Detection method and system for sensitive video

A video and sensitive technology, applied in the field of computer vision, can solve problems such as inaccurate detection results of sensitive video, achieve the effect of solving inaccurate detection results, improving precision and accuracy, and reducing the number of false alarms

Active Publication Date: 2015-09-30
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a sensitive video detection method and system to solve the problem of inaccurate detection results of sensitive video

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
  • Detection method and system for sensitive video
  • Detection method and system for sensitive video
  • Detection method and system for sensitive video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] refer to figure 1 , which shows a flow chart of a sensitive video detection method according to an embodiment of the present invention. This embodiment may specifically include the following steps:

[0038] Step 101, extract key frames from the video to be detected.

[0039] In this embodiment, the extraction of key frames from the video to be detected can be realized by using a frame difference method based on color (or histogram), a method based on motion analysis or a method based on video frame clustering. Among them, the key frames of the video are extracted through the video frame clustering method, that is, the frames of the video shots are divided into several categories through cluster analysis, and the points closest to the cluster center are selected to represent the cluster points, and finally the key frame set of the video sequence is formed. . It should be noted that, in this embodiment, there is no limitation on the specific method for extracting the ke...

Embodiment 2

[0055] On the basis of the foregoing embodiments, this embodiment continues to discuss the sensitive video detection method.

[0056] refer to figure 2 , which shows a flow chart of a sensitive video detection method according to an embodiment of the present invention. This embodiment may specifically include the following steps:

[0057] Step 201, extract key frames from the video to be detected.

[0058] In this embodiment, the key frame of the video to be detected can be extracted by using the color (or histogram) frame difference method to extract the key frame, or based on the motion analysis method or based on the video frame clustering method to extract the key frame. Keyframes can be extracted at intervals, or it can be determined whether it is a keyframe by calculating the difference in color (or grayscale) of several adjacent frames, and the keyframe can also be extracted based on the method of motion analysis. Among them, the key frames of the video are extracted...

Embodiment 3

[0097] On the basis of the above embodiments, this embodiment also discloses a sensitive video detection system.

[0098] refer to Figure 11 , shows a structural block diagram of a sensitive video detection system according to an embodiment of the present invention. This embodiment may specifically include: a key frame extraction module 301, a human motion detection module 302, a human body tracking module 303, a skin color detection module 304, and feature extraction Module 305 and sensitivity determination module 306, wherein:

[0099] The key frame extraction module 301 is used for extracting key frames from the video to be detected.

[0100] The human body motion detection module 302 is configured to perform a frame difference on any two consecutive key frames, and obtain a human body target area according to the result of the frame difference.

[0101] The human body tracking module 303 is configured to track the human body target area in a plurality of consecutive key...

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 provides a detection method and system for a sensitive video. With the method and system, a problem of inaccuracy of a detection result of a sensitive video can be solved. The detection method comprises: key frames are extracted from a to-be-detected video; frame difference processing is carried out on any two continuous key frames and a human body object region is obtained according to a frame difference result; the human body object region is tracked in multiple continuous key frames and human body object regions of all key frames are determined according to the tracking result; skin color detection is carried out on the human body object regions of all key frames at at least two color spade so as to determine skin color points of all key frames; on the basis of the skin color points of all key frames, skin color point feature information of the to-be-detected video is calculated, wherein the skin color point feature information contains a skin color proportion and a skin color point proportion changing amplitude; and whether the skin color point feature information of the to-be-detected video is larger than a preset feature threshold value; if so, the to-be-detected video is determined to be a sensitive video. With the method and system, precision and accuracy of skin color detection are improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a sensitive video detection method and system. Background technique [0002] With the rapid development of the Internet, users can obtain a large amount of information on the Internet, but users may also encounter a lot of bad information while obtaining a large amount of useful information, especially videos containing obscenity and pornography. Therefore, during video review, it is necessary to detect and filter the above-mentioned sensitive videos containing obscene and pornographic content. [0003] The current sensitive video detection methods basically only consider relevant parameters such as the proportion of skin color points in the current frame image. However, the above-mentioned detection method is not very robust, and some non-skin-colored points of the current frame image are recognized as skin-colored points, resulting in misjudgment, and the accuracy of t...

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): G06K9/00G06K9/46G06K9/62
Inventor 兰细鹏王涛张彦刚
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

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