Video type classification method based on video slice

A classification method, video-type technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as less accuracy than manual work, a large number of servers, and large limitations, so as to improve performance and reduce redundant information. Effect

Pending Publication Date: 2020-02-28
HANGZHOU QUWEI SCI & TECH
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the current application limitations are relatively large, and the more mature ones have copyright maintenance (using video comparison technology), the accuracy is still not as good as manual work, and a large number of servers need to be deployed

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
  • Video type classification method based on video slice
  • Video type classification method based on video slice
  • Video type classification method based on video slice

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0027] Such as Figure 1 to Figure 4 As shown, a method for classifying video types based on video slices includes the following steps:

[0028] 101) Step of setting classification: design classification tags according to the application scenario, and the classification tags include tags such as comedy, science fiction, animation, pornography, and terror.

[0029] 102) The step of extracting slice images: For continuous images in a video, take a row of pixels in the middle of each frame of images as a column to form a new image. This new image can reflect the characteristics of some videos, such as video lens switching and video content motion. method, content style and other characteristics. Such as figure 2 As shown, the obvious break position of the new image of the camera cut of the video is the cut shot cut, and the position of the blu...

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 video type classification method based on video slice. The video type classification method comprises the following steps of 101) setting classification, 102) extracting slice images, 103) classifying categories, and 104) judging the categories. The invention provides a video type classification method based on video slice, wherein the performance of the video type classification method is improved by at least more than 100 times.

Description

technical field [0001] The present invention relates to the technical field of video classification, and more specifically, it relates to a method for classifying video types based on video slices. Background technique [0002] Video content analysis is a basic technology of video processing, including: (1) camera cut detection; (2) type classification, such as comedy, war, suspense, animation, etc.; (3) specific object detection, such as detecting faces, Cars, billboards; (4) semantic analysis; (5) content comparison, etc. Video content analysis technology can be applied in various fields, such as video editing software, video recommendation, content review, advertisement placement, copyright protection and so on. [0003] A video is composed of many images. A 10-minute video can contain more than 10,000 frames of images. Simple image-based analysis of video content is very difficult. Assuming that one image is processed in 50ms (usually longer than this time), 10,000 imag...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/41G06V20/46G06N3/045G06F18/241
Inventor 胡能李云夕杨金江胡耀武
Owner HANGZHOU QUWEI SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap