CN104463947A - Human body skeleton modeling method - Google Patents
Human body skeleton modeling method Download PDFInfo
- Publication number
- CN104463947A CN104463947A CN201310602272.4A CN201310602272A CN104463947A CN 104463947 A CN104463947 A CN 104463947A CN 201310602272 A CN201310602272 A CN 201310602272A CN 104463947 A CN104463947 A CN 104463947A
- Authority
- CN
- China
- Prior art keywords
- human body
- joint
- limbs
- skeleton
- modeling method
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Abstract
The invention discloses a human body skeleton modeling method, and relates to the technical field of human body skeleton modeling. The modeling method comprises the steps that sensors are installed on the human body joints and connected with a detecting host; action catching is carried out through the sensor arrays installed on the joints, fitting is carried out on data points in a video to form a spline; the edge contour curve is processed through a smooth and optimization algorithm of the spline; the limbs are abstracted into simple rigid geometric solids according to the layer structure of the joint connecting bodies of the human body, and a sample of a human body skeleton model is established through a VRML; skeleton models of the limbs can be obtained by changing the sample model. The human body skeleton features are analyzed and recognized through the action recognizing technology based on the video, operation is easy, the quick and accurate modeling purpose can be achieved, and online analyzing is achieved.
Description
Technical field:
The present invention relates to skeleton modeling technique field, be specifically related to a kind of skeleton modeling method.
Background technology:
In interpersonal reciprocal process between people, vision is most important information, and people can be helped to obtain rapidly some key features and the fact.Have a wide range of applications in fields such as wisdom video monitoring, abnormal operation identification, man-machine interaction and virtual technologies, current generation, the research of current human action identification aspect mainly concentrates on the aspect such as the structure analysis of action human body, the tracking of human action target.
The analysis of human action and identification are one of the important issue in the field such as existing research computer vision and figure identification.The action of the mankind is made up of continuous static posture, because action is originally in space and the high-dimensional information time with quite complexity, and action may produce oneself covers (Self-Occlusion) phenomenon, therefore accurately will analyze action at general 2D video camera still has its bottleneck.At expression Whole Body this respect, instinctively, represent more more directly perceived than employment external type profile with human skeleton.At present, insider uses Kinect somatosensory video camera to carry out human body tracking and motion capture, and then the joint three-dimensional rectangular coordinate information finding out human skeleton is to carry out human action's identification.
But there is the problem of subsequent processes complexity, length consuming time in the body motion information analytic system of traditional photography principle, can not on-line analysis, and current skeleton modeling method more complicated, cost is higher, can not reach the object of rapid modeling.
Summary of the invention:
The object of this invention is to provide a kind of skeleton modeling method, it is by the action recognition technology based on video, carries out parsing identify skeleton feature, simple to operate, can reach object that is rapid, accurate modeling, achieve on-line analysis.
In order to solve the problem existing for background technology, the present invention is by the following technical solutions: its modeling method is: 1, sensor installation on each joint of human body, is connected by each sensor with detection main frame; 2, the sensor array by being arranged on each joint carries out motion capture, carries out matching form SPL to data point in video; 3, fairing, the optimized algorithm process edge contour curve of curve is recycled; 4, according to the joint connector hierarchical structure of human body, by abstract for each limbs be simple rigidity geometry entity, and use the sample of VRML structure human skeleton model; 5, the skeleton model of each limbs all can obtain through conversion on the basis of this sample pattern.
Principle of the present invention is: detect in main frame and adopt joint single-point identification method, limbs multiple spot recognition technology and monumented point image procossing new method, when carrying out human motion image and detecting, need only at tested joint or limbs privileged site mark special sign point, and sensor installation, just can obtain the locus in joint.
The present invention, by the action recognition technology based on video, carries out parsing to skeleton feature and identifies, simple to operate, can reach object that is rapid, accurate modeling, achieve on-line analysis.
Embodiment:
This embodiment is by the following technical solutions: its modeling method is: 1, sensor installation on each joint of human body, is connected by each sensor with detection main frame; 2, the sensor array by being arranged on each joint carries out motion capture, carries out matching form SPL to data point in video; 3, fairing, the optimized algorithm process edge contour curve of curve is recycled; 4, according to the joint connector hierarchical structure of human body, by abstract for each limbs be simple rigidity geometry entity, and use the sample of VRML structure human skeleton model; 5, the skeleton model of each limbs all can obtain through conversion on the basis of this sample pattern.
The principle of this embodiment is: detect in main frame and adopt joint single-point identification method, limbs multiple spot recognition technology and monumented point image procossing new method, when carrying out human motion image and detecting, need only at tested joint or limbs privileged site mark special sign point, and sensor installation, just can obtain the locus in joint.
This embodiment, by the action recognition technology based on video, is carried out parsing to skeleton feature and is identified, simple to operate, can reach object that is rapid, accurate modeling, achieve on-line analysis.
Claims (2)
1. a skeleton modeling method, is characterized in that its modeling method is: (1), sensor installation on each joint of human body, is connected by each sensor with detection main frame; (2), by the sensor array being arranged on each joint carry out motion capture, matching is carried out to data point in video and forms SPL; (3) fairing, the optimized algorithm process edge contour curve of curve, is recycled; (4), according to the joint connector hierarchical structure of human body, by abstract for each limbs be simple rigidity geometry entity, and use the sample of VRML structure human skeleton model; (5), the skeleton model of each limbs all can obtain through conversion on the basis of this sample pattern.
2. a skeleton modeling method, it is characterized in that its principle is: detect in main frame and adopt joint single-point identification method, limbs multiple spot recognition technology and monumented point image procossing new method, when carrying out human motion image and detecting, need only at tested joint or limbs privileged site mark special sign point, and sensor installation, just can obtain the locus in joint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310602272.4A CN104463947A (en) | 2013-11-25 | 2013-11-25 | Human body skeleton modeling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310602272.4A CN104463947A (en) | 2013-11-25 | 2013-11-25 | Human body skeleton modeling method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104463947A true CN104463947A (en) | 2015-03-25 |
Family
ID=52909929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310602272.4A Pending CN104463947A (en) | 2013-11-25 | 2013-11-25 | Human body skeleton modeling method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104463947A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104952110A (en) * | 2015-07-08 | 2015-09-30 | 安徽瑞宏信息科技有限公司 | Human skeleton modeling method |
| CN107403463A (en) * | 2016-05-18 | 2017-11-28 | 西门子保健有限责任公司 | The human body with nonrigid portions represents in imaging systems |
| CN112149531A (en) * | 2020-09-09 | 2020-12-29 | 武汉科技大学 | Human skeleton data modeling method in behavior recognition |
| CN112720489A (en) * | 2020-12-25 | 2021-04-30 | 华南理工大学 | Unitized combined modeling method, system and medium for wearable robot and human body |
| CN113268626A (en) * | 2021-05-26 | 2021-08-17 | 中国人民武装警察部队特种警察学院 | Data processing method and device, electronic equipment and storage medium |
| CN113268626B (en) * | 2021-05-26 | 2024-04-26 | 中国人民武装警察部队特种警察学院 | Data processing method, device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1231753A (en) * | 1996-08-14 | 1999-10-13 | 挪拉赫梅特·挪利斯拉莫维奇·拉都色夫 | Method for following and imaging a subject's three-dimensional position and orientation, method for presenting a virtual space to a subject,and systems for implementing said methods |
| US6738065B1 (en) * | 1999-08-10 | 2004-05-18 | Oshri Even-Zohar | Customizable animation system |
| US20090220124A1 (en) * | 2008-02-29 | 2009-09-03 | Fred Siegel | Automated scoring system for athletics |
| CN101579238A (en) * | 2009-06-15 | 2009-11-18 | 吴健康 | Human motion capture three dimensional playback system and method thereof |
| CN103135765A (en) * | 2013-02-20 | 2013-06-05 | 兰州交通大学 | Human motion information capturing system based on micro-mechanical sensor |
-
2013
- 2013-11-25 CN CN201310602272.4A patent/CN104463947A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1231753A (en) * | 1996-08-14 | 1999-10-13 | 挪拉赫梅特·挪利斯拉莫维奇·拉都色夫 | Method for following and imaging a subject's three-dimensional position and orientation, method for presenting a virtual space to a subject,and systems for implementing said methods |
| US6738065B1 (en) * | 1999-08-10 | 2004-05-18 | Oshri Even-Zohar | Customizable animation system |
| US20090220124A1 (en) * | 2008-02-29 | 2009-09-03 | Fred Siegel | Automated scoring system for athletics |
| CN101579238A (en) * | 2009-06-15 | 2009-11-18 | 吴健康 | Human motion capture three dimensional playback system and method thereof |
| CN103135765A (en) * | 2013-02-20 | 2013-06-05 | 兰州交通大学 | Human motion information capturing system based on micro-mechanical sensor |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104952110A (en) * | 2015-07-08 | 2015-09-30 | 安徽瑞宏信息科技有限公司 | Human skeleton modeling method |
| CN107403463A (en) * | 2016-05-18 | 2017-11-28 | 西门子保健有限责任公司 | The human body with nonrigid portions represents in imaging systems |
| CN107403463B (en) * | 2016-05-18 | 2022-05-10 | 西门子保健有限责任公司 | Human body representation with non-rigid parts in an imaging system |
| CN112149531A (en) * | 2020-09-09 | 2020-12-29 | 武汉科技大学 | Human skeleton data modeling method in behavior recognition |
| CN112149531B (en) * | 2020-09-09 | 2022-07-08 | 武汉科技大学 | Human skeleton data modeling method in behavior recognition |
| CN112720489A (en) * | 2020-12-25 | 2021-04-30 | 华南理工大学 | Unitized combined modeling method, system and medium for wearable robot and human body |
| CN112720489B (en) * | 2020-12-25 | 2022-03-25 | 华南理工大学 | Unitized combined modeling method, system and medium for wearable robot and human body |
| CN113268626A (en) * | 2021-05-26 | 2021-08-17 | 中国人民武装警察部队特种警察学院 | Data processing method and device, electronic equipment and storage medium |
| CN113268626B (en) * | 2021-05-26 | 2024-04-26 | 中国人民武装警察部队特种警察学院 | Data processing method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gu et al. | Human gesture recognition through a kinect sensor | |
| Xia et al. | Vision-based hand gesture recognition for human-robot collaboration: A survey | |
| CN105739702B (en) | Multi-pose finger tip tracking for natural human-computer interaction | |
| Wang et al. | Point cloud and visual feature-based tracking method for an augmented reality-aided mechanical assembly system | |
| Xing et al. | People-following system design for mobile robots using kinect sensor | |
| Wang et al. | Real-time drogue recognition and 3D locating for UAV autonomous aerial refueling based on monocular machine vision | |
| CN104423569A (en) | Pointing position detecting device, method and computer readable recording medium | |
| CN104463947A (en) | Human body skeleton modeling method | |
| CN104821010A (en) | Binocular-vision-based real-time extraction method and system for three-dimensional hand information | |
| Li et al. | RGB-D image processing algorithm for target recognition and pose estimation of visual servo system | |
| Bian et al. | Machine learning-based real-time monitoring system for smart connected worker to improve energy efficiency | |
| Khan et al. | Surface estimation of a pedestrian walk for outdoor use of power wheelchair based robot | |
| Yang et al. | Transformer-based deep learning model and video dataset for unsafe action identification in construction projects | |
| Sun et al. | ATOP: An attention-to-optimization approach for automatic LiDAR-camera calibration via cross-modal object matching | |
| Kassab et al. | Real-time human-UAV interaction: New dataset and two novel gesture-based interacting systems | |
| CN103903279A (en) | Parallel tracking system and method based on bionic binocular vision onboard platform | |
| Li et al. | Accurate and fast 3D head pose estimation with noisy RGBD images | |
| Darujati et al. | Facial motion capture with 3D active appearance models | |
| CN103177245B (en) | gesture recognition method and device | |
| CN104952110A (en) | Human skeleton modeling method | |
| Ikram et al. | Real time hand gesture recognition using leap motion controller based on CNN-SVM architechture | |
| Hsieh et al. | A real time hand gesture recognition system based on DFT and SVM | |
| Peris et al. | Both-hand gesture recognition based on KOMSM with volume subspaces for robot teleoperation | |
| Kim et al. | Visual multi-touch air interface for barehanded users by skeleton models of hand regions | |
| Dou et al. | Boosting cnn-based pedestrian detection via 3d lidar fusion in autonomous driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160420 Address after: 230001 Mount Huangshan road Anhui city Hefei province high tech Zone No. 616 iFLYTEK No. 1 building three layer Applicant after: Hefei Huanjing Information Technology Co., Ltd. Address before: 241000 Anhui city of Wuhu province Zhongshan Science Industrial Park Road No. 717 B6 Applicant before: Anhui Coswit Information Technology Co., Ltd. |
|
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150325 |