WO2022168252A1 - Procédé d'estimation de taille de corps, dispositif d'estimation de taille de corps et programme - Google Patents
Procédé d'estimation de taille de corps, dispositif d'estimation de taille de corps et programme Download PDFInfo
- Publication number
- WO2022168252A1 WO2022168252A1 PCT/JP2021/004226 JP2021004226W WO2022168252A1 WO 2022168252 A1 WO2022168252 A1 WO 2022168252A1 JP 2021004226 W JP2021004226 W JP 2021004226W WO 2022168252 A1 WO2022168252 A1 WO 2022168252A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- person
- height
- image
- pattern
- skeleton
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 238000012937 correction Methods 0.000 claims description 90
- 238000005452 bending Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 6
- 210000003423 ankle Anatomy 0.000 description 59
- 210000001624 hip Anatomy 0.000 description 49
- 210000002414 leg Anatomy 0.000 description 47
- 210000003127 knee Anatomy 0.000 description 46
- 238000004364 calculation method Methods 0.000 description 36
- 238000010586 diagram Methods 0.000 description 18
- 210000001508 eye Anatomy 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 210000005069 ears Anatomy 0.000 description 8
- 238000012795 verification Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005401 electroluminescence Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000003703 image analysis method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 210000001513 elbow Anatomy 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 210000003739 neck Anatomy 0.000 description 1
- 210000001331 nose Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 210000002832 shoulder Anatomy 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
Definitions
- a method of extracting a rectangle that circumscribes the outline of a person or object in the input image from an input image in which the person or object is captured.
- Mask R-CNN (Region-Convolutional Neural Network) described in Non-Patent Document 2 is an object detection algorithm that performs object detection and segmentation, and extracts the position coordinates of the circumscribing rectangles of people and objects in the input image. can do.
- FIG. 1 is a block diagram showing the functional configuration of a height estimation device 1 according to an embodiment of the present invention
- FIG. FIG. 10 is a diagram for explaining the difference in the Y-axis width of the person frame that accompanies the difference in the posture of the person
- FIG. 11 is a diagram for explaining correction of an estimated height value in the case of pattern 2
- FIG. 11 is a diagram for explaining correction of an estimated height value in the case of pattern 3
- FIG. 10 is a diagram for explaining correction of an estimated height value in the case of pattern 4
- 4 is a flow chart showing the operation of the state determination unit 14 according to the embodiment of the present invention
- It is a figure which shows an example of the content of a determination condition, and the pattern specified when a determination condition is satisfy
- FIG. 1 is a block diagram showing the functional configuration of a height estimation device 1 according to an embodiment of the invention.
- the correction unit 15 corrects the estimated height value by applying the length of the longer left leg, as indicated by the dashed line in the image A41, to the left leg as in the image A32.
- Thresholds A1 to A6 are defined as follows.
- the thresholds A1 to A6 are numerical values used to determine the positional relationship of each part of the skeleton in the input image, as described below.
- Coefficient K1 ⁇ (Right eye Y-axis value - Left eye Y-axis value) / (Right eye X-axis value - Left eye X-axis value) + (Right ear Y-axis value - Left ear Y-axis value) / (Right ear X-axis value - Left Ear X-axis value) ⁇ /2
- Coefficient K2 (Right shoulder Y-axis value ⁇ Left shoulder Y-axis value)/(Right shoulder X-axis value ⁇ Left shoulder X-axis value)
- Coefficient K3 (Right waist Y-axis value ⁇ Left waist Y-axis value)/(Right waist X-axis value ⁇ Left waist X-axis value)
- Coefficient K4 (right ankle Y-axis value ⁇ left ankle Y-axis value)/(right ankle X-axis value ⁇ left ankle X-axis value)
- Coefficient K6 ⁇ (sum of length from right hip to right knee and length from right knee to right ankle) ⁇ (sum of length from left hip to left knee and length from left knee to left ankle ) ⁇ / ⁇ (Sum of length from right hip to right knee and length from right knee to right ankle) + (sum of length from left hip to left knee and length from left knee to left ankle) ) ⁇
- the values of the length from the right hip to the right knee, the length from the right knee to the right ankle, the length from the left hip to the left knee, and the length from the left knee to the left ankle are as follows.
- the state determination unit 14 performs the following threshold determination using thresholds A1 to A6 and coefficients K1 to K6 calculated based on the above definitions.
- the following threshold judgments 1 to 6 are judgment formulas for judging the posture pattern of the person in the input image by comparing the thresholds A1 to A6 and the coefficients K1 to K6.
- step S1406 determines whether or not the determination condition 4 is satisfied based on the determination results of the threshold determinations 1 to 6.
- judgment condition 4 satisfies threshold judgments 3 to 6 but does not satisfy threshold judgments 1 and 2.
- step S1408: YES the state determination unit 14 determines that the posture of the person in the input image is pattern 4 (that is, the person bends his/her body sideways). posture) (step S1409).
- FIG. 7 is a diagram summarizing the details of each of the determination conditions 1 to 4 and the patterns identified when the determination conditions 1 to 4 are satisfied.
- the correction value B3 is obtained by curve approximation or linear approximation, which is selectively used according to the characteristics of the bending of the skeleton corresponding to the pattern.
- curve approximation is used to calculate the length of the upper body (here, from the nose to the middle of both hips)
- linear approximation is used to calculate the length of the lower body (here, from the waist to the ankle). configuration.
- the correction unit 15 outputs the correction value, B3, and information indicating the pattern to the height calculation unit 18 (step S1503).
- the operation of the correction unit 15 shown in the flowchart of FIG. 8 is completed.
- FIG. 9 is a diagram summarizing the correction processing (methods of calculating the calculated values B1 and B2 and the correction value B3, etc.) by the correcting unit 15 for each pattern described above.
- the height calculator 18 acquires the correction value and the information indicating the pattern output from the corrector 15 .
- the height calculator 18 also acquires the XY coordinates of the object frame, the height information, and the XY coordinates of the person frame output from the object matching unit 17 . (Step S1801).
- the object verification unit 17 acquires information indicating the object name output from the person/object extraction unit 16, the XY coordinates of the object frame, and the XY coordinates of the person frame (step S1701).
- the object matching unit 17 acquires the height value (height information) of the object associated with the object name included in the object data 110 detected by matching (step S1703).
- the height estimation device 1 extracts the position of the skeleton of the person from an image in which the person and the object are captured, and calculates the posture pattern of the person based on the positional relationship of each part of the skeleton. judge.
- the height estimation device 1 estimates the height of a person based on a correction value calculated based on a predetermined arithmetic expression for each pattern, the actual height of the object, and the height of the object and the height of the person in the image. Estimate your actual height.
- the height estimation apparatus 1 according to the present embodiment can more accurately estimate the height of a person from the input image even when the person in the input image is not in an upright posture. can.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
La présente invention concerne un procédé d'estimation de taille de corps qui comprend : une étape d'acquisition d'image consistant à acquérir une image capturée d'une personne et d'un objet ; une étape d'extraction de squelette consistant à extraire la position de squelette de la personne dans l'image ; une étape de détermination consistant à déterminer le modèle de pose de la personne sur la base de la relation de position entre les parties du squelette ; et une étape d'estimation consistant à estimer la taille de corps réelle de la personne sur la base de la taille de corps de la personne dans l'image et d'une valeur corrigée obtenue par une approximation de courbe ou une approximation linéaire qui est utilisée en fonction de caractéristiques de courbure du squelette, les caractéristiques de courbure correspondant au modèle.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/004226 WO2022168252A1 (fr) | 2021-02-05 | 2021-02-05 | Procédé d'estimation de taille de corps, dispositif d'estimation de taille de corps et programme |
JP2022579251A JPWO2022168252A1 (fr) | 2021-02-05 | 2021-02-05 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/004226 WO2022168252A1 (fr) | 2021-02-05 | 2021-02-05 | Procédé d'estimation de taille de corps, dispositif d'estimation de taille de corps et programme |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022168252A1 true WO2022168252A1 (fr) | 2022-08-11 |
Family
ID=82740993
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/004226 WO2022168252A1 (fr) | 2021-02-05 | 2021-02-05 | Procédé d'estimation de taille de corps, dispositif d'estimation de taille de corps et programme |
Country Status (2)
Country | Link |
---|---|
JP (1) | JPWO2022168252A1 (fr) |
WO (1) | WO2022168252A1 (fr) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008286638A (ja) * | 2007-05-17 | 2008-11-27 | Sogo Keibi Hosho Co Ltd | 身長推定装置および身長推定方法 |
US20090232353A1 (en) * | 2006-11-10 | 2009-09-17 | University Of Maryland | Method and system for markerless motion capture using multiple cameras |
WO2019082376A1 (fr) * | 2017-10-27 | 2019-05-02 | 株式会社アシックス | Système d'évaluation d'état de mouvement, dispositif d'évaluation d'état de mouvement, serveur d'évaluation d'état de mouvement, procédé d'évaluation d'état de mouvement et programme d'évaluation d'état de mouvement |
-
2021
- 2021-02-05 WO PCT/JP2021/004226 patent/WO2022168252A1/fr active Application Filing
- 2021-02-05 JP JP2022579251A patent/JPWO2022168252A1/ja active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090232353A1 (en) * | 2006-11-10 | 2009-09-17 | University Of Maryland | Method and system for markerless motion capture using multiple cameras |
JP2008286638A (ja) * | 2007-05-17 | 2008-11-27 | Sogo Keibi Hosho Co Ltd | 身長推定装置および身長推定方法 |
WO2019082376A1 (fr) * | 2017-10-27 | 2019-05-02 | 株式会社アシックス | Système d'évaluation d'état de mouvement, dispositif d'évaluation d'état de mouvement, serveur d'évaluation d'état de mouvement, procédé d'évaluation d'état de mouvement et programme d'évaluation d'état de mouvement |
Also Published As
Publication number | Publication date |
---|---|
JPWO2022168252A1 (fr) | 2022-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9031286B2 (en) | Object detection device and object detection method | |
US9480417B2 (en) | Posture estimation device, posture estimation system, and posture estimation method | |
US10600207B2 (en) | Posture state estimation apparatus and posture state estimation method | |
US9047507B2 (en) | Upper-body skeleton extraction from depth maps | |
US9262671B2 (en) | Systems, methods, and software for detecting an object in an image | |
US5995639A (en) | Apparatus for identifying person | |
JP4830650B2 (ja) | 追跡装置 | |
US9262674B2 (en) | Orientation state estimation device and orientation state estimation method | |
Kishore et al. | Estimation of yoga postures using machine learning techniques | |
CN114616588A (zh) | 图像处理装置、图像处理方法以及存储图像处理程序的非暂时性计算机可读介质 | |
US10496874B2 (en) | Facial detection device, facial detection system provided with same, and facial detection method | |
US20190065900A1 (en) | Information processing device, information processing program, and information processing method | |
Cai et al. | Accurate eye center localization via hierarchical adaptive convolution | |
US20220366716A1 (en) | Person state detection apparatus, person state detection method, and non-transitory computer readable medium storing program | |
US10824868B2 (en) | Image processing for determining relationships between tracked objects | |
Yu et al. | 3D facial motion tracking by combining online appearance model and cylinder head model in particle filtering | |
CN111784660B (zh) | 一种用于人脸图像的正脸程度的分析方法和系统 | |
Hata et al. | Detection of distant eye-contact using spatio-temporal pedestrian skeletons | |
WO2022168252A1 (fr) | Procédé d'estimation de taille de corps, dispositif d'estimation de taille de corps et programme | |
US11527090B2 (en) | Information processing apparatus, control method, and non-transitory storage medium | |
CN110826495A (zh) | 基于面部朝向的身体左右肢体一致性跟踪判别方法及系统 | |
EP4053790A1 (fr) | Dispositif de traitement d'image, procédé de traitement d'image et support non-transitoire lisible par ordinateur stockant un programme de traitement d'image | |
Ng et al. | Multi-view gait based human identification system with covariate analysis. | |
JP7136344B2 (ja) | カメラの較正方法、カメラ及びプログラム | |
KR101785661B1 (ko) | 회색 값 분산을 이용한 얼굴 윤곽 인식방법 및 그 장치 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21924647 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022579251 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21924647 Country of ref document: EP Kind code of ref document: A1 |