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

Method and device for detecting micro-expression video sequence in video stream

A detection method and video sequence technology, which is applied in the field of image processing, can solve problems such as inability to meet real-time processing requirements, long detection time, and short micro-expression duration.

Pending Publication Date: 2022-05-10
CHINA ACADEMY OF ELECTRONICS & INFORMATION TECH OF CETC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Micro-expressions are short in duration and involve small facial muscle movements, which are difficult to pinpoint and detect accurately in real-time video streams
Usually, most of the video sequences for detecting micro-expressions come from videos taken by high-speed cameras, and the number of video frames per second contained in the video is several times that of ordinary cameras. The detection of micro-expressions refers to the detection of micro-expressions in the video. Most of the micro-expression detection methods have high computational complexity, and the detection takes a long time. The traditional computing framework cannot meet the real-time processing 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
  • Method and device for detecting micro-expression video sequence in video stream
  • Method and device for detecting micro-expression video sequence in video stream
  • Method and device for detecting micro-expression video sequence in video stream

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0036] An embodiment of the present invention provides a method for detecting micro-expression video sequences in video streams, which is applied to a processing framework including at least two graphics processing unit groups, at least two graphics processing unit groups are cascaded, and each graphics processing unit group includes multiple a graphics processing unit GPU. In this example at least two GPU groups are cascaded. Spe...

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 method and device for detecting a micro-expression video sequence in a video stream, and the method comprises the steps: obtaining the video stream, enabling the video stream to generate a plurality of batches of video frame sequences according to a time sequence, and enabling the number of video frames contained in the batch of video frame sequences to be the same as the number of GPUs of a first graphic processing unit group; loading each video frame in the video frame sequence of the first batch by using each GPU of the first graphic processing unit group, and preprocessing the video frames of the batch; inputting at least part of the preprocessed video frame sequence of the batch into a second graphic processing unit group; and loading each video frame of the at least partial video frame sequence after preprocessing by using each GPU of the second graphic processing unit group to realize micro-expression detection. According to the embodiment of the invention, the micro-expression detection of a large number of video frames is completed by utilizing a processing framework of at least two graphic processing unit groups, and the maximum utilization rate of each GPU computing resource and equipment I / O resource is realized through a stream processing mode.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for detecting micro-expression video sequences in video streams. Background technique [0002] Micro-expressions are facial expressions that are not self-controlled when people try to suppress or hide their true emotions. They can truly reflect a person's psychological activities and play an important role in criminal investigation, business negotiation, clinical diagnosis and other fields. Therefore, micro-expression detection technology has attracted researchers from various industries to conduct cross-field cooperative research on it, and has become a research hotspot in human expression detection and recognition. [0003] Micro-expressions are short in duration and involve small facial muscle movements, making them difficult to pinpoint and detect accurately in real-time video streams. Usually, most of the video sequences for detecting micro-expr...

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): G06V40/16G06V20/40G06V10/764G06K9/62G06T1/20
CPCG06T1/20G06F18/2431
Inventor 吕相文田子袁柳吕东岳刘弋锋
Owner CHINA ACADEMY OF ELECTRONICS & INFORMATION TECH OF CETC