A method and a system for detecting and evaluating a motion state based on machine vision
A motion state and machine vision technology, applied in the direction of instruments, computer parts, character and pattern recognition, etc., can solve problems such as evaluation errors, users feeling uncomfortable, inaccurate, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0084] Such as figure 1 As shown, step 100 is executed to obtain dynamic facial features. The dynamic facial features include at least one of basic sportsman features, facial orientation features, timing features, and motion state features. Wherein the basic sportsman's feature refers to the comprehensive feature that includes face outline, mouth, eye, eyebrow, nose and ear, and the described basic sportsman's feature of each sportsman is represented by the vector representation that n mark points form, X i =([x i0 ,y i0 ], [x i1 ,y i1 ],...,[x ij ,y ij ],...,[x in ,y in ]), where i is the serial number of each moving individual, j is a natural number, and 0≤j≤n, [x in ,y in ] is the coordinate of the calibration point on the face; the face orientation feature is an angle vector value θ starting from the center of the athlete’s silhouette; the timing feature is the momentary time node of the movement process, and the vector is expressed as S i =([Y i0 ,M i0 ,D i0...
Embodiment 2
[0088] Such as figure 2 As shown, the motion state detection and evaluation system based on machine vision includes an acquisition module 200, a dynamic modeling module 210 and a calculation module 220.
[0089] Acquisition module 200 is used to obtain the acquisition module of dynamic facial feature, and dynamic facial feature comprises at least one in basic athlete's feature, facial orientation feature timing feature and motion state feature. The basic sportsman's feature refers to the comprehensive features including face contour, mouth, eyes, eyebrows, nose and ears, and the said basic sportsman's feature of each sportsman is represented by the vector representation of n calibration points, X i =([x i0 ,y i0 ], [x i1 ,y i1 ],...,[x ij ,y ij ],...,[x in ,y in ]), where, i is the serial number of each moving individual, j is a natural number, and 0≤j≤n, [x in ,y in ] is the coordinate of the calibration point on the face; the face orientation feature is an angle v...
Embodiment 3
[0093] This method is derived on the basis of the basic sportsman identification theory, combined with the difference characteristics of the sportsman in the sports state to compare the results, and compared with the time series changes, to obtain the sports state evaluation results of different sportsmen.
[0094] The motion state detection and evaluation method based on machine vision includes the following parts:
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


