Video screening method, device and storage medium
A screening method and video quality technology, applied in the field of video screening, can solve the problems of low accuracy of duplicate checking results, high labor costs, and high false positives
Active Publication Date: 2020-06-26
北京海天瑞声科技股份有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
For manual comparison, not only the labor cost is high, but also the probability of false detection is high
For people who have been duly recorded through the face plagiarism check algorithm, since the face plagiarism check algorithm can only calculate the similarity between two static pictures, the accuracy of the plagiarism check result is not high
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0037] The principle and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present disclosure, rather than to limit the scope of the present disclosure in any way.
[0038] It should be noted that although expressions such as "first" and "second" are used herein to describe different modules, steps, data, etc. of the embodiments of the present disclosure, expressions such as "first" and "second" are only for A distinction is made between different modules, steps, data, etc., without implying a particular order or degree of importance. In fact, expressions such as "first" and "second" can be used interchangeably.
[0039] In computer vision training for face video algorithms, a large amount of face video data needs to be collected. In the process of collecting a large number of face data...
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
Login to View More Abstract
The disclosure relates to a video screening method, device and storage medium. Wherein, the video screening method includes: obtaining a video set, the video set includes a plurality of video subsets respectively corresponding to the target person, the video subset includes one or more video clips, and the video clip includes the target person; based on the video clip, the video The first representative frame picture and multiple second representative frame pictures of the segment; the feature vector of the first representative frame picture and the feature vectors of each second representative frame picture are obtained, and based on the feature vector of the first representative frame picture and each second representative frame picture The feature vector representing the frame picture determines the feature vector of the video segment; based on the feature vector of the video segment in the video subset, it is judged whether any two video subsets belong to the video subset of the same target person; if the two video subsets belong to the same target If the person is a video subset, one of the two video subsets is deleted. The accuracy rate of filtering out repeated video segments is improved through the present disclosure.
Description
technical field [0001] The present disclosure relates to the technical field of video screening, in particular to a video screening method, device and storage medium. Background technique [0002] In computer vision training for face video algorithms, a large amount of face video data needs to be collected. In the process of collecting a large number of face data, it is inevitable that personnel will repeatedly collect and record, which will interfere with the subsequent production of video training sets and video model training. [0003] In addition to using manual comparison to find and eliminate repeated recording personnel, you can also use the face plagiarism check algorithm to find repeated recording personnel. For manual comparison, not only the labor cost is high, but also the probability of false detection is high. For people who are repeatedly recorded through the face plagiarism check algorithm, since the face plagiarism check algorithm can only calculate the si...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/783G06K9/00
CPCG06F16/784G06V40/161G06V20/40
Inventor 刘杰辰曹琼黄宇凯郝玉峰李科
Owner 北京海天瑞声科技股份有限公司