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

A behavior recognition method based on self-attention mechanism

A recognition method and attention mechanism technology, applied in character and pattern recognition, computer parts, details involving image stitching, etc., can solve problems affecting the applicability of action recognition algorithms, poor support for 3D convolution, and increased kernel parameters , to achieve the effect of improving the parallel computing ability

Active Publication Date: 2022-02-01
SHANDONG SYNTHESIS ELECTRONICS TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with 2D convolution, 3D convolution needs to consider time axis features, resulting in a large increase in kernel parameters
At the same time, as a new computing method, 3D has poor support for 3D convolution under different deep learning frameworks, which affects the practical applicability of action recognition algorithms based on 3D convolution.

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
  • A behavior recognition method based on self-attention mechanism
  • A behavior recognition method based on self-attention mechanism
  • A behavior recognition method based on self-attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] This embodiment discloses a behavior recognition method based on a self-attention mechanism, such as figure 1 shown, including the following steps:

[0063] S01), continuous frame image reading

[0064] With the key frame as the first frame image, 16 frames of image data input are continuously read in a continuous time sequence, and the key frame target label information target is read at the same time, and the position encoding initial matrix mask is constructed.

[0065] The dimensions of the continuous frame image data input are [16,3,H,W], where H,W represent the height and width of the network input image, and 3 indicates that the read frame image is a 3-channel RGB image.

[0066] The target label information target contains the target position information and action category information of the key frame of the image.

[0067] For 16 consecutive frames of images, the same data preprocessing operation is used, so for 16 consecutive frames of pictures, a two-dimen...

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 self-attention mechanism. The method adopts a key frame target position prediction and continuous frame action category prediction module based on a multi-angle attention mechanism, and can realize target positioning while completing continuous frame action detection. Function. In the method, the key frame target position prediction based on the multi-angle attention mechanism and the continuous frame action category prediction module are used to replace the 3D convolutional network, which solves the problem of a large amount of calculation for the 3D convolutional network model, and improves the parallelism of the model on the GPU. At the same time, the key frame target position prediction and continuous frame action category prediction module based on the multi-angle attention mechanism can avoid the problem of weak compatibility during model conversion or deployment due to 3D convolution under different deep learning frameworks.

Description

technical field [0001] The invention relates to a behavior recognition method based on a self-attention mechanism, which belongs to the field of human motion recognition. Background technique [0002] Action recognition realizes the action classification task by extracting the action features of continuous video frames, and avoids the occurrence of possible dangerous behaviors in practice, and has a wide range of practical application scenarios. [0003] The existing action recognition methods are all based on 3D convolution, which is used to extract continuous frame features in time series, improve the algorithm's ability to extract image features in time series, and increase the accuracy of action recognition. Compared with 2D convolution, 3D convolution needs to consider time axis features, resulting in a large increase in kernel parameters. At the same time, 3D, as a new computing method, has poor support for 3D convolution under different deep learning frameworks, whic...

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): G06V10/82G06V10/774G06V40/20G06N3/04G06T3/40G06T7/70H04N19/172G06V10/764
CPCG06T3/4038G06T7/70H04N19/172G06T2200/32G06T2207/10016G06V20/46G06V2201/07G06N3/045
Inventor 刘辰飞高朋井焜
Owner SHANDONG SYNTHESIS ELECTRONICS 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