Video matching method
A video, to-be-matching technology, applied in the field of video matching, can solve problems such as slow matching speed, and achieve the effect of improving matching accuracy, improving efficiency, and strong fault tolerance.
Pending Publication Date: 2021-04-02
季鹏飞
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] Due to the rapid development of the Internet in recent years, especially the development of the mobile Internet, the spread of videos has increased significantly, and the copyright of videos has also been taken seriously. It is very slow to manually judge whether a video clip belongs to a certain video
The traditional automatic judgment method is frame-by-frame comparison. If all frame data are equal in turn, the matching is considered successful. The matching speed is slow and the aspect ratio of the video clip changes, or the video is degraded. This method will fail.
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
[0027] Below will be combined with the appended in the embodiment of the present invention Figure 1-5 , clearly and completely describe the technical solutions in the embodiments of the present invention, obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention belong to the protection scope of the present invention.
[0028] The present invention provides a technical solution: wherein, the public module S is a program used to compare two video key frames in the prior art, wherein the threshold α is an artificially set value, and the value output by the public module is greater than α, which means that the matching is successful , otherwise the matching fails. The neural network matching module is a supervised learning artificial intelligence technology, which is also an existing technology. In this s...
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 invention discloses a video matching method. The method comprises the following steps: S1, preprocessing a to-be-matched video; s2, preprocessing the original video; s3, pre-training a neural network; and S4, high-efficiency matching: performing high-efficiency matching operation on the to-be-matched video and the original video. Key frames are extracted from scene conversion points in a video, key frame data are further extracted and compressed through convolution and pooling operation to form a new key frame sequence, the key frame sequence is matched, the matching speed is greatly increased through an efficient matching algorithm and a neural network, and the matching accuracy is improved. Compared with a traditional frame-by-frame comparison mode, the matching speed and the matching accuracy are greatly improved.
Description
technical field [0001] The invention relates to the technical field of video matching and screening, in particular to a video matching method. Background technique [0002] Due to the rapid development of the Internet in recent years, especially the development of the mobile Internet, the spread of videos has increased significantly, and the copyright of videos has also been taken seriously. It is very slow to manually judge whether a video clip belongs to a certain video. The traditional automatic judgment method is frame-by-frame comparison. If all frame data are equal in turn, the matching is considered successful. The matching speed is slow and the aspect ratio of the video clip changes, or the video is degraded. This method will fail. Contents of the invention [0003] The purpose of the present invention is to provide a video matching method that can quickly and automatically identify whether a video segment belongs to an original video, even if the video segment is ...
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 IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/46G06V20/48G06F18/22
Inventor 季鹏飞季坤朋周培明
Owner 季鹏飞