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

Audio and video clip classification method and device

A classification method and audio and video technology, applied in the Internet field, can solve the problems of long time-consuming audio and video classification, low audio and video classification efficiency, etc. Effect

Pending Publication Date: 2020-09-04
NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the prior art, when the data volume of audio and video clips is large, extracting all video frames in the audio and video clips, and performing video classification based on all video frames, not only requires a large computing and processing capability, but also results in time-consuming audio and video classification. Longer, resulting in lower efficiency of audio and video classification

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
  • Audio and video clip classification method and device
  • Audio and video clip classification method and device
  • Audio and video clip classification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0051] Audio and video classification usually refers to given an audio and video segment, and performs audio and video classification on the content contained in the audio and video segment. The audio and video classification results can usually be categories such as actions, scenes, and objects. Audio and video classification is a basic problem in computer vision. In daily life, people can identify and predict the behavior of surrounding people such as walking, running, sports activities, etc. by classifying audio and video clips. Alternatively, by classifying audio and video clips, various applications in multiple fields such as surveillance video, Internet video re...

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 embodiment of the invention discloses an audio and video clip classification method and device, and the method comprises the steps: extracting a target video frame based on a video frame sequenceof a to-be-classified audio and video clip, and extracting a target audio frame based on an audio frame sequence of the to-be-classified audio and video clip; determining a first audio and video sub-clip / a second audio and video sub-clip based on the first occurrence time / the second occurrence time of the target video frame / the target audio frame and the preset sub-clip duration; extracting a first video component feature and a first audio component feature / a second video component feature and a second audio component feature based on the first audio and video sub-clip / the second audio and video sub-clip; and determining an audio and video classification result of the to-be-classified audio and video clip based on the first video component feature, the first audio component feature, the second video component feature and the second audio component feature through a preset audio and video classification model. By adopting the method, the audio and video classification efficiency can beimproved, and the robustness and accuracy of audio and video classification are improved.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a method and device for classifying audio and video segments. Background technique [0002] With the continuous development of Internet technology, more and more audio and video clips are emerging. In order to enable the user to obtain the desired audio and video clips from a large number of audio and video clips, it is necessary to classify the audio and video clips. [0003] At this stage, when audio and video clips need to be classified, the two-stream method model can be used for audio and video classification. Specifically, the dual-stream method model usually includes two channels, one is an RGB (RGB color mode, RGB color mode) image channel that can extract all video frames in an audio and video clip and model spatial information based on all video frames, and the other is an image channel that can extract All video frames in the audio and video clips are modeled ba...

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): G06F16/45G06F16/483H04N21/845G06N3/04G06N3/08
CPCG06F16/45G06F16/483H04N21/8456G06N3/049G06N3/084G06N3/045
Inventor 孙旭东张震林格平刘铭刘发强倪善金
Owner NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
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