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

Group behavior recognition method based on graph convolutional network and group relationship modeling

A convolutional network and recognition method technology, applied in the field of group behavior recognition based on graph convolutional network and group relationship modeling, can solve problems such as difficulty in group feature representation, and achieve the effect of improving accuracy and robustness

Pending Publication Date: 2022-07-22
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of this application is to provide a group behavior recognition method based on graph convolutional network and group relationship modeling, which overcomes the difficulty of characterizing group characteristics and can make full use of sensor data information to improve the correctness and robustness of group behavior recognition sex

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
  • Group behavior recognition method based on graph convolutional network and group relationship modeling
  • Group behavior recognition method based on graph convolutional network and group relationship modeling
  • Group behavior recognition method based on graph convolutional network and group relationship modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

[0033] Sensor data group behavior recognition is to obtain individual behavior data through sensors, use different individual data in the group as input, and finally output the group behavior of the group. The sensors that collect data mainly include accelerometers and gyroscopes. When the human body moves in different states, accelerometers and gyroscopes have specific manifestations. Through the above two sensors, collecting individual activity data in different parts of the body, coupled with the coordinate position of the individual, can make full use of the senso...

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 group behavior recognition method based on a graph convolutional network and group relationship modeling, which comprises the following steps of: segmenting continuous sensor data acquired by sensors at different local positions of individuals through a sliding window; and inputting individual local position sensor data into the convolutional neural network and the bidirectional long-short-term memory network to obtain individual behavior characteristics, obtaining individual behavior correlation and individual position correlation through calculation, constructing an individual relation graph, and inputting the individual relation graph into the graph convolutional network to identify group behaviors. According to the method, individual behaviors in a sensor data group and interaction relation characteristics among individuals are fully mined, group characteristic-level characterization is carried out, and the group behavior recognition accuracy and robustness are improved.

Description

technical field [0001] The present application belongs to the technical field of behavior recognition, and in particular relates to a group behavior recognition method based on graph convolution network and group relationship modeling. Background technique [0002] Group behavior recognition has become a prominent research field at present. Group behavior refers to the overall behavior of two or more individuals who interact and depend on each other. It is a challenging task to identify group behaviors in complex scenarios, because group behaviors are not simply summed up of individual behaviors, but need to be inferred from individual behaviors and the interaction between individuals. Therefore, it not only needs to identify the behavior of individuals in the group, but also needs to consider the complex interaction between individuals, and conduct bottom-up behavior analysis. [0003] In recent years, the rapid development of the Internet of Things industry, the developme...

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 Applications(China)
IPC IPC(8): G06N3/08G06N3/04G06K9/00
CPCG06N3/08G06N3/044
Inventor 宦若虹舒佳
Owner ZHEJIANG UNIV OF TECH