Behavior Recognition Method Based on Comprehensive Linear Classifier and Analytical Dictionary

A linear classifier and recognition method technology, applied in the fields of pattern recognition and computer vision, can solve the problem of the lack of judgment ability of the analytic dictionary learning model, and achieve the effect of improving the accuracy and running speed of behavior recognition and strong judgment.

Active Publication Date: 2020-05-19
DALIAN UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the lack of certain decision-making ability of the analytical dictionary learning model, most of the current research at home and abroad only stays on the application of the analytical dictionary to reconstruct the signal, rather than the classification recognition problem.

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 Recognition Method Based on Comprehensive Linear Classifier and Analytical Dictionary
  • Behavior Recognition Method Based on Comprehensive Linear Classifier and Analytical Dictionary
  • Behavior Recognition Method Based on Comprehensive Linear Classifier and Analytical Dictionary

Examples

Experimental program
Comparison scheme
Effect test

experiment example

[0078] In order to specify the specific implementation of the present invention and verify the effectiveness of the present invention, the method proposed by the present invention is applied to a public human behavior database, namely the UCF 50 behavior database. The UCF 50 behavior database has a total of 6680 behavior videos in 50 categories, all of which are selected from YouTube, including different behaviors such as playing basketball, riding a bicycle, and playing the piano. figure 2 Shown are some human behavior samples used in the embodiment of the present invention, from which it can be clearly seen that there are obvious differences between different human behaviors. Perform 205 different angle detection samples on the same scale for behavior video samples, use behavior detectors for detection at different angles, and perform maximum pooling (Max-pooling) on ​​the detected images, using 3-layer pooling processing, which can be corresponding Get a 73-dimensional vec...

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 behavior recognition method based on a comprehensive linear classifier and an analytical dictionary that can improve the accuracy and running speed of behavior recognition. High-level representation method, each sample corresponds to a feature column vector with rich semantics; optimize learning to obtain an analytical dictionary Ω and an ensemble linear classifier R ; Obtain the coding coefficient of the test sample; the coding coefficient of the test sample, the comprehensive linear classifier R Input them into the classifier together to get the final classification result.

Description

technical field [0001] The invention relates to technical fields such as computer vision and pattern recognition, in particular to a behavior recognition method based on a comprehensive linear classifier and an analytical dictionary that can improve the accuracy and running speed of behavior recognition. Background technique [0002] Human behavior recognition technology plays a huge role in many applications such as video surveillance, human-computer interaction, and content-based video search. Conventional behavior recognition technology mainly includes two main processes, namely training process and testing process. There are three specific processing links in the training process, which are preprocessing the training samples, extracting the features of the training samples, and establishing a classification model. The test process also has three processing links, which are preprocessing the test samples, extracting the characteristics of the test samples, and using the ...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/10G06V10/40G06V10/513G06F18/2136G06F18/24G06F18/2415
Inventor 郭艳卿王久君郭君孔祥维
Owner DALIAN 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