Parallelized human body behavior identification method

A recognition method and behavior technology, applied in the field of parallelized human behavior recognition, can solve problems such as the inability to meet the fast and real-time calculation, and inefficient task scheduling, and achieve the effect of reducing the number of iterations and speeding up the training rate.

Inactive Publication Date: 2015-09-09
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 77 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The currently widely used Hadoop framework implements the distributed file system HDFS and the MapReduce programming mode, which solves the problems of massive data storage and calculation analysis, but...

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
  • Parallelized human body behavior identification method
  • Parallelized human body behavior identification method
  • Parallelized human body behavior identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be further described below in conjunction with specific examples.

[0054] The parallel human behavior recognition method described in this embodiment includes the following steps:

[0055] 1) Obtain the joint point (skeleton) data and RGB image data of the human body based on the depth sensor of Kinect;

[0056] 2) Joint point data preprocessing to ensure the displacement and scale invariance of features;

[0057] 3) For the selection of static behavior features, starting from the human body structure, three aspects of information, including the human body structure vector, the space angle between bones and the bone length offset, are selected for fusion;

[0058] 4) For dynamic behavior features, define the similarity of human body structure with the method described in static features. On the basis of sliding window, take the change of structure similarity as the search strategy, and dynamically search according to the changes between the ...

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 present invention discloses a parallelized human body behavior identification method. According to the method, skeleton data of Kinect is used as input; a distributed behavior identification algorithm is implemented based on a Spark computing framework; and a complete parallel identifying process is formed. Acquisition of the skeleton data of a human body is based on scene depth acquisition capacity of Kinect and the data is preprocessed to ensure invariability of displacement and scale of characteristics; and a human body structural vector, joint included angle information and skeleton weight bias are respectively selected for static behavior characteristics and a dynamic behavior searching algorithm for a structural similarity is provided. On the identification algorithm, a neural network algorithm is parallelized on Spark; a quasi-newton method L-BFGS is adopted to optimize a network weight updating process; and the training speed is obviously increased. According to an identification platform, a Hadoop distributed file system HDFS is used as a behavior data storage layer; Spark is applied to a universal resource manager YARN; the parallel neural network algorithm is used as an upper application; and the integral system architecture has excellent extendibility.

Description

technical field [0001] The invention relates to the technical field of human behavior recognition and distributed computing research, in particular to a parallel human behavior recognition method. Background technique [0002] Today's society is developing at an unprecedented speed in the wave of digitization and intelligence. People are no longer satisfied with computers as a tool for production. They hope to liberate themselves from tedious operations, let computers independently understand external information, and explore more naturally. way of interaction. Human behavior recognition, as one of the research hotspots, has received more and more attention. [0003] Human behavior recognition research has very broad application prospects. For example, 1) Video surveillance and video retrieval. Traditional video surveillance completely relies on manpower to manually search for suspicious behaviors and potential safety hazards. Applying behavior recognition to video surveil...

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): G06K9/00G06K9/62
CPCG06V40/25G06V40/103G06F18/214
Inventor 董敏金泽豪毕盛刘皓熙
Owner SOUTH CHINA 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