CN111611928A - Height and body size measuring method based on monocular vision and key point identification - Google Patents

Height and body size measuring method based on monocular vision and key point identification Download PDF

Info

Publication number
CN111611928A
CN111611928A CN202010438604.XA CN202010438604A CN111611928A CN 111611928 A CN111611928 A CN 111611928A CN 202010438604 A CN202010438604 A CN 202010438604A CN 111611928 A CN111611928 A CN 111611928A
Authority
CN
China
Prior art keywords
height
human body
key
user
points
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.)
Granted
Application number
CN202010438604.XA
Other languages
Chinese (zh)
Other versions
CN111611928B (en
Inventor
黄明阳
董静雅
郑泽宇
桂珺
付殿峥
高原
杨天吉
张力超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zheng Zeyu
Original Assignee
Hangzhou Zhiron Intelligent Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Zhiron Intelligent Technology Co ltd filed Critical Hangzhou Zhiron Intelligent Technology Co ltd
Priority to CN202010438604.XA priority Critical patent/CN111611928B/en
Publication of CN111611928A publication Critical patent/CN111611928A/en
Application granted granted Critical
Publication of CN111611928B publication Critical patent/CN111611928B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • A61B5/1072—Measuring physical dimensions, e.g. size of the entire body or parts thereof measuring distances on the body, e.g. measuring length, height or thickness
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • A61B5/1077—Measuring of profiles
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • 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
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Surgery (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Human Computer Interaction (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Geometry (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention relates to a height and body size measuring method based on monocular vision and key point identification, which can be generally applied to body measuring equipment based on a monocular camera. According to the method, the height and body size of a user are measured through camera image acquisition and image processing, a height measuring module based on matching of a height estimation model and a template, and a body size calculating module based on key feature points of a human body. The measuring method of the invention is based on monocular vision, so the cost of the equipment can be greatly reduced; the height measurement module abandons the traditional monocular vision method of obtaining model parameters through physical calibration, and updates parameters aiming at different users through an iterative template matching method, so that equipment does not need to be additionally provided with a calibration reference object, the equipment has stronger flexibility, and meanwhile, compared with the fixed parameter method, the height measurement module has stronger parameter adaptability and accuracy.

Description

Height and body size measuring method based on monocular vision and key point identification
Technical Field
The invention relates to a height and body size measuring method based on monocular vision and key point identification.
Background
In order to acquire height information of a human body, a depth camera is often adopted by the current body measuring equipment to acquire depth information of a human body image. However, depth cameras are expensive and so to reduce cost, monocular cameras have become one option for volumetric devices. The measuring equipment based on the monocular camera usually needs to calibrate the parameters of the measurement model by means of a reference object, so that the flexibility of the equipment is limited to a certain extent; the calibrated parameters are fixed parameters, so the method has no robustness. Under the background, the invention realizes the self-adaptive change of the model parameters in a key characteristic point template matching mode, enhances the robustness of the model while reducing the cost by utilizing a monocular camera, and is generally suitable for volume equipment with low cost and high robustness.
Disclosure of Invention
The invention aims to provide a height and body size measuring method based on monocular vision and key point identification, which reduces the cost of a measuring device and improves the robustness of a measuring result of the device.
The invention adopts the following measurement technical scheme:
1. a height and body size measuring method based on monocular vision and key point identification mainly comprises the following steps:
s1 data acquisition unit: when the correct posture of the user is detected, the camera of the equipment can automatically acquire the picture of the whole body of the user;
s2 image processing unit: extracting edge contour points of the human body by combining a semantic segmentation model, detecting and identifying key nodes of the human body through key nodes of the human body, and further expanding key characteristic points of the human body according to the contour points and the key nodes;
s3 height calculation unit: matching the user with the template, adaptively updating to obtain height calculation model parameters of the user, and calculating the real height of the user through the height calculation model after the parameters are updated;
s4 body size calculation unit: and calculating each size data by combining the key feature points of the user obtained in the step S2 and the height information obtained in the step S3.
2. The further technical scheme of the invention is as follows: step S1 also includes the following contents:
1) detecting a human body in real time, and detecting an anchor point frame area of the human body;
2) detecting key points of human body in real time, and detecting key points of human body (key points of arms, legs, head and trunk);
3) and judging whether the posture of the user is correct or not according to the distribution condition of the key points of the human body in the anchor point frame. The human body standard posture: the front part is seen visually, and the body is opposite to the camera; the two arms are unfolded about 30 degrees to 45 degrees, and the two legs are separated to have the same width of the feet and the shoulders;
the advantage is that the user's gesture is automatically grabbed without additional manual operations.
3. The further technical scheme of the invention is as follows: step S2 also includes the following contents:
1) firstly, carrying out sparse processing and smoothing noise reduction processing on the coordinates of the edge contour points of the human body, wherein the sparse processing is to adaptively select a sparse coefficient according to the area of a human body region in an image;
2) according to the structural features of body parts such as shoulders, chests, waists, middle waists and hips of the human body and the detected key node coordinates of the human body, the vertex coordinates of the human body and other key feature points related to the body size, such as waist edge points and hip edge points, are found in the processed edge contour points in an expanding manner.
4. The further technical solution of the present invention is that the step S3 further includes the following steps:
1) collecting sample data: in order to avoid the traditional calibration mode, M groups of real person feature points (M reference values are larger than 10) and height data are collected as a sample data set at first, height calculation model parameters are initialized through the sample data, and an external auxiliary calibration reference object is not needed. The secondary recording is not needed after the primary sample collection is realized;
2) obtaining a height calculation model and parameters: (1) a height calculation model: the precondition of the height calculation model is that the plane of the camera lens on the device is perpendicular to the ground. In the image coordinate system, the longitudinal coordinate of the top of the human head in the image is
Figure 100002_DEST_PATH_IMAGE002
The longitudinal coordinate of the key point of the heel of the human body is
Figure 100002_DEST_PATH_IMAGE004
The height of the human body in the image coordinate system
Figure 100002_DEST_PATH_IMAGE006
The ordinate of the vanishing line in the image coordinate system is
Figure 100002_DEST_PATH_IMAGE008
The height of the disappearance line from the heel of the human body in the image coordinate system is
Figure 100002_DEST_PATH_IMAGE010
(ii) a In the world coordinate system, the real height of the user is
Figure 100002_DEST_PATH_IMAGE012
The height of the vanishing line (virtual line, actually absent) in the world coordinate system is
Figure 100002_DEST_PATH_IMAGE014
(the reference height may be a lens-to-ground height). (2) According to the perspective principle of
Figure 100002_DEST_PATH_IMAGE016
I.e. by
Figure 100002_DEST_PATH_IMAGE018
(ii) a Wherein
Figure 100002_DEST_PATH_IMAGE020
In order to be a hyper-parameter,
Figure 100002_DEST_PATH_IMAGE022
the real height is known (can be obtained according to the coordinates of key feature points in the image)
Figure 100002_DEST_PATH_IMAGE012A
Is a target value; (3) acquiring parameters: collecting a certain amount of sample data of real height and picture of human body, and updating hyper-parameters through a regression model
Figure 100002_DEST_PATH_IMAGE020A
The parameter update of the height calculation model is completed once, and then the height calculation model can be updated
Figure 100002_DEST_PATH_IMAGE018A
Directly calculating to obtain the real height of the human body
Figure 100002_DEST_PATH_IMAGE012AA
；
3) Template initialization and height calculation model parameter initialization: performing template matching on key feature points of a user and key feature points of a sample set to obtain an array sample template subset with high matching degree, namely an initial template sample; initializing height calculation model parameters through the initial template sample;
4) iterative update of height calculation model parameters:
after the height calculation model parameters are updated every time, the height of the user is estimated through the model and matched with the template, the array sample with the higher matching degree is found to serve as the updated template sample, and the model parameters are updated according to the template sample. This process is iterated up to n times (reference value n = 3).
Drawings
FIG. 1 is an application of a height and body size measurement method based on monocular vision and key point identification to a measuring device equipped with a monocular camera.
FIG. 2 shows a flow of height measurement and body size calculation.
Detailed description of the preferred embodiment
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the patent embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The first step is as follows: inputting a sample data set: in the data preparation, firstly, sample data (including key characteristic point information and height information of a human body) of a real human body is input on equipment to be used as a matching template to be determined. The advantages of collecting samples in advance: the method replaces the traditional parameter acquisition mode of a fixed reference object, can adaptively generate height measurement model parameters suitable for users through different template sets, and improves the adaptivity of the model parameters. And the recording is not required to be carried out again after the primary recording is realized.
The second step is that: inputting a user picture: when an actual user performs measurement, the user stands according to a required posture, the camera can automatically judge the correctness of the posture according to the distribution of key characteristic points in the human body anchor point frame, and a correct posture image is captured. The human body standard posture: the front part is seen visually, and the body is opposite to the camera; the arms are unfolded about 30 degrees to 45 degrees, and the legs are separated to have the same width as the shoulders. The mode of detecting the human body through the front end has the following advantages: the image acquisition process is automatically completed without additional manual operation.
The third step: calculating the height of the user: and matching the user with the template, adaptively updating to obtain the height calculation model parameters of the user, and calculating the real height of the user through the height calculation model after the parameters are updated. The method has the advantages that: the fixed model parameters are banned, and the height model parameters of different users are acquired in a self-adaptive mode, so that the robustness and the accuracy are high.
The fourth step: calculating a body, and firstly performing sparse processing and smooth noise reduction processing on the coordinates of the edge contour points of the human body, wherein the sparse processing is to adaptively select a sparse coefficient according to the area of a human body region in an image; according to the structural features of body parts such as shoulders, chests, waists, middle waists and hips of the human body and the detected key node coordinates of the human body, the vertex coordinates of the human body and other key feature points related to the body size, such as waist edge points and hip edge points, are found in the processed edge contour points in an expanding manner. The human body contour sparse method adopts a self-adaptive sparse method, and a proper sparse coefficient is self-adaptively selected according to the size of a human body region, so that the method has the advantages that: the reasonable number of the contour points is ensured according to the distance between the human body and the lens, the calculated amount when the key feature points are searched in the contour points is saved, and meanwhile, the precision of the key feature points is ensured.
The fifth step: and calculating the body size of the user according to the key feature points and the height information of the user.

Claims (5)

1. A height and body size measuring method based on monocular vision and key point identification is characterized in that:
s1 data acquisition unit: when the correct posture of the user is detected, the camera of the equipment can automatically acquire the picture of the whole body of the user;
s2 image processing unit: extracting edge contour points of the human body by combining a semantic segmentation model, detecting and identifying key nodes of the human body through key nodes of the human body, and further expanding key characteristic points of the human body according to the contour points and the key nodes;
s3 height calculation unit: matching the user with the template, adaptively updating to obtain height calculation model parameters of the user, and calculating the real height of the user through the height calculation model after the parameters are updated;
s4 body size calculation unit: and calculating each size data by combining the key feature points of the user obtained in the step S2 and the height information obtained in the step S3.
2. The method of claim 1, the detecting of user gesture correctness in step S1 being:
1) detecting a human body in real time, and detecting an anchor point frame area of the human body;
2) detecting key points of human body in real time, and detecting key points of human body (key points of arms, legs, head and trunk);
3) judging whether the posture of the user is correct or not according to the distribution condition of the human body key points in the anchor point frame, wherein the human body standard posture is as follows: the front part is seen visually, and the body is opposite to the camera; the arms are unfolded about 30 degrees to 45 degrees, and the legs are separated to have the same width as the shoulders.
3. The method according to claim 1, wherein the step S2 of expanding human key feature points is characterized in that,
1) firstly, carrying out sparse processing and smoothing noise reduction processing on the coordinates of the edge contour points of the human body, wherein the sparse processing is to adaptively select a sparse coefficient according to the area of a human body region in an image;
2) according to the structural features of body parts such as shoulders, chests, waists, middle waists and hips of the human body and the detected key node coordinates of the human body, the vertex coordinates of the human body and other key feature points related to the body size, such as waist edge points and hip edge points, are found in the processed edge contour points in an expanding manner.
4. The method according to claim 1, wherein said step S3 is characterized by 1) collecting sample data: in order to avoid a traditional calibration mode, M groups of real person feature points (M reference values are more than 10) and height data are collected as a sample data set at first, height calculation model parameters are initialized through the sample data, an external auxiliary calibration reference object is not needed, and the fact that the sample is not needed to be input again after one-time sample collection is achieved;
2) obtaining a height calculation model and parameters: (1) a height calculation model: the precondition of the height calculation model is that the plane of the camera lens on the device is perpendicular to the ground.
5. In the image coordinate system, the longitudinal coordinate of the top of the human head in the image is
Figure DEST_PATH_IMAGE002
The longitudinal coordinate of the key point of the heel of the human body is
Figure DEST_PATH_IMAGE004
The height of the human body in the image coordinate system
Figure DEST_PATH_IMAGE006
The ordinate of the vanishing line in the image coordinate system is
Figure DEST_PATH_IMAGE008
The height of the disappearance line from the heel of the human body in the image coordinate system is
Figure DEST_PATH_IMAGE010
(ii) a In the world coordinate system, the real height of the user is
Figure DEST_PATH_IMAGE012
The height of the vanishing line (virtual line, actually absent) in the world coordinate system is
Figure DEST_PATH_IMAGE014
(the reference height may be a lens-to-ground height); (2) according to the perspective principle of
Figure DEST_PATH_IMAGE016
I.e. by
Figure DEST_PATH_IMAGE018
(ii) a Wherein
Figure DEST_PATH_IMAGE020
In order to be a hyper-parameter,
Figure DEST_PATH_IMAGE022
it is known (can be based on key features in the image)Point coordinates obtained), true height
Figure DEST_PATH_IMAGE012A
Is a target value; (3) acquiring parameters: collecting a certain amount of sample data of real height and picture of human body, and updating hyper-parameters through a regression model
Figure DEST_PATH_IMAGE020A
The parameter update of the height calculation model is completed once, and then the height calculation model can be updated
Figure DEST_PATH_IMAGE018A
Directly calculating to obtain the real height of the human body
Figure DEST_PATH_IMAGE012AA
；
3) Template initialization and height calculation model parameter initialization: performing template matching on key feature points of a user and key feature points of a sample set to obtain an array sample template subset with high matching degree, namely an initial template sample; initializing height calculation model parameters through the initial template sample;
4) iterative update of height calculation model parameters:
and after the height calculation model parameters are updated every time, estimating the height of the user through the model and matching the height with the template, finding an array sample with higher matching degree as an updated template sample, updating the model parameters according to the template sample, and iterating the process for n times (the reference value n = 3).
CN202010438604.XA 2020-05-22 2020-05-22 Height and body size measuring method based on monocular vision and key point identification Active CN111611928B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010438604.XA CN111611928B (en) 2020-05-22 2020-05-22 Height and body size measuring method based on monocular vision and key point identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010438604.XA CN111611928B (en) 2020-05-22 2020-05-22 Height and body size measuring method based on monocular vision and key point identification

Publications (2)

Publication Number Publication Date
CN111611928A true CN111611928A (en) 2020-09-01
CN111611928B CN111611928B (en) 2023-07-28

Family

ID=72199472

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010438604.XA Active CN111611928B (en) 2020-05-22 2020-05-22 Height and body size measuring method based on monocular vision and key point identification

Country Status (1)

Country Link
CN (1) CN111611928B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111930240A (en) * 2020-09-17 2020-11-13 平安国际智慧城市科技股份有限公司 Motion video acquisition method and device based on AR interaction, electronic equipment and medium
CN113763453A (en) * 2021-09-06 2021-12-07 北京云数工场数据科技有限公司 Artificial intelligence energy system and method

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140204205A1 (en) * 2013-01-21 2014-07-24 Kapsch Trafficcom Ag Method for measuring the height profile of a vehicle passing on a road
US20150154453A1 (en) * 2012-09-05 2015-06-04 Body Pass Ltd. System and method for deriving accurate body size measures from a sequence of 2d images
CN105930581A (en) * 2016-04-20 2016-09-07 北京长城华冠汽车科技股份有限公司 Method and device for determining vertical distance between steering wheel center and heel point
CN105956539A (en) * 2016-04-27 2016-09-21 武汉大学 Method for height measurement of human body based on background modeling and binocular vision
CN107041585A (en) * 2017-03-07 2017-08-15 上海优裁信息技术有限公司 The measuring method of human dimension
CN107507213A (en) * 2016-06-13 2017-12-22 北京理工大学 A kind of method and device based on end point extraction image information
CN108596888A (en) * 2018-04-19 2018-09-28 李富平 A kind of Human Height Real-time Generation based on monocular image
JP2018195050A (en) * 2017-05-17 2018-12-06 株式会社デンソーアイティーラボラトリ Object detecting device, object detecting method, and program
CN109938737A (en) * 2019-03-01 2019-06-28 苏州博慧智能科技有限公司 A kind of human body body type measurement method and device based on deep learning critical point detection
CN110263662A (en) * 2019-05-28 2019-09-20 北京智形天下科技有限责任公司 A kind of human body contour outline key point and key position recognition methods based on classification
US20200126295A1 (en) * 2018-10-22 2020-04-23 The Hong Kong Polytechnic University Method and/or system for reconstructing from images a personalized 3d human body model and thereof

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150154453A1 (en) * 2012-09-05 2015-06-04 Body Pass Ltd. System and method for deriving accurate body size measures from a sequence of 2d images
US20140204205A1 (en) * 2013-01-21 2014-07-24 Kapsch Trafficcom Ag Method for measuring the height profile of a vehicle passing on a road
CN105930581A (en) * 2016-04-20 2016-09-07 北京长城华冠汽车科技股份有限公司 Method and device for determining vertical distance between steering wheel center and heel point
CN105956539A (en) * 2016-04-27 2016-09-21 武汉大学 Method for height measurement of human body based on background modeling and binocular vision
CN107507213A (en) * 2016-06-13 2017-12-22 北京理工大学 A kind of method and device based on end point extraction image information
CN107041585A (en) * 2017-03-07 2017-08-15 上海优裁信息技术有限公司 The measuring method of human dimension
JP2018195050A (en) * 2017-05-17 2018-12-06 株式会社デンソーアイティーラボラトリ Object detecting device, object detecting method, and program
CN108596888A (en) * 2018-04-19 2018-09-28 李富平 A kind of Human Height Real-time Generation based on monocular image
US20200126295A1 (en) * 2018-10-22 2020-04-23 The Hong Kong Polytechnic University Method and/or system for reconstructing from images a personalized 3d human body model and thereof
CN109938737A (en) * 2019-03-01 2019-06-28 苏州博慧智能科技有限公司 A kind of human body body type measurement method and device based on deep learning critical point detection
CN110263662A (en) * 2019-05-28 2019-09-20 北京智形天下科技有限责任公司 A kind of human body contour outline key point and key position recognition methods based on classification

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
SAHAR ASHMAWI.ET.: "FITME: BODY MEASUREMENT ESTIMATIONS USING MACHINE LEARNING METHOD", 《PROCEDIA COMPUTER SCIENCE 》, vol. 163, pages 209 - 217, XP086008848, DOI: 10.1016/j.procs.2019.12.102 *
杨泷迪: "基于红外图像的人体参数测量技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 3, pages 138 - 1353 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111930240A (en) * 2020-09-17 2020-11-13 平安国际智慧城市科技股份有限公司 Motion video acquisition method and device based on AR interaction, electronic equipment and medium
CN113763453A (en) * 2021-09-06 2021-12-07 北京云数工场数据科技有限公司 Artificial intelligence energy system and method

Also Published As

Publication number Publication date
CN111611928B (en) 2023-07-28

Similar Documents

Publication Publication Date Title
CN111156984B (en) Monocular vision inertia SLAM method oriented to dynamic scene
CN109118528A (en) Singular value decomposition image matching algorithm based on area dividing
CN107358629B (en) Indoor mapping and positioning method based on target identification
CN111914642B (en) Pedestrian re-identification method, device, equipment and medium
US10460471B2 (en) Camera pose estimating method and system
JP2016091108A (en) Human body portion detection system and human body portion detection method
CN107492107B (en) Object identification and reconstruction method based on plane and space information fusion
CN107316326A (en) Applied to disparity map computational methods of the binocular stereo vision based on side and device
CN106296613B (en) A kind of Dual Energy Subtraction method based on DR machine
CN111611928A (en) Height and body size measuring method based on monocular vision and key point identification
CN108335319A (en) A kind of image angle point matching process based on adaptive threshold and RANSAC
CN109725721B (en) Human eye positioning method and system for naked eye 3D display system
CN109740659B (en) Image matching method and device, electronic equipment and storage medium
CN105279522A (en) Scene object real-time registering method based on SIFT
CN101765019A (en) Stereo matching algorithm for motion blur and illumination change image
US11461914B2 (en) Measuring surface distances on human bodies
CN105654479A (en) Multispectral image registering method and multispectral image registering device
CN111047553B (en) Characteristic point positioning method for non-contact human body parameter measurement
Ward et al. A model-based approach to recovering the structure of a plant from images
CN117152787A (en) Character clothing recognition method, device, equipment and readable storage medium
Tordoff et al. Head pose estimation for wearable robot control.
JP7136344B2 (en) Camera calibration method, camera and program
CN113808256A (en) High-precision holographic human body reconstruction method combined with identity recognition
CN113887279A (en) Pedestrian re-identification method with half-length being blocked and related device
Liu et al. New anti-blur and illumination-robust combined invariant for stereo vision in human belly reconstruction

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
TA01 Transfer of patent application right

Effective date of registration: 20230703

Address after: 2-1-1, No. 5-533, Langyun Street, Hunnan District, Shenyang, Liaoning 110623

Applicant after: Zheng Zeyu

Address before: Room 101-4, building 1, Juhua building, 6 Longzhou Road, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province 310000

Applicant before: Hangzhou Zhiron Intelligent Technology Co.,Ltd.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant