CN108053462A - A kind of method that animation is directly automatically generated from static human model - Google Patents
A kind of method that animation is directly automatically generated from static human model Download PDFInfo
- Publication number
- CN108053462A CN108053462A CN201711349152.2A CN201711349152A CN108053462A CN 108053462 A CN108053462 A CN 108053462A CN 201711349152 A CN201711349152 A CN 201711349152A CN 108053462 A CN108053462 A CN 108053462A
- Authority
- CN
- China
- Prior art keywords
- animation
- model
- exercise data
- automatically generated
- artis
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
-
- 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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Processing Or Creating Images (AREA)
Abstract
The present invention proposes a kind of method that animation is directly automatically generated from static human model, comprise the following steps (1) and automatically extract and identify first 5 characteristic points for being located at human limb and crown end, using characteristic point as starting point, the geodesic center line such as computation model;(2) gained knowledge on centerline according to anthropological measuring, determine the apparent position of artis;(3) and then according to the bone information that skeleton rigid motion feature and exercise data file provide, carry out artis and be accurately positioned;(4) vertex weights calculated by thermodynamics diffusion equation again finally realize the bone of extraction using the method that local coordinate frame aligns and match with exercise data, and skin generation human body animation driven with exercise data the experimental results showed that.The present invention has the characteristics that unrelated with model attitude, full-automatic, generation animation effect is good without manually participating in.
Description
Technical field
The invention belongs to directly automatically generate animation field from static human model.
Background technology
The human body animation of computer generation is widely used in fields such as game, film advertisement, virtual realities,
In it is the most commonly used be skeleton cartoon, it drives skin deformation to generate animation by bone, have data volume is small, it is simple to calculate,
It is easily achieved the advantages that hardware-accelerated.Human body surface model, human body movement data can be respectively by spatial digitizer, fortune at present
The dynamic instrument that captures easily obtains.But bone modeling therein and binding, weight setting need the personnel by specialized training
It realizes by hand, it is very time-consuming and loaded down with trivial details;In addition, or bone extraction algorithm is confined to the pass of standard posture or extraction at present
Node is not accurate enough, can not meet animation needs.
The content of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of side that animation is directly automatically generated from static human model
Method without manually participating in, has the characteristics that unrelated with model attitude, full-automatic, generation animation effect is good.
The technical proposal of the invention is realized in this way:A kind of side that animation is directly automatically generated from static human model
Method, including
(1) automatically extract and identify first 5 characteristic points positioned at human limb and crown end, using characteristic point for
The geodesic center line such as point, computation model;
(2) gained knowledge on centerline according to anthropological measuring, determine the apparent position of artis;
(3) and then according to the bone information that skeleton rigid motion feature and exercise data file provide, joint is carried out
Point is accurately positioned;
(4) vertex weights are calculated by thermodynamics diffusion equation again finally the bone of extraction is alignd using local coordinate frame
Method realization match with exercise data, and with exercise data drive skin generation human body animation the experimental results showed that.
Further, harmonic function algorithm can be used in the extraction of the center line or geodesic distance calculates the side of isopleth
Method.
Further, the search range of the joint on centerline is [ri-a(ri-ri-1), ri+a(ri+1-ri)],
Middle i represents i-th of joint, riRepresent i-th of joint jiValue on geodetic survey model, a are 0.5.
Compared with prior art, the present invention has the following advantages:
1) automatically, without manual intervention, on the basis of manikin and exercise data are provided, you can automatically generate human body
Animation;
2) posture is unrelated, and context of methods does not limit human body attitude, suitable for various non-standard postures, with existing method
Compared to better versatility;
3) high efficiency can quickly generate human body animation.
Specific embodiment
Technical scheme is clearly and completely described below in conjunction with embodiment, it is clear that described reality
It is only part of the embodiment of the present invention to apply example, instead of all the embodiments.Based on the embodiments of the present invention, this field is general
Logical technical staff all other embodiments obtained without creative efforts belong to what the present invention protected
Scope.
A kind of method that animation is directly automatically generated from static human model, including
(1) automatically extract and identify first 5 characteristic points positioned at human limb and crown end, using characteristic point for
The geodesic center line such as point, computation model;
(2) gained knowledge on centerline according to anthropological measuring, determine the apparent position of artis;
(3) and then according to the bone information that skeleton rigid motion feature and exercise data file provide, joint is carried out
Point is accurately positioned;
(4) vertex weights are calculated by thermodynamics diffusion equation again finally the bone of extraction is alignd using local coordinate frame
Method realization match with exercise data, and with exercise data drive skin generation human body animation the experimental results showed that.
In above-described embodiment, harmonic function algorithm can be used for the extraction of the center line or geodesic distance calculates isopleth
Method.
In above-described embodiment, the search range of the joint on centerline is [ri-a(ri-ri-1), ri+a(ri+1-
ri)], wherein i represents i-th of joint, riRepresent i-th of joint jiValue on geodetic survey model, a are 0.5.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
With within principle, any modifications, equivalent replacements and improvements are made should all be included in the protection scope of the present invention god.
Claims (3)
- A kind of 1. method that animation is directly automatically generated from static human model, which is characterized in that comprise the following steps:(1) automatically extract and identify first 5 characteristic points positioned at human limb and crown end, using characteristic point as starting point, meter Calculate the geodesic center lines such as model;(2) gained knowledge on centerline according to anthropological measuring, determine the apparent position of artis;(3) and then according to the bone information that skeleton rigid motion feature and exercise data file provide, artis essence is carried out Determine position;(4) side of the vertex weights finally by the bone of extraction using the alignment of local coordinate frame is calculated by thermodynamics diffusion equation again Method realization match with exercise data, and with exercise data drive skin generation human body animation the experimental results showed that.
- 2. the method for animation is directly automatically generated from static human model as described in claim 1, which is characterized in that the center The method that harmonic function algorithm or geodesic distance calculate isopleth can be used in the extraction of line.
- 3. the method for animation is directly automatically generated from static human model as described in claim 1, which is characterized in that the joint Search range on centerline is [ri-a(ri-ri-1), ri+a(ri+1-ri)], wherein i represents i-th of joint, riRepresent i-th A joint jiValue on geodetic survey model, a are 0.5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711349152.2A CN108053462A (en) | 2017-12-15 | 2017-12-15 | A kind of method that animation is directly automatically generated from static human model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711349152.2A CN108053462A (en) | 2017-12-15 | 2017-12-15 | A kind of method that animation is directly automatically generated from static human model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108053462A true CN108053462A (en) | 2018-05-18 |
Family
ID=62133249
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711349152.2A Withdrawn CN108053462A (en) | 2017-12-15 | 2017-12-15 | A kind of method that animation is directly automatically generated from static human model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108053462A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109068069A (en) * | 2018-07-03 | 2018-12-21 | 百度在线网络技术(北京)有限公司 | Video generation method, device, equipment and storage medium |
CN110458046A (en) * | 2019-07-23 | 2019-11-15 | 南京邮电大学 | A kind of human body motion track analysis method extracted based on artis |
-
2017
- 2017-12-15 CN CN201711349152.2A patent/CN108053462A/en not_active Withdrawn
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109068069A (en) * | 2018-07-03 | 2018-12-21 | 百度在线网络技术(北京)有限公司 | Video generation method, device, equipment and storage medium |
CN110458046A (en) * | 2019-07-23 | 2019-11-15 | 南京邮电大学 | A kind of human body motion track analysis method extracted based on artis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10984578B2 (en) | Method and system for directly manipulating the constrained model of a computer-generated character | |
CN104008564A (en) | Human face expression cloning method | |
EP2369553A3 (en) | Three-dimensional template transformation method and apparatus | |
CN105243375B (en) | A kind of motion characteristic extracting method and device | |
CN103886588A (en) | Feature extraction method of three-dimensional human body posture projection | |
CN103854306A (en) | High-reality dynamic expression modeling method | |
CN107240049A (en) | The automatic evaluation method and system of a kind of immersive environment medium-long range action quality of instruction | |
CN108053462A (en) | A kind of method that animation is directly automatically generated from static human model | |
CN102930599B (en) | A kind of chirokinesthetic three-dimensional simulation method based on biquaternion | |
CN105045496A (en) | Gesture interaction method based on joint point transformation | |
CN109741371A (en) | A kind of human action based on inertial sensor describes method | |
CN115797851B (en) | Cartoon video processing method and system | |
KR101095860B1 (en) | Method for shape deforming feature | |
CN107146288A (en) | The soft tissue model modeling method of pressing deformation in real time is supported in virtual operation | |
CN107563490A (en) | A kind of crowd's diversity emulation mode based on concern power model | |
CN110688770B (en) | Recurrence simulation method for experience effect of large-scale amusement facility | |
JP2021122736A (en) | Method for finding center of rotation of joint | |
CN109215128A (en) | The synthetic method and system of object motion attitude image | |
CN104318615B (en) | Vocal organ three-dimensional modeling method | |
CN107038914A (en) | A kind of Language for English learning system | |
Hou et al. | RETRACTED ARTICLE: An auxiliary training system for swimming in coastal areas based on remote sensing images and virtual simulation technology | |
Xiang et al. | Comparing real-time human motion capture system using inertial sensors with microsoft kinect | |
Geijtenbeek et al. | Evaluating the physical realism of character animations using musculoskeletal models | |
KR20200078858A (en) | Method for Calculating Skinning Weight of 3D Character Based on Musculoskeletal Structure | |
Chan et al. | Immersive performance training tools using motion capture technology |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180518 |
|
WW01 | Invention patent application withdrawn after publication |