CN104899927A - Human posture reconstruction method - Google Patents
Human posture reconstruction method Download PDFInfo
- Publication number
- CN104899927A CN104899927A CN201510393114.1A CN201510393114A CN104899927A CN 104899927 A CN104899927 A CN 104899927A CN 201510393114 A CN201510393114 A CN 201510393114A CN 104899927 A CN104899927 A CN 104899927A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- human
- image
- human body
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a human posture reconstruction method and relates to the technical field of human postures. The human posture reconstruction method comprises the following steps: (1) downloading a pure human movement database; (2) constructing a human skeleton image; (3) constructing a three-dimensional human skeleton model; (4) tracking articulation points of the three-dimensional human skeleton model; (5) comparing and correcting images; (6) reconstructing a human posture in a three-dimensional manner. The reconstruction steps can be simplified, and the human posture reconstruction method is low in cost and easy to operate, and has a quick and easy reconstruction function.
Description
Technical field:
The present invention relates to human body attitude technical field, be specifically related to a kind of human body posture reconstruction method.
Background technology:
Human motion capture technology is widely applied to cartoon making, film special efficacy, and the entertainment field such as computer game bring huge economic benefit.Although current various business capture systems can carry out following the tracks of and recording human motion with very high spatial and temporal resolution, but (dress pretty troublesome owing to needing the software of very high cost, equipment and data acquisition, business machine needs user to dress 40-50 the reflective marker point be carefully placed with usually, or 18 magnetic force or inertial sensor), in addition, they can have special requirement and restriction to the performer of performance and collection environment usually, cause them to be not suitable for family expenses; Its complex steps of existing human body posture reconstruction method, and the equipment needed is costly, and cost is high.
Summary of the invention:
The object of this invention is to provide a kind of human body posture reconstruction method, it can simplify the step of reconstruction, and cost is low, easy and simple to handle, rebuilds quick, easy.
In order to solve the problem existing for background technology, the present invention adopts following technical scheme: its method for reconstructing is:
(1), downloading pure human body movement data storehouse: downloading data library information, is TRC form by the data of the database of download from BVH format conversion;
(2), human skeleton image is set up: select human skeleton image by the image being converted into TRC form, then mark in each articulation point, then coupled together by gauge point, obtain two-dimension human body skeleton pattern;
(3) three-dimensional human skeleton model, is set up: the two-dimension human body skeleton pattern obtained in step (two) is carried out each attitude and carries out translation and rotational transform, export translation and rotational transform after exercise data index building, extract the data of corresponding articulation point, set up three-dimensional human skeleton model by data;
(4), to the articulation point setting up three-dimensional human skeleton model follow the tracks of: by needing the articulation point of following the tracks of to mark, obtaining new node by tracing, new node is transformed into new two dimensional image;
(5), the comparison of image and correction: two-dimension human body skeleton pattern and new two dimensional image are compared and obtains final two dimensional image after correcting;
(6), human body attitude three-dimensional reconstruction: final two dimensional image is converted to three-dimensional framework model with the method for parameter estimation of scaled orthographic projection model.
The present invention has following beneficial effect: can simplify the step of rebuilding, and cost is low, easy and simple to handle, rebuilds quick, easy.
Embodiment:
This embodiment adopts following technical scheme: its method for reconstructing is:
(1), downloading pure human body movement data storehouse: downloading data library information, is TRC form by the data of the database of download from BVH format conversion;
(2), human skeleton image is set up: select human skeleton image by the image being converted into TRC form, then mark in each articulation point, then coupled together by gauge point, obtain two-dimension human body skeleton pattern;
(3) three-dimensional human skeleton model, is set up: the two-dimension human body skeleton pattern obtained in step (two) is carried out each attitude and carries out translation and rotational transform, export translation and rotational transform after exercise data index building, extract the data of corresponding articulation point, set up three-dimensional human skeleton model by data;
(4), to the articulation point setting up three-dimensional human skeleton model follow the tracks of: by needing the articulation point of following the tracks of to mark, obtaining new node by tracing, new node is transformed into new two dimensional image;
(5), the comparison of image and correction: two-dimension human body skeleton pattern and new two dimensional image are compared and obtains final two dimensional image after correcting;
(6), human body attitude three-dimensional reconstruction: final two dimensional image is converted to three-dimensional framework model with the method for parameter estimation of scaled orthographic projection model.
This embodiment has following beneficial effect: can simplify the step of rebuilding, and cost is low, easy and simple to handle, rebuilds quick, easy.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (1)
1. a human body posture reconstruction method, is characterized in that its method for reconstructing is:
(1), downloading pure human body movement data storehouse: downloading data library information, is TRC form by the data of the database of download from BVH format conversion;
(2), human skeleton image is set up: select human skeleton image by the image being converted into TRC form, then mark in each articulation point, then coupled together by gauge point, obtain two-dimension human body skeleton pattern;
(3) three-dimensional human skeleton model, is set up: the two-dimension human body skeleton pattern obtained in step (two) is carried out each attitude and carries out translation and rotational transform, export translation and rotational transform after exercise data index building, extract the data of corresponding articulation point, set up three-dimensional human skeleton model by data;
(4), to the articulation point setting up three-dimensional human skeleton model follow the tracks of: by needing the articulation point of following the tracks of to mark, obtaining new node by tracing, new node is transformed into new two dimensional image;
(5), the comparison of image and correction: two-dimension human body skeleton pattern and new two dimensional image are compared and obtains final two dimensional image after correcting;
(6), human body attitude three-dimensional reconstruction: final two dimensional image is converted to three-dimensional framework model with the method for parameter estimation of scaled orthographic projection model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510393114.1A CN104899927A (en) | 2015-07-07 | 2015-07-07 | Human posture reconstruction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510393114.1A CN104899927A (en) | 2015-07-07 | 2015-07-07 | Human posture reconstruction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104899927A true CN104899927A (en) | 2015-09-09 |
Family
ID=54032570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510393114.1A Pending CN104899927A (en) | 2015-07-07 | 2015-07-07 | Human posture reconstruction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104899927A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11557150B2 (en) * | 2017-09-11 | 2023-01-17 | Conti Temic Microelectronic Gmbh | Gesture control for communication with an autonomous vehicle on the basis of a simple 2D camera |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090252423A1 (en) * | 2007-12-21 | 2009-10-08 | Honda Motor Co. Ltd. | Controlled human pose estimation from depth image streams |
| CN103942829A (en) * | 2014-04-02 | 2014-07-23 | 上海交通大学 | Single-image human body three-dimensional posture reconstruction method |
| CN104167016A (en) * | 2014-06-16 | 2014-11-26 | 西安工业大学 | Three-dimensional motion reconstruction method based on RGB color and depth image |
| CN104463945A (en) * | 2013-11-25 | 2015-03-25 | 安徽寰智信息科技股份有限公司 | Human body posture rebuilding method |
-
2015
- 2015-07-07 CN CN201510393114.1A patent/CN104899927A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090252423A1 (en) * | 2007-12-21 | 2009-10-08 | Honda Motor Co. Ltd. | Controlled human pose estimation from depth image streams |
| CN104463945A (en) * | 2013-11-25 | 2015-03-25 | 安徽寰智信息科技股份有限公司 | Human body posture rebuilding method |
| CN103942829A (en) * | 2014-04-02 | 2014-07-23 | 上海交通大学 | Single-image human body three-dimensional posture reconstruction method |
| CN104167016A (en) * | 2014-06-16 | 2014-11-26 | 西安工业大学 | Three-dimensional motion reconstruction method based on RGB color and depth image |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11557150B2 (en) * | 2017-09-11 | 2023-01-17 | Conti Temic Microelectronic Gmbh | Gesture control for communication with an autonomous vehicle on the basis of a simple 2D camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110533752B (en) | Human body action editing model generation method, storage medium and electronic equipment | |
| WO2021169839A1 (en) | Action restoration method and device based on skeleton key points | |
| CN102848389B (en) | Realization method for mechanical arm calibrating and tracking system based on visual motion capture | |
| US8462198B2 (en) | Animation generation systems and methods | |
| US11195318B2 (en) | Rapid avatar capture and simulation using commodity depth sensors | |
| CN110637323A (en) | Robust mesh tracking and fusion by using part-based keyframes and prior models | |
| JP2012038334A5 (en) | ||
| US20130293686A1 (en) | 3d reconstruction of human subject using a mobile device | |
| CN104915978A (en) | Realistic animation generation method based on Kinect | |
| JP2011521357A (en) | System, method and apparatus for motion capture using video images | |
| CN103578135A (en) | Virtual image and real scene combined stage interaction integrating system and realizing method thereof | |
| Tong et al. | Research on skeleton animation motion data based on Kinect | |
| CN110327048A (en) | A kind of human upper limb posture reconstruction system based on wearable inertial sensor | |
| KR20230078777A (en) | 3D reconstruction methods, devices and systems, media and computer equipment | |
| CN106683181A (en) | Method for reconstructing three-dimensional human body dense surface motion field | |
| CN105225262A (en) | A kind of motion capture 3D data processing method and 3D model thereof | |
| US20210209808A1 (en) | Compression of dynamic unstructured point clouds | |
| JP2002269580A (en) | Animation creating system | |
| CN203630822U (en) | Virtual image and real scene combined stage interaction integrating system | |
| CN107945270A (en) | A kind of 3-dimensional digital sand table system | |
| Jain et al. | Leveraging the talent of hand animators to create three-dimensional animation | |
| CN204695673U (en) | A kind of for the three-dimensional digital sand table in urban planning and construction | |
| Song et al. | Real-time expressive avatar animation generation based on monocular videos | |
| Schönauer et al. | Wide area motion tracking using consumer hardware | |
| CN104899927A (en) | Human posture reconstruction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150909 |