Unlock instant, AI-driven research and patent intelligence for your innovation.

Action recognition method and system based on channel allocation under partial decoupling condition

A technology for action recognition and channel allocation, which is applied to computer components, character and pattern recognition, instruments, etc., and can solve problems such as the balance of temporal and spatial expression capabilities of convolution kernels.

Pending Publication Date: 2021-04-02
SUN YAT SEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, some current mainstream decomposition work does not consider the balance of the temporal and spatial expression capabilities of the convolution kernel.

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
  • Action recognition method and system based on channel allocation under partial decoupling condition
  • Action recognition method and system based on channel allocation under partial decoupling condition
  • Action recognition method and system based on channel allocation under partial decoupling condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. For the step numbers in the following embodiments, it is only set for the convenience of illustration and description, and the order between the steps is not limited in any way. The execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art sexual adjustment.

[0026] refer to figure 1 and image 3 , the present invention provides an action recognition method based on channel allocation under partial decoupling conditions, the method comprising the following steps:

[0027] S1. Obtain video information and process the video information, and extract video frame images;

[0028] S2. Input the video frame image to the preset convolutional neural network for action recognition, and obtain the recognition result;

[0029] The preset convolutional neural network includes a res...

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 an action recognition method and system based on channel allocation under a partial decoupling condition. The method comprises the steps: obtaining video information, processing the video information, and extracting a video frame image; inputting the video frame image into a preset convolutional neural network for action recognition to obtain a recognition result, wherein the preset convolutional neural network comprises a residual layer, two R (2 + 1) blocks, a Decoupled 3D module, a pooling layer and a full connection layer. The system comprises a video frame extraction module and an recognition module. According to the method, the expression capability of the model is balanced by distributing channel dimension information in space and time through the Decoupld3Dmodule. The action recognition method and system based on channel allocation under the partial decoupling condition can be widely applied to the field of model improvement.

Description

technical field [0001] The invention belongs to the field of model improvement, in particular to an action recognition method and system based on channel allocation under partial decoupling conditions. Background technique [0002] The current mainstream video action recognition methods include dual-stream networks that integrate dynamic features such as appearance and optical flow, 3DCNN and its decomposition methods, and methods based on recurrent neural networks. The dual-stream network generally includes two branches, one branch uses the RGB image to extract the apparent features of the action, and the other branch uses the optical flow or the dynamic information between adjacent frames to extract the temporal features; 3DCNN expands the 2D convolutional network, The convolution kernel can perform feature extraction in time and space at the same time, and the decomposition method is to decompose the original 3D convolution into 2D spatial convolution and 1D time convolut...

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
IPC IPC(8): G06K9/00G06N3/04
CPCG06V20/41G06V20/46G06N3/045
Inventor 郑慧诚程凤雯张伟刘泽华
Owner SUN YAT SEN UNIV