Supercharge Your Innovation With Domain-Expert AI Agents!

Short video classification method and system based on optimized video key frame extraction

A video key frame and classification method technology, which is applied in the field of short video classification method and system based on optimized video key frame extraction, can solve problems such as motion blur, and achieve the effects of reducing resource consumption, improving time efficiency, and high classification efficiency

Pending Publication Date: 2020-04-28
HANGZHOU QUWEI SCI & TECH
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention screens the video frames based on the amount of information, avoids the motion blur of the extracted frames caused by video jitter or the problem that the extracted frames are solid colors due to screen switching, and improves the accuracy of 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
  • Short video classification method and system based on optimized video key frame extraction
  • Short video classification method and system based on optimized video key frame extraction
  • Short video classification method and system based on optimized video key frame extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, this embodiment proposes a short video classification method based on optimized video key frame extraction, including:

[0052] S1. Extract dense short video frames;

[0053] The 30fps and 60fps short video in the usual sense means that the short video consists of 30 or 60 pictures per second, and if a 10-second short video corresponds to 300 or 600 images. If all the image frames in the short video are processed, the performance of the system will undoubtedly be affected. The existing short video frame cutting is usually to cut the short video at a certain time interval and break the short video into multiple image frames, such as Image frames are extracted at 1 second intervals. As mentioned above, in the video frame extraction process, the randomness of the video frames extracted at equal intervals is too large. Usually, there are motion blur caused by video jitter or the extracted frames are pure colors due to screen switching. If these frames...

Embodiment 2

[0082] Such as image 3 As shown, this embodiment proposes a short video classification system based on optimized video key frame extraction, including:

[0083] Frame cutting module, used to extract dense short video frames;

[0084] The 30fps and 60fps short video in the usual sense means that the short video consists of 30 or 60 pictures per second, and if a 10-second short video corresponds to 300 or 600 images. If all the image frames in the short video are processed, the performance of the system will undoubtedly be affected. The existing short video frame cutting is usually to cut the short video at a certain time interval and break the short video into multiple image frames, such as Image frames are extracted at 1 second intervals. As mentioned above, in the video frame extraction process, the randomness of the video frames extracted at equal intervals is too large. Usually, there are motion blur caused by video jitter or the extracted frames are pure colors due to screen...

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 short video classification method and system based on optimized video key frame extraction. The classification method comprises the following steps: S1, extracting short video dense frames; S2, calculating the information amount of each image frame in the dense frame; S3, selecting a plurality of image frames with the maximum information amount as key frames of the shortvideo; and S4, splicing the key frames to generate a short video tensor, inputting the short video tensor into a 3D-CNN classification model, performing feature learning on the short video tensor based on the 3D-CNN classification model, and outputting a short video category. According to the method, the video frames are screened based on the information amount, so that the problem of motion blurof the extracted frames caused by video jittering or the problem that the extracted frames are in pure colors caused by picture switching are avoided, and the classification accuracy is improved.

Description

Technical field [0001] The invention relates to the field of short video processing, in particular to a short video classification method and system based on optimized video key frame extraction. Background technique [0002] In recent years, short videos have been widely used and disseminated as information carriers because the content expressed by short videos is richer and more intuitive. However, some criminals will use short videos to spread unhealthy or illegal videos for personal gain. Therefore, short video platforms should classify target videos and filter out illegal videos before publishing short videos. At the same time, due to the different interests of individuals, the recommended videos for each user should also be different. Therefore, the use of short video classification to recommend different categories to different users is also essential. [0003] The current video classification processing flow is: 1. Video frame extraction, 2. Use machine learning or deep le...

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): G06K9/62G06K9/00G06F16/75
CPCG06F16/75G06V20/42G06V20/46G06F18/241
Inventor 刘昱龙范俊顾湘余李文杰
Owner HANGZHOU QUWEI SCI & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com