A motion data distortion recovery method
A motion data and distortion recovery technology, applied in image data processing, image analysis, instruments, etc., can solve the problem of accurate distance measurement of difficult marked points, unable to maintain the accuracy of missing point coordinate recovery at the same time, bone length recovery accuracy, low-rank filling inherent approximation errors, etc.
Active Publication Date: 2020-06-16
嘉兴芸诗娇电子商务有限公司
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the high dependence of this method on other markers in the same segment, it is difficult to accurately measure the distance between markers
Even if the constraint of constant bone length is used on the basis of matrix filling, the accuracy can be further improved, but it also has the inherent approximation error of low-rank filling
[0005] The above algorithms cannot maintain the coordinate recovery accuracy of missing points and the bone length recovery accuracy at the same time when the marker points are continuously missing.
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
Embodiment Construction
[0107] Such as figure 1 As shown, the present embodiment takes the human body as an example, and the motion data distortion recovery method includes the following steps:
[0108] Step 1: standardize the motion data coordinates;
[0109] The human body motion capture data mainly records the spatial position of the marked points of the human skeleton and its motion trajectory information. Usually, the motion capture data directly obtains the three-dimensional coordinates of the marked points in the world coordinate system. Subsequent storage generally stores data by storing translation and rotation information of each marker, wherein the rotation information is represented by Euler angles. These data reflecting coordinate changes are stored in the AMC file, while some invariable data, such as the initial position of the marker point, degree of freedom and bone length, are stored separately in the ASF file. This storage method undoubtedly avoids data redundancy. The representat...
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 motion data distortion recovery method, comprising the following steps: step 1: standardize the motion data coordinates; step 2: segment and combine different parts of the human body processed in step 1; step 3: perform step 2 Segment the combined data and carry out the sliding window processing on the time axis respectively to obtain the data sequence of adjacent frames; Step 4: carry out dictionary training; Step 5: build the target function to recover human body motion data by the dictionary that step 4 obtains; The present invention The motion data distortion recovery method can maintain the bone length invariance while maintaining a good recovery effect, which makes the recovered motion sequence more natural and facilitates subsequent data storage.
Description
technical field [0001] The invention relates to the field of three-dimensional motion data processing, in particular to a motion data distortion restoration method. Background technique [0002] Motion capture (MOCAP) is a technology to obtain real motion data. It refers to recording the motion trajectory of the human body in three-dimensional space through sensing devices, converting it into abstract motion data, and finally driving objects or virtual human motion based on these data. Technology. With the rapid development of virtual reality technology, MOCAP has been widely used in various fields, such as computer animation, computer games, film and television animation, education and medicine, sports analysis, sports training, intelligent monitoring, motion simulation and other fields. In order to obtain accurate data, there are already many MOCAP technologies, among which motion capture technology based on optical sensors is the most popular technology, and representati...
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): G06T7/215G06T7/277G06T7/285G06K9/62
CPCG06T7/215G06T7/277G06T7/285G06F18/28
Inventor 汪亚明韩永华鲁涛马可
Owner 嘉兴芸诗娇电子商务有限公司