Video matching, retrieval, classification and recommendation method, device and electronic equipment

A video and matching technology, applied in the field of video retrieval, can solve problems such as frequent scene switching, too many long video frames, and large amount of calculation

Active Publication Date: 2020-12-18
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the embodiments of the present invention is to provide video matching, retrieval, classification and recommendation methods, devices and electronic equipment to solve the problem of large amount of calculation caused by too many long video frames and frequent scene switching

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 matching, retrieval, classification and recommendation method, device and electronic equipment
  • Video matching, retrieval, classification and recommendation method, device and electronic equipment
  • Video matching, retrieval, classification and recommendation method, device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0145] The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.

[0146] In order to solve the problem in the prior art that when the video is a long video or a video with a fast scene switching frequency, the number of sub-video segments that need to be divided increases, resulting in a large amount of calculation in video segmentation, feature extraction and similarity judgment. The embodiment of the invention provides video matching, retrieval, classification and recommendation methods, devices and electronic equipment.

[0147] The video matching, retrieval, classification and recommendation methods provided by the embodiments of the present invention are all implemented based on the density clustering algorithm.

[0148] For the sake of clarity, first introduce the density clustering algorithm and the related definitions involved:

[0149] Density clustering alg...

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

Embodiments of the present invention provide video matching, retrieval, classification and recommendation methods, devices, and electronic equipment, wherein the video matching method includes: acquiring a video to be matched; extracting a plurality of key frames from the video to be matched; extracting The image feature value of each key frame of the video to be matched; using a density clustering algorithm, according to the image feature value of each key frame, from the multiple key frames of the video to be matched, select the one that meets the preset conditions The key frame is used as the core scene frame to be matched; the core scene frame of the core scene frame to be matched and the core scene frame of each original video stored in advance are similarly judged; if any core scene frame of an original video and the core scene frame to be matched If similar, the original video is determined as the target video matching the video to be matched. The embodiment of the present invention solves the problem of a large amount of calculation caused by too many long video frames and frequent scene switching.

Description

technical field [0001] The invention relates to the technical field of video retrieval, in particular to video matching, retrieval, classification and recommendation methods, devices and electronic equipment. Background technique [0002] With the rapid development of computer technology, network technology and multimedia technology, video data has been widely used in various fields such as entertainment, education and business. Explosive growth. At the same time, there are more and more users watching videos such as movies and TV dramas online, and the demand for video retrieval is increasing day by day. [0003] In the process of video retrieval, classification and recommendation, video similarity matching is required. For example: video retrieval, the main steps include: pre-segment the video for each original video in the video database, obtain multiple video clips, and then extract video features for each video clip, and save each original video. The video characteri...

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 Patents(China)
IPC IPC(8): G06F16/783G06F16/75G06K9/62
CPCG06F16/783G06F18/23G06F18/22
Inventor 潘凌越傅一峰吴金贵
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD
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