Unlock instant, AI-driven research and patent intelligence for your innovation.

Human body behavior recognition method based on inertial sensor

A technology of inertial sensor and recognition method, which is applied in the field of human behavior recognition and can solve problems such as single

Pending Publication Date: 2020-08-25
ZHEJIANG UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the study, all transition actions were considered as a single class and no distinction was made between

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Human body behavior recognition method based on inertial sensor
  • Human body behavior recognition method based on inertial sensor
  • Human body behavior recognition method based on inertial sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings.

[0047] refer to figure 1 and figure 2 , a human behavior recognition method based on inertial sensors, comprising the following steps:

[0048] Step (1): Build a human behavior hierarchical recognition model based on support vector machines and random forests, which includes static and dynamic action classifiers c 1 , period and transition action classifier c 2 , static action classifier c 3 , a dynamic periodic action classifier c 4 , transition action classifier c 5 A total of 5 sub-classifiers, use the feature selection method to select some features suitable for each sub-classifier from the feature set F to form a feature subset, feature subset F i for classifier c i The corresponding classification feature subsets, where i=1, 2, ..., 5, use the training data set to train the sub-classifiers in the hierarchical recognition model, and perform performance eva...

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

No PUM Login to View More

Abstract

The invention discloses a human body behavior recognition method based on an inertial sensor, and relates to the technical field of behavior recognition. The method comprises the steps of filtering and denoising the original data to generate data by adopting the data of an inertial sensor; secondly, carrying out action fragment segmentation, and carrying out feature extraction on data fragments; and finally, constructing a hierarchical recognition model based on a support vector machine and a random forest model, combining the sub-classifiers into a hierarchical model according to priori knowledge, proposing a feature layering method, selecting different features from different classifiers in the model for classification, and performing layer-by-layer recognition to obtain a final behaviorrecognition result. According to the method, the robustness of the classification model is effectively improved, the recognition accuracy is remarkably improved, and the method has obvious advantages.

Description

technical field [0001] The invention belongs to the field of human body behavior recognition based on inertial sensors, and relates to a human body behavior recognition method. Background technique [0002] Human behavior recognition technology can fully reflect human behavior status and physiological information, and has broad application prospects in sports tracking, fitness exercise, daily monitoring, medical rehabilitation, human-computer interaction, virtual reality, intelligent environment and other fields. Behavior recognition based on inertial sensors uses sensors such as accelerometers, gyroscopes, and direction sensors to collect physical information such as acceleration, angular velocity, and direction generated by human motion to identify current human behavior. [0003] The current research mainly focuses on the basic movements such as standing, sitting, walking, running, going up and down stairs, etc., and for the transitional movements between basic movements,...

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
no application Login to View More
IPC IPC(8): G06K9/62G01P15/02G01C19/00
CPCG01P15/02G01C19/00G06F18/214G06F18/2411G06F18/24323
Inventor 潘赟肖沛文朱怀宇李俊捷
Owner ZHEJIANG UNIV