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

Method and device for identifying objectionable video content

A bad video and content recognition technology, applied in character and pattern recognition, image data processing, instruments, etc., can solve the problems of bad video misjudgment and bad video missed judgment, so as to improve the efficiency of research and judgment, improve the accuracy and recognition rate , the effect of reducing the amount of calculation

Active Publication Date: 2013-02-13
CHINA MOBILE GROUP SHAIHAI
View PDF2 Cites 53 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The method of researching and judging the entire video based on extracting the key frames of the video stays in the detection of the static image features of the key frames, which is likely to cause misjudgment of bad videos. At the same time, there are not many bad key frames in bad videos. In a more concentrated situation, it is easy to cause missed judgments on bad videos

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 identifying objectionable video content
  • Method and device for identifying objectionable video content
  • Method and device for identifying objectionable video content

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Such as figure 1 As shown, it is a flow chart of judging a bad video using the motion feature-based video shot recognition method proposed in the embodiment of the present invention. The specific implementation process is as follows:

[0037] Step 11, for an input video file to be detected or a section of video stream, extract video key frames;

[0038] 1) Use the k-means clustering method to extract video key frames from the video to be detected, specifically: first divide the video to be detected into N segments according to equal time intervals, and randomly select a video within the divided N time intervals Frame, the extracted N video frames represent the cluster center frames of N clusters respectively;

[0039] 2) Then, for each video frame in the video to be detected except the cluster center frame, execute separately: respectively calculate the similarity between the video frame and the N cluster center frames, according to the calculated video frame and The ...

Embodiment 2

[0082] In the first embodiment, the method of judging whether the video content to be detected is bad video content based on the motion information of the video to be detected is discussed in detail, further, as image 3 As shown, it is a flow chart of a method for comprehensively judging a bad video based on the image features of the video key frame and the motion features of the video lens proposed by the embodiment of the present invention, and the specific implementation process is as follows:

[0083] Step 31, for an input video file to be detected or a section of video stream, extract video key frames;

[0084] For details about the process of extracting video key frames, please refer to the detailed discussion in step 11 in the first embodiment above, and details will not be repeated here.

[0085] Step 32, analyze each extracted video key frame respectively, and obtain the relevant features among the extracted multiple video key frames;

[0086] Step 33, according to ...

Embodiment 3

[0095] The basic research method of video structural analysis is to make structural assumptions on video data, and then carry out progressive analysis of video data from low-level semantics to high-level semantics from video frames, video shots, video scenes to video stories and other logical concepts . Among them, a video shot is a physical unit composed of continuous video frames during a recording period, and a video scene is considered to be the smallest semantic unit that occurs continuously at the same place in time or describes a certain group of coherent behaviors. At the semantic level, video scenes have better description capabilities and are easier to be understood and accepted by people. Therefore, a video scene can become a descriptive unit in objectionable video content detection.

[0096]On the basis of comprehensively considering the static and dynamic features of the video to be detected, this embodiment further adopts the video scene as the discrimination un...

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 for identifying objectionable video content. The method comprises the following steps of extracting video key frames in a video to be detected; grouping the video key frames, wherein each group of grouped video key frames form a video shot which performs shot segmentation on the video to be detected; executing each segmented video shot; extracting movement feature information of the video shot, and determining whether the video shot is an objectionable video shot or not according to the extracted movement feature information; and determining whether the video to be detected is the objectionable video content or not according to the quantity of the determined objectionable video shots. According to the method for identifying the objectionable video content, the identification accuracy of the objectionable video content can be improved.

Description

technical field [0001] The invention relates to the technical field of data services, in particular to a method and device for identifying bad video content. Background technique [0002] With the rapid development of mobile communication technology, mobile multimedia information services are becoming more and more popular in people's daily life. Many services based on modern mobile multimedia information, such as SMS, MMS, mobile newspapers, mobile tickets, mobile TV and streaming media, etc. Being developed and applied in people's daily life, these services bring some potential dangers while bringing convenience to people. Various types of bad video information such as pornographic violence, cult transmission, hostile propaganda, and pirated content have appeared on mobile terminals such as mobile phones. How to effectively control these bad videos based on mobile multimedia services and protect mobile multimedia information Content security has become one of the main con...

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): G06T7/20G06T7/00G06K9/62
Inventor 王斌周晨艳贝悦李辉朱剑
Owner CHINA MOBILE GROUP SHAIHAI
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com