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

Video restoration method and system

A repair method and repair system technology, applied in the field of video processing, can solve problems such as cumbersome process, time-consuming and laborious, and achieve the effect of good repair effect and high efficiency

Active Publication Date: 2020-09-01
上海推乐信息技术服务有限公司
View PDF13 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although there are some tools in the prior art that provide the function of removing these additional content, these tools usually require manual operations, for example, manual selection of operation areas, manual identification of additional content, etc., not only the process is cumbersome, but also time-consuming and laborious

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 restoration method and system
  • Video restoration method and system
  • Video restoration method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0083] According to another aspect of the present invention, the present invention provides a video restoration system, such as Figure 8 As shown, the video restoration system includes a separation module 1 , a frame cutting module 2 , a detection module 3 , a filling module 4 and a synthesis module 5 . Wherein, the separation module 1 obtains basic information of the video from a given video to be repaired, such as resolution, frame rate, duration, total number of frames, etc., and separates the video and audio of the video to be repaired. For example, the basic information of the video can be obtained through OpenCV; the video and audio content can be obtained by using FFmpeg, and saved to the disk in the form of a file.

[0084] The frame cutting module 2 is connected with the separation module 1, and cuts the separated video into multiple video frames. For example, use OpenCV to complete frame cutting to obtain multiple video frames.

[0085] The detection module 3 is c...

Embodiment 2

[0091] Such as Figure 9 Shown is the functional block diagram of another video restoration system. In this example, with Figure 8 The difference between the embodiments is that after the detection module 3 of this embodiment obtains the additional content information according to the target detection algorithm, it also corrects it through the templates in the template library in order to further improve the accuracy of the obtained additional content information. Specifically, the detection module 3 includes a detection unit 31 , a template matching unit 32 and an additional information determination unit 33 . Wherein, the detection unit 31 uses a deep learning object detection algorithm to detect whether the video frame contains additional content, obtains the contour information of the additional content and its position information in the video frame, and obtains the category of the additional content. The template matching unit 32 is connected to the detection unit 31 ...

Embodiment 3

[0094] Such as Figure 10 As shown, it is a functional block diagram of the video restoration system in another embodiment of the present invention, as Figure 8 Compared with the embodiment shown in the present embodiment, the present embodiment includes a grouping module 7, which is connected to the detection module 3, and is configured to use an image histogram to perform scene segmentation on the video frame, and divide a plurality of video frames into segments according to the scene. a. For example, taking the background of the additional content of a synthesized video frame as a scene, video frames similar to its background are divided into one group, so that all video frames can be divided into multiple groups, and each group of video frames includes at least one synthesized video frame frame, the background of other video frames is the same or similar to the background of the synthesized video frame.

[0095] When the filling module 4 performs image filling on the 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

No PUM Login to View More

Abstract

The invention relates to a video restoration method and system, and the method comprises the steps: separating a video and an audio of a to-be-restored video, and enabling the to-be-restored video tocomprise additional contents; performing frame cutting processing on the video to obtain a plurality of video frames; performing target detection on the plurality of video frames to obtain additionalcontent information; obtaining matched image information, and filling an image area where the additional content is located with the image information; and synthesizing the filled video frame and theseparated audio into a restored video. When the original video is restored, manual operation is not needed, the removal effect is good, and the efficiency is high.

Description

technical field [0001] The invention relates to the technical field of video processing, in particular to a video repair method and system for eliminating added additional content. Background technique [0002] In the field of video applications, with the development of video editing technology, it is allowed to add some additional content to the video to obtain a composite video. For example, static information such as text and images can be added to the video, and dynamic information such as animation can also be added to the video. However, irrelevant information such as advertisements and clips in synthetic videos are often objectionable. Therefore, it is sometimes necessary to eliminate these additions from the composite video. Although there are some tools in the prior art that provide the function of removing these additional content, these tools usually require manual operations, for example, manual selection of operation areas, manual identification of additional ...

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): H04N21/44H04N21/234H04N21/233H04N21/439G06T5/00
CPCH04N21/44008H04N21/23418H04N21/234H04N21/233H04N21/44H04N21/439G06T2207/10016G06T2207/20081G06T2207/20084G06T5/77
Inventor 赵玉良郭玉峰黄鑫何林晋吴昌猛王连杰张博伦
Owner 上海推乐信息技术服务有限公司
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