Two-stage behavior recognition fine classification method based on graph convolutional network

A convolutional network and subdivision technology, applied in the field of two-stage behavior recognition subdivision, can solve the problem of not classifying highly similar actions well, and achieve the effect of expanding the receptive field and improving the accuracy rate

Pending Publication Date: 2021-12-07
FUDAN UNIV +1
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is an improvement on the defect that the existing model does not classify highly similar actions well.

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
  • Two-stage behavior recognition fine classification method based on graph convolutional network
  • Two-stage behavior recognition fine classification method based on graph convolutional network
  • Two-stage behavior recognition fine classification method based on graph convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] One proposed based on the behavior of the present invention is to identify a two-stage network of FIG convolutional fine classification method, disclosed in the experimental data set NTU-RGB + D 60, and the method and the results were compared mainstream. According to mainstream practice, experiments were performed on X-Sub and X-View two benchmark, using Top1 as an evaluation index. This experiment was carried out using only a single embodiment of the data stream (as joint data), and the results compared with only a single stream model.

[0055] Experimental parameters of the invention to:

[0056] Experimental environment for the present invention: processor Intel (R) Xeon (R) CPU E5-2603 v4@1.70GHz, graphics card, an NVIDIA Titan XP 12GB, memory 64GB, operating system Ubuntu 16.04 (64-bit), the programming language Python3.7.4, deep learning framework for PyTorch1.2.0.

[0057] Training and testing process model, a continuous human skeletal joints 300 as input data, i.e....

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 two-stage behavior recognition fine classification method based on a graph convolutional network. According to the method, the accuracy of behavior recognition is improved mainly by reclassifying a difficult category set, and the method is divided into three stages: in the first stage, training a coarse classification model; in the second stage, acquiring difficult category sets and training difficult category set models, acquiring the difficult category sets by a confusion matrix of the rough classification model on the test set and a union-check set algorithm, and training the difficult category set models for the different difficult category sets; and in a third stage: during on-line inference, according to an inference result of the rough classification model, inputting the samples which need to be finely classified into the difficult category set model for re-classification. According to the method provided by the invention, aiming at the problem that a model is difficult to classify similar actions, the problem that the similar actions are difficult to classify is relieved to a certain extent by a rough classification-fine classification two-stage architecture, the accuracy of behavior recognition is improved, and a better result is obtained on a public data set.

Description

Technical field [0001] The present invention is in the field of behavior recognition, in particular to a method of identifying a fine classification based on the behavior of the two-stage network of FIG convolution. This method is superior to conventional methods for the single-flow model to identify a single popular classification task. Background technique [0002] Behavior recognition is a hot research tasks in computer vision: behavior recognition goal is to identify the behavior of the human image or video. Behavior recognition method based on the depth of learning methods can be divided based on RNN, CNN-based approach, GCN-based approach. GCN based method because of its high accuracy, many researchers to be selected, the method is employed in the present invention. At present, the main methods are mostly focused on improving the overall classification accuracy of behavior recognition model, and most of the behavior recognition model for class actions in the action part of ...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2431
Inventor 金城胡海苗段梦梦
Owner FUDAN UNIV
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