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

Human body behavior recognition method and system based on 3D attention residual error model

A recognition method and attention technology, applied in character and pattern recognition, neural learning methods, biological neural network models, etc., can solve the problem of not prominent key information

Active Publication Date: 2020-07-07
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the shortcomings of the current 3D convolutional network model in the human body behavior recognition for complex scenes or feature information capture in field video clips, and propose a human body behavior recognition method and system based on the 3D attention residual model, Make up for the shortcomings of 3D CNN in the deep model, such as gradient disappearance, excessive redundant information, and unprominent key information, so as to strengthen its feature extraction, improve the recognition efficiency of the model in complex scenes or long videos, and enable it to better used in actual production applications

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
  • Human body behavior recognition method and system based on 3D attention residual error model
  • Human body behavior recognition method and system based on 3D attention residual error model
  • Human body behavior recognition method and system based on 3D attention residual error model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The following will further describe and illustrate with reference to the accompanying drawings and the specific implementation details of the present invention.

[0058] like figure 1 As shown, the human action recognition method based on the 3D attention residual model provided by this embodiment includes the following steps:

[0059] 1) Obtain human behavior video data sets: collect YouTube website videos, download UCF101 and Kinetics-400 public data sets, and video data collected through monocular cameras, as follows:

[0060] 1.1) Collect video data from open source video datasets, by downloading UCF101 and Kinetics-400 public datasets; use crawler scripts to capture video data related to human behavior recognition from YouTube; use monocular cameras to collect data from actual environments The human behavior video data is used as the test dataset.

[0061] 1.2) Format the video data, first file it into the respective category folders according to different catego...

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 human body behavior recognition method and a human body behavior recognition system based on a 3D attention residual error model. The human body behavior recognition method comprises the following steps of: 1) acquiring a human body behavior video data set, namely, collecting YouTube website videos, downloading UCF101 and Kinetics-400 public data sets, and collecting video data through using a monocular camera; 2) performing preprocessing operation on the video data in the step 1), including video frame conversion and key frame extraction, and making a data set; 3) establishing a 3D attention residual error model, and extracting features of the data set obtained in the step 2); 4) utilizing a Softmax classifier to classify and identify the features obtained in thestep 3), so as to realize model training; and 5) migrating the model trained in the step 4) according to an actual scene or an actual demand, finely adjusting the model to improve the generalizationability of the model, and finally applying the finely adjusted model to an actual human body behavior recognition task. The human body behavior recognition method and the human body behavior recognition system improve the real-time human body behavior analysis of multi-class and complex video scene processing, and have wide research and practical application values.

Description

technical field [0001] The invention relates to the technical field of human action recognition and analysis based on complex video scenes, in particular to a human action recognition method and system based on a 3D attention residual model. Background technique [0002] With the emergence and application of 5G technology, the traditional Internet era is about to enter the intelligent era of the Internet of Everything. With the continuous deepening and application of intelligence, more and more fields require intelligent solutions or related systems to assist. Such as smart city management, application of intelligent monitoring system, intelligent human-computer interaction, etc. In these fields, the related technologies of computer vision are inseparable. Among these technologies, deep learning is the most widely developed and applied. However, improving the video analysis processing efficiency and recognition accuracy of deep learning related models is still a very chall...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/20G06N3/045G06F18/24G06F18/214Y02D10/00
Inventor 董敏李永发毕盛
Owner SOUTH CHINA UNIV OF TECH
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