Restaurant kitchen personnel behavior identification method based on attention mechanism

A recognition method and attention technology, applied in the fields of image understanding and computer vision, can solve problems such as expensive computing consumption and storage requirements, and achieve the effect of ensuring speed and detection accuracy

Inactive Publication Date: 2020-02-21
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
View PDF8 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with 2D convolution, 3D convolutional network can better capture spatiotemporal information, but it requires expensive computing consumption and storage requirements

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
  • Restaurant kitchen personnel behavior identification method based on attention mechanism
  • Restaurant kitchen personnel behavior identification method based on attention mechanism
  • Restaurant kitchen personnel behavior identification method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be described below in conjunction with the accompanying drawings and specific embodiments. The present invention will be further described below in conjunction with the accompanying drawings.

[0024] The flowchart of this invention is as figure 1 shown. After inputting the video frames and optical flow images in the restaurant kitchen video database into the spatial stream and time stream networks respectively, the features obtained after the last convolution of the basic network BNInception are called segment-level features; for each part of the video Fragment-level features of the segment-level features are fused into part-level features X by taking the maximum value in each dimension, X∈R H×W×C (H represents the height of part-level features, W represents the width of part-level features, and C represents the number of channels of part-level features), let X=[x 1 , x 2 ,...x c ], where x i Represents the feature vector on the i-th ch...

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 restaurant kitchen personnel behavior identification method based on an attention mechanism, and aims to effectively identify human body behaviors in restaurant kitchen videos and realize kitchen monitoring management. The method comprises the following steps: acquiring working videos of kitchen workers by using a camera, constructing a database of which the videos comprise clear actions, performing frame cutting on the database, and extracting optical flow images; inputting the video frames into a spatial stream network based on a spatial attention mechanism to obtain spatial features; inputting the optical flow image into a time flow network based on a long-short-term memory network to obtain a time sequence feature; and respectively inputting the space and timesequence features into a classifier to obtain classification scores, and carrying out score fusion to complete kitchen personnel behavior identification. According to the method, a spatial attentionmechanism is added, so that the model pays more attention to more important points in space; and the long-short-term memory network better reserves the time sequence information in the video, so thatthe kitchen personnel behavior recognition accuracy is improved.

Description

technical field [0001] The invention relates to the fields of image understanding and computer vision, in particular to a method for recognizing human body behavior. Background technique [0002] With the rapid development of economy and technology, the demand for video surveillance systems continues to increase, such as parking lots, supermarkets, shopping malls, banks, factories, mines, restaurant kitchens and other places. Mining human behavior information in videos has become a major development direction. [0003] To put it simply, behavior recognition is to classify a given video clip. The categories are usually various actions of people, that is, to detect the behavior of the human body and better grasp the behavior information of people in the video. Nowadays, bright kitchens and bright stoves are getting more and more attention. There is an increasing demand to detect whether there are violations of human behavior in the video of the restaurant’s back kitchen. Real...

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): G06K9/00G06K9/62G06N3/04
CPCG06N3/049G06V20/41G06N3/045G06F18/214G06F18/254G06F18/253
Inventor 颜津蔡强毛典辉
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
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