Three-dimensional human body motion editing method driven by demonstration show based on speedup sensor
An acceleration sensor and motion technology, applied in animation production, 3D image processing, instruments, etc.
Inactive Publication Date: 2010-12-29
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
From a practical point of view, one disadvantage of traditional machine learning methods is that a large number of samples from many different users need to be collected for training
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach
[0054] First, calculate the acceleration data of the corresponding body parts for each action segment in the motion capture database as the initial sample, image 3 (a) is an example of a motion capture data fragment, image 3 (b) is the acceleration sample calculated from the motion capture data. Next, the system automatically generates a series of training samples by adding noise. There are two noise generation methods to choose from: uniformly distributed noise, see image 3 (c), Gaussian distributed noise, see image 3 (d). Standardize and feature extract the training sample set, Figure 4 (a) is an example of a training sample after normalization. In the next step, use the preprocessed sample set to train the hidden Markov model. For the training process, see Figure 5 . Connect the acceleration sensor and place it on the designated part of the human body, figure 1 Shows where the acceleration sensor is placed on the human body. Then, the user wears an acceleratio...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for arranging three-dimensional human body movements, which is driven by a demonstration performance and is based on an acceleration sensor. The method comprises the following steps: 1) segmenting movement capturing data and calculating the data segments to obtain acceleration data of an appointed part; 2) generating a training sample set automatically through adding noises; 3) preprocessing the training sample; 4) training a hidden Markov model; 5) connecting the acceleration sensor and placing the acceleration sensor at an appointed part on a human body; 6) performing demonstration movements by a user; 7) preprocessing a demonstration performance sample; 8) identifying the demonstration performance movements by using the hidden Markov model; and 9) editing and modifying the identified movements to obtain a result movement sequence. The method achieves the function of performing movement identification and movement arrangement by using the acceleration sensor, solves the problem that the prior movement identifying method needs to collect a large amount of training samples, and provides a method driven by demonstration performance to perform the movement identification and the movement arrangement on an acceleration space.
Description
technical field [0001] The invention relates to a three-dimensional human action recognition and action arrangement method, in particular to a three-dimensional human action arrangement method driven by a demonstration performance based on an acceleration sensor. Background technique [0002] Demonstrative performance-driven choreography builds on existing work in several areas, including doll-driven animation, motion capture with minimal markers or sensors, and user-independent motion recognition. [0003] Doll-driven animation is an effective demonstration performance-driven animation method, which can convert the actions of performers into the actions of computer virtual characters in real time. This method provides a live performance and visualization tool for traditional film animation. The main technical point is: when the size and proportion of the target character and the performer are different, how to effectively map the action of the performer to the target charac...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T15/70G06T13/40
Inventor 耿卫东梁秀波李启雷张翔张顺
Owner ZHEJIANG UNIV