Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Behavior identification method based on integration depth typical time wrapping and related correction

A technology of time regularization and recognition method, applied in character and pattern recognition, instrument, calculation, etc., can solve the problems of long time and low detection and recognition accuracy.

Active Publication Date: 2017-10-03
空间视创(重庆)科技股份有限公司
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is the technical problem of low detection and recognition accuracy and long time in the prior art

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
  • Behavior identification method based on integration depth typical time wrapping and related correction
  • Behavior identification method based on integration depth typical time wrapping and related correction
  • Behavior identification method based on integration depth typical time wrapping and related correction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] This embodiment provides a behavior recognition method based on integrated deep typical time warping and related corrections, including image preprocessing, image analysis, and image understanding, such as figure 1 , the image analysis includes:

[0087] (1) Express the behavior of the human body as a rigid body displacement, decompose the rigid body displacement into rigid body translation and rigid body rotation, use the homogeneous matrix Lie group SE(3) to represent the rigid body displacement, and the Lie algebra SO(3) reflects the homogeneous matrix Lie group SE (3) All information;

[0088] (2) Skeleton model C(t) is established from the collected bone data. Skeleton model C(t) has N segments of bone rigid body. At time t, a segment of bone is defined as the result of displacement of another segment of bone. One segment of bone is connected to another segment of bone. The position relationship between is defined as the displacement mapping relationship. In 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 invention relates to a behavior identification method based on integration depth typical time wrapping and related correction. The behavior identification method solves the technical problems of low identification accuracy degree and long consumed time, and comprises the steps of: expressing a behavior of a human body as rigid body displacement, decomposing the rigid body displacement into rigid body translation and rigid body rotation, and expressing the rigid body displacement by means of a homogeneous matrix Lie group SE (3), wherein Lie Algebra is SO(3); establishing a skeleton model C(t) according to acquired skeleton data, expressing a displacement mapping relation as the homogeneous matrix Lie group SE (3), establishing the skeleton model C (t) based in a Lie algebra relative feature description method, and subjecting the skeleton model C(t) to difference value processing; aligning the skeleton model C(t) by adopting a integration depth typical time wrapping method; and correcting aligned feature samples by utilizing correlation features, and classifying the corrected feature samples by means of a support vector machine. The behavior identification method solves the problems, and is applied to the behavior identification of 3D skeletons.

Description

technical field [0001] The invention relates to the field of human behavior recognition, in particular to a behavior recognition method based on integration depth typical time regularization and related correction. Background technique [0002] Human behavior recognition belongs to the field of computer vision and behavior pattern recognition, and has gradually become a hot topic in recent years. Behavior recognition has huge practical value in human-computer interaction, security monitoring, and content-based video retrieval. The role of behavior recognition is becoming increasingly prominent with the construction of informatization. At the same time, behavior recognition can also promote other fields of computer vision, such as face recognition and gait analysis. In the past, due to technological limitations, most behavior recognition was based on 2D videos and images, and the recognition effect was not satisfactory. With the development and popularization of 3D technolo...

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
CPCG06V40/20G06F18/2411
Inventor 葛永新陈乐扬杨丹张小洪徐玲杨梦宁洪明坚王洪星黄晟陈飞宇
Owner 空间视创(重庆)科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com