An Adaptive Behavior Recognition Method Based on Physical Attributes

A technology of physical attributes and identification methods, applied in the field of sensor networks, can solve the problems of flexible adaptability and dynamic improvement without considering individual users, and achieve the effects of enhanced adaptability, high recognition rate, and improved system performance.

Active Publication Date: 2020-06-30
ZHEJIANG UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional behavior recognition methods can effectively recognize human behavior, but most of them are based on a static model, which has a very strong dependence on the sample feature value, without considering the flexible adaptability and dynamic improvement of individual users, such as different People have different behavioral characteristics, one person's walking behavior may correspond to another person's running behavior

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
  • An Adaptive Behavior Recognition Method Based on Physical Attributes
  • An Adaptive Behavior Recognition Method Based on Physical Attributes
  • An Adaptive Behavior Recognition Method Based on Physical Attributes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0052] refer to figure 1 and figure 2 , an adaptive behavior recognition method based on physical attributes, comprising the following steps:

[0053] Step 1: Extraction of sample eigenvalues

[0054] Step 1.1: First recruit 8 volunteers to do the traditional hula hoop exercise, wear the hardware on the waist of the volunteers, each volunteer performs each movement 1000 times, and collect the acceleration data during the exercise as a training sample, the accelerometer The frequency of reading data is 100Hz.

[0055] Step 1.2: First use the Kalman filter to filter out some abnormal data in the training samples, and obtain the available training set through filtering. The data in the training set is divided into three categories, which are the data of the X, Y, and Z axes of the accelerometer. Separate each action cycle and record the number of acceleration...

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

An adaptive behavior recognition method based on physical attributes, by collecting the acceleration data of the motion process as training samples, using the Kalman filter to filter the training samples, and calculating the physical attributes of a complete cycle of each type of action as the sample feature value, A variable-sized dynamic sliding window is used to process real-time data streams, and the average value and gravity of each feature value are selected as the basis for voting, and classification is performed by voting. Finally, through the incremental learning process, the sample feature value is dynamically updated, so that it gradually tends to the user's behavior habits, and achieves better behavior recognition purposes. The invention has good flexibility and adaptability to individual users, and has a high recognition rate.

Description

technical field [0001] The invention belongs to the field of sensor networks, in particular to an adaptive behavior recognition method based on physical attributes. Background technique [0002] In recent years, with the rapid development of Internet of Things technology and information science and technology, human body behavior recognition has received more and more attention. It is an important technology to improve people's lives and has a very broad application prospect. Traditional behavior recognition methods can effectively recognize human behavior, but most of them are based on a static model, which has a very strong dependence on the sample feature value, without considering the flexible adaptability and dynamic improvement of individual users, such as different Different people have different behavioral characteristics, and the walking behavior of one person may correspond to the running behavior of another person. Therefore, it is very important to design a beha...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06T7/277G06T7/66
CPCG06T7/277G06T7/66G06T2207/20081G06V40/23G06F18/24G06F18/214
Inventor 钱丽萍李鹏欢吴远黄亮
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap