CN111444804A - Human body checking method and system based on gait recognition - Google Patents
Human body checking method and system based on gait recognition Download PDFInfo
- Publication number
- CN111444804A CN111444804A CN202010193810.9A CN202010193810A CN111444804A CN 111444804 A CN111444804 A CN 111444804A CN 202010193810 A CN202010193810 A CN 202010193810A CN 111444804 A CN111444804 A CN 111444804A
- Authority
- CN
- China
- Prior art keywords
- human body
- image
- gait
- method based
- infrared
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Processing (AREA)
Abstract
The invention provides a human body checking method and a human body checking system based on gait recognition, wherein the method comprises the following steps: acquiring an infrared human body image shot by a thermal imager and carrying out skeletonization treatment; the gender of the human body is identified according to the gait characteristics of the skeletonized human body image. By adopting the technical scheme of the invention to identify the gait, the identification process is simple and the identification accuracy is high.
Description
Technical Field
The invention relates to the field of biological feature recognition, in particular to a human body checking method and a human body checking system based on gait recognition.
Background
The biometric identification technology is a method for identifying individual identity, and comprises various identification technologies such as face identification, fingerprint identification, iris identification, gait identification and the like, the fingerprint identification, iris identification, face identification and the like which are widely used at present are the first generation biometric identification technology, but the fingerprint and iris including face features are easily copied and backed up, and accordingly malicious behaviors of counterfeiting by others for identity authentication are generated, so that serious consequences are caused.
Gait recognition aims at identity recognition according to walking postures of people, is a novel biological authentication technology, is used as a second generation biological feature recognition technology, is the only biological feature recognition technology capable of identity authentication under the remote condition, and has the advantages of good concealment, low requirement on video quality, remote non-contact, difficulty in camouflage and the like. In the field of intelligent video monitoring, gait recognition is more advantageous than facial recognition.
The existing gait recognition mode usually recognizes the features of the gait based on various algorithms, neglects the auxiliary effect of the features of the human body on the gait recognition, and leads the algorithm of the gait recognition to be too complex and not to obtain accurate recognition degree.
Disclosure of Invention
The invention aims to provide a human body checking method and a human body checking system based on gait recognition, which have the advantages of simple recognition process and high recognition accuracy.
In an embodiment of the present invention, a human body inspection method based on gait recognition is provided, which includes:
acquiring an infrared human body image shot by a thermal imager and carrying out skeletonization treatment;
the gender of the human body is identified according to the gait characteristics of the skeletonized human body image.
In the embodiment of the present invention, the human body checking method based on gait recognition further includes:
the gait characteristics include hip swing amplitude, step frequency and degree of flexion of the foot.
In the embodiment of the invention, the step of identifying the sex of the human body according to the gait characteristics of the skeletonized human body image comprises the following steps:
collecting a plurality of infrared human body images of human body walking of men and women, and acquiring gait characteristics of the human body walking;
carrying out big data training on the collected gait features to obtain recognition models of the gait features of human bodies of different sexes;
and judging the gender of the currently shot infrared human body image by adopting the identification model.
In the embodiment of the present invention, the human body checking method based on gait recognition further includes: acquiring a human body image shot by a camera and carrying out skeletonization treatment;
and judging whether the human body is a disabled human body or not according to the difference between the human body image shot by the camera and the infrared human body image shot by the thermal imager.
In the embodiment of the invention, if the human body image shot by the camera has one more leg than the infrared human body image shot by the thermal imager, the human body is a disabled human body and is provided with the artificial limb.
In the embodiment of the invention, skeletonization processing is carried out on an infrared human body image shot by a thermal imager, and the skeletonization processing comprises the following steps:
subtracting the background image from the extracted infrared human body image to obtain a temperature image of the human body;
carrying out binarization on the obtained temperature image of the human body and carrying out Gaussian blur processing;
and extracting a bone image from the image after the Gaussian blur processing.
In the embodiment of the present invention, the human body checking method based on gait recognition further includes:
judging the number of human bodies: and judging the number of human bodies in the image according to the number of human legs of the skeletonized infrared human body image.
In the embodiment of the invention, whether the human leg is the human leg or not is judged according to the inverted V-shaped shape appearing in the skeletonized infrared human body image.
The embodiment of the invention also provides a human body checking system based on gait recognition, which adopts the human body checking method based on gait recognition to recognize the human body.
Compared with the prior art, the human body checking method and the human body checking system based on gait recognition acquire the infrared human body image shot by the thermal imaging instrument and perform skeletonization treatment, and recognize the sex of the human body according to the gait characteristics of the skeletonized human body image, such as hip swing amplitude, step frequency, foot bending degree and the like; in addition, whether the human body is disabled or not is judged according to the difference between the infrared image and the image shot by the camera; finally, the human body can be identified according to the shape characteristics of the legs of the human body, so that the number of the human bodies can be judged.
Drawings
Fig. 1 is a flow chart of a human body inspection method based on gait recognition according to an embodiment of the invention.
Fig. 2 is a schematic control flow diagram of the anti-following access control system according to the embodiment of the present invention.
Fig. 3 is a schematic flow chart of detecting the number of human legs of the anti-following access control system according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of implementations of the invention refers to specific embodiments,
as shown in fig. 1, in an embodiment of the present invention, a human body inspection method based on gait recognition is provided, which includes:
step S1: acquiring an infrared human body image shot by a thermal imager and carrying out skeletonization treatment;
step S2: the gender of the human body is identified according to the gait characteristics of the skeletonized human body image.
In step S1, the skeletonization process of the infrared human body image captured by the thermal imager includes:
step S11: subtracting the background image from the extracted infrared human body image to obtain a temperature image of the human body;
step S12: carrying out binarization on the obtained temperature image of the human body and carrying out Gaussian blur processing;
step S13: and extracting a bone image from the image after the Gaussian blur processing.
In step S2, the step of recognizing the sex of the human body based on the gait features of the skeletonized human body image includes:
step S21: collecting a plurality of infrared human body images of human body walking of men and women, and acquiring gait characteristics of the human body walking;
step S22: carrying out big data training on the collected gait features to obtain recognition models of the gait features of human bodies of different sexes;
step S23: and judging the gender of the currently shot infrared human body image by adopting the identification model.
It should be noted that the gait characteristics include hip swing amplitude, step frequency and degree of flexion of the foot. The bone structures of boys and girls are different, the hip bone part of girls is relatively wide, and the problems of boys and girls are relatively gathered because the situation that the girls want to grow exists. And the body fat content of women is higher than that of men; the combination of the two elements makes the female buttocks look bigger and more mellow than the male buttocks; therefore, when walking, the hip shaking range of girls is larger and more obvious than that of boys; modern adult women also wear high-heeled shoes, silk stockings and body-tightening underwear, which have the function of lifting the buttocks, so that the swinging range of the buttocks is larger. In addition, men and women have different walking steps, different frequencies and different degrees of foot bending. The sex can be judged through the two characteristics, the walking mode of men and women is acquired by using the infrared thermal imaging image as the biological image, and a large amount of data is acquired for model training. And finally judging the gender by using an artificial intelligence algorithm.
Further, in the embodiment of the present invention, whether the human body is a disabled person may be determined according to gait recognition, and the specific method includes:
acquiring a human body image shot by a camera and carrying out skeletonization treatment;
and judging whether the human body is a disabled human body or not according to the difference between the human body image shot by the camera and the infrared human body image shot by the thermal imager.
It should be noted that if the human body image shot by the camera has one more leg than the infrared human body image shot by the thermal imager, the human body is a disabled human body and is provided with a prosthesis.
Further, in the embodiment of the present invention, the human body checking method based on gait recognition may also be used to determine the number of human bodies. It should be noted that, because an included angle is formed between two legs when a person walks, the shape is similar to a shape of a reverse V, the legs of the person can be identified through the characteristic, and the number of the human bodies in the image can be judged according to the number of the legs of the person.
Further, in the embodiment of the present invention, a human body inspection system based on gait recognition is further provided, which uses the human body inspection method based on gait recognition to recognize a human body.
In summary, the human body inspection method and system based on gait recognition of the invention acquire the infrared human body image shot by the thermal imager and perform skeletonization processing, and recognize the sex of the human body according to the gait characteristics of the skeletonized human body image, such as hip swing amplitude, step frequency, foot bending degree and the like; in addition, whether the human body is disabled or not is judged according to the difference between the infrared image and the image shot by the camera; finally, the human body can be identified according to the shape characteristics of the legs of the human body, so that the number of the human bodies can be judged.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (9)
1. A human body checking method based on gait recognition is characterized by comprising the following steps:
acquiring an infrared human body image shot by a thermal imager and carrying out skeletonization treatment;
the gender of the human body is identified according to the gait characteristics of the skeletonized human body image.
2. The human body examination method based on gait recognition according to claim 1, characterized by further comprising:
the gait characteristics include hip swing amplitude, step frequency and degree of flexion of the foot.
3. The human body inspection method based on gait recognition according to claim 2, wherein recognizing the sex of the human body from the gait features of the skeletonized human body image comprises:
collecting a plurality of infrared human body images of human body walking of men and women, and acquiring gait characteristics of the human body walking;
carrying out big data training on the collected gait features to obtain recognition models of the gait features of human bodies of different sexes;
and judging the gender of the currently shot infrared human body image by adopting the identification model.
4. The human body examination method based on gait recognition according to claim 1, characterized by further comprising: acquiring a human body image shot by a camera and carrying out skeletonization treatment;
and judging whether the human body is a disabled human body or not according to the difference between the human body image shot by the camera and the infrared human body image shot by the thermal imager.
5. The human body examination method based on gait recognition according to claim 4, wherein if the image of the human body taken by the camera has one more leg than the image of the human body taken by the thermal imaging camera, it is interpreted that the human body is a disabled human body and a prosthetic limb is installed.
6. The human body inspection method based on gait recognition according to claim 1, wherein the skeletonization processing of the infrared human body image taken by the thermal imaging camera comprises:
subtracting the background image from the extracted infrared human body image to obtain a temperature image of the human body;
carrying out binarization on the obtained temperature image of the human body and carrying out Gaussian blur processing;
and extracting a bone image from the image after the Gaussian blur processing.
7. The human body examination method based on gait recognition according to claim 1, characterized by further comprising:
judging the number of human bodies: and judging the number of human bodies in the image according to the number of human legs of the skeletonized infrared human body image.
8. The body examination method based on gait recognition according to claim 7, characterized in that it is judged whether it is a human leg or not according to the shape of "Λ" appearing in the skeletonized infrared body image.
9. A human body inspection system based on gait recognition, characterized in that the human body is recognized by the human body inspection method based on gait recognition according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010193810.9A CN111444804A (en) | 2020-03-19 | 2020-03-19 | Human body checking method and system based on gait recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010193810.9A CN111444804A (en) | 2020-03-19 | 2020-03-19 | Human body checking method and system based on gait recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111444804A true CN111444804A (en) | 2020-07-24 |
Family
ID=71629595
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010193810.9A Pending CN111444804A (en) | 2020-03-19 | 2020-03-19 | Human body checking method and system based on gait recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111444804A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113408354A (en) * | 2021-05-19 | 2021-09-17 | 珠海方图智能科技有限公司 | Method, system and terminal for detecting physical condition of driver |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101251894A (en) * | 2008-01-28 | 2008-08-27 | 天津大学 | Gait recognizing method and gait feature abstracting method based on infrared thermal imaging |
CN101290658A (en) * | 2007-04-18 | 2008-10-22 | 中国科学院自动化研究所 | Gender recognition method based on gait |
CN108280435A (en) * | 2018-01-25 | 2018-07-13 | 盛视科技股份有限公司 | A kind of passenger's abnormal behaviour recognition methods based on human body attitude estimation |
CN110363140A (en) * | 2019-07-15 | 2019-10-22 | 成都理工大学 | A kind of human action real-time identification method based on infrared image |
-
2020
- 2020-03-19 CN CN202010193810.9A patent/CN111444804A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101290658A (en) * | 2007-04-18 | 2008-10-22 | 中国科学院自动化研究所 | Gender recognition method based on gait |
CN101251894A (en) * | 2008-01-28 | 2008-08-27 | 天津大学 | Gait recognizing method and gait feature abstracting method based on infrared thermal imaging |
CN108280435A (en) * | 2018-01-25 | 2018-07-13 | 盛视科技股份有限公司 | A kind of passenger's abnormal behaviour recognition methods based on human body attitude estimation |
CN110363140A (en) * | 2019-07-15 | 2019-10-22 | 成都理工大学 | A kind of human action real-time identification method based on infrared image |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113408354A (en) * | 2021-05-19 | 2021-09-17 | 珠海方图智能科技有限公司 | Method, system and terminal for detecting physical condition of driver |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ma et al. | Iris recognition using circular symmetric filters | |
Burge et al. | Ear biometrics in computer vision | |
WO2013087026A1 (en) | Locating method and locating device for iris | |
JP2002312772A (en) | Individual identification device and eye forgery judgment method | |
Nithya et al. | Iris recognition techniques: a literature survey | |
Fatima et al. | A secure personal identification system based on human retina | |
Khokher et al. | Footprint-based personal recognition using scanning technique | |
Araghi et al. | IRIS recognition using neural network | |
Borgen et al. | Visible-spectrum biometric retina recognition | |
CN107862298B (en) | Winking living body detection method based on infrared camera device | |
Burge et al. | Using ear biometrics for passive identification | |
Hájek et al. | Recognition-based on eye biometrics: Iris and retina | |
Aminah et al. | Retracted: Application of Machine Learning Techniques for Diagnosis of Diabetes Based on Iridology | |
CN111444804A (en) | Human body checking method and system based on gait recognition | |
Sigit et al. | Classification of cataract slit-lamp image based on machine learning | |
KR100376415B1 (en) | Pupil acquisition method using eye image | |
CN113033387A (en) | Intelligent assessment method and system for automatically identifying chronic pain degree of old people | |
CN110765925A (en) | Carrier detection and gait recognition method based on improved twin neural network | |
Buddharaju et al. | Face recognition beyond the visible spectrum | |
Betaouaf et al. | A biometric identification algorithm based on retinal blood vessels segmentation using watershed transformation | |
AU2021104108A4 (en) | An automated iris recognition based authentication and gender classification using neural network for cyber security investigation | |
Elangovan et al. | A review: person identification using retinal fundus images | |
Tomeo-Reyes et al. | Input images in iris recognition systems: A case study | |
Abdel-Latif et al. | Achieving Information Security by multi-Modal Iris-Retina Biometric Approach Using Improved Mask R-CNN | |
CN112233769A (en) | Recovery system after suffering from illness based on data acquisition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |