diagram is got s maximum difference constantly, is called the gait deflection graph; Dual-gripper phase and single the support are drawn respectively a gait deflection graph mutually, have two; The 2nd, gait energygram itself, i.e. ifm diagram mean value in gait cycle; Obtain classifying after the proper vector, because the emphasis of Research on Gait Recognition generally only uses simple nearest neighbor classification at sorting phase in feature extraction and expression.
Claims (1)
1. the far distance identity identifying method of a phase decomposition during based on gait and instantaneous gait energygram is characterized in that: may further comprise the steps:
(1), Method of Gait Feature Extraction and identification: the position of video camera is fixed, and shooting angle is vertical with the direction of travel of subject, extracts subject standard side profile image from a series of walking images that video is taken continuously;
Be divided into for three steps in this step: the methods such as use background subtraction extract preliminary profile, reduce noise effect by Morphology Algorithm again, at last the contour images that extracts are carried out size criteria;
(2), calculate gait cycle: each width of cloth side profile figure in the walking image is calculated swinging distance, namely in the profile distance of the profile barycenter of having a few with; Swinging distance is larger when taking a step, and swinging distance was less when two legs were overlapping, and in the walking image of a series, swinging distance presents approximate periodic character; Because maximum value is usually clearer and more definite, be subjected to noise less, get the odd number maximum point averaging time difference as gait cycle;
(3), calculate instantaneous gait energygram: first according to the swinging distance extreme point that obtains in (2), phase when gait cycle is decomposed into gait, in biological gait time phase dividing, both feet are divided separately, to each pin, support and account for mutually 60%, swing and account for mutually 40%, and the swing of a pin overlaps mutually with the support of another pin, in the outboard profile of walking image, can think that both feet are symmetrical, not distinguish, phase when therefore gait cycle being decomposed into two, be dual-gripper phase and single phase that supports, the former supports simultaneously for both feet, and corresponding both feet support the lap of phase, occur twice in a gait cycle, approximately respectively account for 10% of gait cycle, centered by the maximum point of swinging distance, to each maximum value get gait cycle 10% as the dual-gripper phase, all the other are single phase that supports, phase during to every class, calculate according to the following steps respectively instantaneous gait energygram:
A. the time interval specifies s constantly to be crucial moment equably, and the image at each crucial moment is called ifm diagram;
Get in all gait datas, this time the minimum frame number that comprises mutually as s, to obtain ifm diagram as much as possible;
B. phase in the time of to same subject, the ifm diagram at each crucial moment averages, and obtains in the gait cycle, and each average ifm diagram constantly is as the basis of calculating instantaneous gait energygram;
C. calculate instantaneous gait energygram on the ifm diagram basis;
To each constantly, this instantaneous gait energygram constantly is defined as the ifm diagram in this moment, with the ifm diagram in other moment by with the decay result of rear stack of the time interval in this moment; In calculating, need a decay factor, determine according to experiment, generally get 0.8;
(4), can extract proper vector with distinct methods by instantaneous gait energygram, represent the gait characteristic of subject, according to proper vector subject is done Classification and Identification, identify its different identity; Use in the method two feature vectors, the one, the difference of instantaneous gait energygram and profile diagram is got s maximum difference constantly, is called the gait deflection graph; Dual-gripper phase and single the support are drawn respectively a gait deflection graph mutually, have two; The 2nd, gait energygram itself, i.e. ifm diagram mean value in gait cycle; Obtain classifying after the proper vector, because the emphasis of Research on Gait Recognition generally only uses simple nearest neighbor classification at sorting phase in feature extraction and expression.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105869207A CN103065125A (en) | 2012-12-31 | 2012-12-31 | Remote personal identification method based on instantaneous gait energy diagram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105869207A CN103065125A (en) | 2012-12-31 | 2012-12-31 | Remote personal identification method based on instantaneous gait energy diagram |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103065125A true CN103065125A (en) | 2013-04-24 |
Family
ID=48107748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012105869207A Pending CN103065125A (en) | 2012-12-31 | 2012-12-31 | Remote personal identification method based on instantaneous gait energy diagram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103065125A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593651A (en) * | 2013-10-28 | 2014-02-19 | 西京学院 | Method for identifying identities of underground coal mine workers based on gaits and two-dimensional discriminant analysis |
| CN109002785A (en) * | 2018-07-05 | 2018-12-14 | 西安交通大学 | Gait recognition method based on movement timing energy diagram |
| CN111196135A (en) * | 2018-11-20 | 2020-05-26 | 宝沃汽车（中国）有限公司 | Vehicle door control method and device and vehicle |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101241551A (en) * | 2008-03-06 | 2008-08-13 | 复旦大学 | Gait recognition method based on tangent vector |
| CN101571917A (en) * | 2009-06-16 | 2009-11-04 | 哈尔滨工程大学 | Front side gait cycle detecting method based on video |
| US20120321136A1 (en) * | 2011-06-14 | 2012-12-20 | International Business Machines Corporation | Opening management through gait detection |
-
2012
- 2012-12-31 CN CN2012105869207A patent/CN103065125A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101241551A (en) * | 2008-03-06 | 2008-08-13 | 复旦大学 | Gait recognition method based on tangent vector |
| CN101571917A (en) * | 2009-06-16 | 2009-11-04 | 哈尔滨工程大学 | Front side gait cycle detecting method based on video |
| US20120321136A1 (en) * | 2011-06-14 | 2012-12-20 | International Business Machines Corporation | Opening management through gait detection |
Non-Patent Citations (1)
| Title |
|---|
| 马勤勇，等: "基于瞬时步态能量图的远距离身份识别", 《电子学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593651A (en) * | 2013-10-28 | 2014-02-19 | 西京学院 | Method for identifying identities of underground coal mine workers based on gaits and two-dimensional discriminant analysis |
| CN103593651B (en) * | 2013-10-28 | 2016-10-05 | 西京学院 | Based on gait and the coal mine down-hole personnel authentication identifying method of two dimension discriminant analysis |
| CN109002785A (en) * | 2018-07-05 | 2018-12-14 | 西安交通大学 | Gait recognition method based on movement timing energy diagram |
| CN111196135A (en) * | 2018-11-20 | 2020-05-26 | 宝沃汽车（中国）有限公司 | Vehicle door control method and device and vehicle |
| CN111196135B (en) * | 2018-11-20 | 2021-05-14 | 宝沃汽车（中国）有限公司 | Vehicle door control method and device and vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104915649B (en) | A kind of biopsy method applied to recognition of face | |
| WO2019080578A1 (en) | 3d face identity authentication method and apparatus | |
| Nejati et al. | Wonder ears: Identification of identical twins from ear images | |
| WO2019080579A1 (en) | 3d face identity authentication method and apparatus | |
| Batchuluun et al. | Gait-based human identification by combining shallow convolutional neural network-stacked long short-term memory and deep convolutional neural network | |
| KR20130048076A (en) | Face recognition apparatus and control method for the same | |
| CN103942577A (en) | Identity identification method based on self-established sample library and composite characters in video monitoring | |
| CN105260726A (en) | Interactive video in vivo detection method based on face attitude control and system thereof | |
| Lee et al. | Emotional recognition from facial expression analysis using bezier curve fitting | |
| Min et al. | Gait recognition using deep convolutional features | |
| CN103065125A (en) | Remote personal identification method based on instantaneous gait energy diagram | |
| CN104636756A (en) | Posture recognition method for family elder monitoring | |
| CN104573628A (en) | Three-dimensional face recognition method | |
| CN107862298A (en) | It is a kind of based on the biopsy method blinked under infrared eye | |
| Liu et al. | Gender recognition using dynamic gait energy image | |
| CN104217211A (en) | Multi-visual-angle gait recognition method based on optimal discrimination coupling projection | |
| Hu et al. | A new approach for gender classification based on gait analysis | |
| Luo et al. | Robust gait recognition based on partitioning and canonical correlation analysis | |
| He et al. | Spontaneous facial expression recognition based on feature point tracking | |
| Huynh | A new eye gaze detection algorithm using PCA features and recurrent neural networks | |
| CN105631387A (en) | Instantaneous gait remote identification method | |
| Alotaibi et al. | Automatic real time gait recognition based on spatiotemporal templates | |
| Nguyen et al. | Gaze detection based on head pose estimation in smart TV | |
| Jüngling et al. | A Multi-staged System for Efficient Visual Person Reidentification. | |
| Ahmed et al. | Survey: Gait Recognition Based on Image Energy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130424 |