An action recognition system and method based on common contraction rate
A technology of motion recognition and shrinkage rate, applied in the field of intelligence, to achieve the effect of simple motion recognition
Active Publication Date: 2020-05-19
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, this technology has certain limitations for children, the elderly and the sick. Long-term sports training and multi-node motion sensors will bring a certain burden to their psychology and body.
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
[0022] In one embodiment, an action recognition system based on common contractions, such as figure 1 As shown, the action recognition system includes but not limited to an acquisition device 11 , a filter 12 and a processor 13 .
[0023] In this embodiment, the acquiring device 11 is used to acquire the physiological electromyographic signals released by the moving muscles during exercise, the filter 12 is used to preprocess the physiological electromyographic signals by using a filtering algorithm, and the processor 13 It is used for extracting the common contraction rate of the exercise muscle from the preprocessed physiological electromyography signal through the average myoelectric algorithm, and is used for feature recognition based on the common contraction rate to identify the action corresponding to the exercise muscle.
[0024] In a preferred embodiment, the acquiring device 11 is specifically used to acquire the myoelectric value of the antagonist muscle and the myo...
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 present application relates to an action recognition system and method based on common contraction rate. The action recognition system includes: the acquisition device acquires the physiological electromyographic signal released by the exercise muscle during exercise; the filter adopts a filtering algorithm to analyze the physiological electromyographic signal Preprocessing; the processor extracts the common contraction rate of the exercise muscle from the preprocessed physiological electromyography signal through the average myoelectric algorithm; the processor performs feature recognition according to the common contraction rate to identify the exercise muscle corresponding action. This application collects the physiological electromyographic signals of muscles in a non-invasive, objective and scientific way, and obtains the muscle co-contraction rate of the exercising muscles under different sports, so as to identify different sports; this application makes full use of the co-contraction rate in different sports Significant difference characteristics in the motion mode, an objective and simple way to realize motion recognition, provide a practical basis for the human body motion posture pattern recognition system.
Description
technical field [0001] The present application relates to the field of intelligent technology, in particular to an action recognition system and method based on a common contraction rate. Background technique [0002] Human motion gesture recognition is a very active research direction in the field of computer vision. Human motion recognition mainly includes the detection and tracking of moving humans in images and video sequences, and extracting motion features to characterize human behavior, so that feature data can be used to understand the state of human motion. In recent years, with the popularization of smartphones and wearable devices, human motion recognition has been widely used in fields such as child monitoring and learning ability assessment. Many motion recognition systems mainly obtain human motion information through acceleration sensors to detect human motion. [0003] Researchers at home and abroad initially used needle electrodes inserted into muscles to ...
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): G06F3/01G06K9/00
CPCG06F3/015G06F2203/011G06F2218/02G06F2218/12G06F2218/08
Inventor 杜文静王磊李慧慧
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI