Montage video determination method, device and equipment and storage medium

A determination method and mixed-cutting technology, applied in the direction of TV, color TV, color TV components, etc., can solve the problems of poor coherence and poor visual experience of mixed-cut video, to overcome video mixed-cut, improve coherence and user experience. The effect of the visual experience

Active Publication Date: 2020-07-17
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The mixed-cut video obtained by this method is usually poor in coherence, which leads to poor visual experience for users

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
  • Montage video determination method, device and equipment and storage medium
  • Montage video determination method, device and equipment and storage medium
  • Montage video determination method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] figure 1 It is a flow chart of a method for determining audio key points provided by Embodiment 1 of the present disclosure. This embodiment is applicable to the situation where mixed-cut video needs to be performed, and the method can be executed by a device for determining mixed-cut video, which can be implemented in software and / or hardware, and which can be configured in a computer device. Such as figure 1 As shown, the method may include the following steps:

[0035] S110. According to the preset background audio, sequentially determine the first video clip set corresponding to each audio clip; wherein, the audio clips are audio clips obtained by dividing the preset background audio according to the key points of the audio.

[0036] Preferably, the preset background audio can be pure music background audio, or background audio including lines and music. Audio key points can be used to extract each audio clip from the preset background audio, and audio key points...

Embodiment 2

[0088] Figure 2a It is a flow chart of an audio key point determination method provided in Embodiment 2 of the present disclosure. This embodiment can be combined with each optional solution in one or more of the above embodiments. In this embodiment, according to the first video feature representation data set, each first video segment finally used for mixed cutting is determined, including :

[0089] For each of the first video feature representation data sets, in the corresponding first video segment set, determine a candidate first video segment set;

[0090] Based on the second video feature, determine the second video feature characterization data corresponding to the candidate first video clip pair, wherein the two candidate video clips in the candidate first video clip pair respectively belong to two adjacent audio clips corresponding to Two candidate first video clip sets, the second video features include motion direction;

[0091] According to the second video f...

Embodiment 3

[0127] image 3 It is a schematic structural diagram of an apparatus for determining a mixed-cut video provided in Embodiment 3 of the present disclosure. This embodiment is applicable to the situation where mixed cutting of videos is required. The device can be implemented in the form of software and / or hardware, and the device can be configured in computer equipment. Such as image 3 As shown, the device may include:

[0128] The information determining module 310 is used to sequentially determine the first set of video clips corresponding to each audio clip according to the preset background audio; wherein, the audio clips are audio clips obtained after the preset background audio is divided according to the key points of the audio;

[0129] The first video feature characterization data set determination module 320 is configured to determine a first video feature characterization data set respectively corresponding to each first video segment set based on the first video...

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 embodiment of the invention discloses a montage video determination method and device, equipment and a storage medium. The method comprises the following steps: according to a preset background audio, sequentially determining a first video clip set corresponding to each audio clip, wherein the audio clips are obtained by segmenting a preset background audio according to the audio key points; determining a first video feature representation data set corresponding to each first video clip set based on the first video features, the first video features comprising at least two video features;according to each first video feature representation data set, determining each first video clip used for montage, wherein every two adjacent first video clips belong to a first video clip set corresponding to two adjacent audio clips; and sequentially splicing the adjacent first video clips by using a video splicing algorithm to obtain a target montage video. According to the technical scheme ofthe embodiment of the invention, the coherence of the montage video and the visual experience of a user are improved.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of video data processing, and in particular, to a method, device, device, and storage medium for determining a mixed-cut video. Background technique [0002] Mixing and cutting multiple videos into a single video and spreading it with popular music is a common scenario for short video applications at present. [0003] Video contains rich video feature information, which plays a very important role in video mixing and editing. Existing video mixing and cutting methods are usually based on a single video feature information. Taking the video feature information as the color richness as an example, this type of video mixed cutting method uses the background music change point as the video switching point, determines the optimal solution under the current segment based on the video color richness, and finally obtains the mixed cut video. The mixed-cut video obtained by this method is usu...

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): H04N5/265
CPCH04N5/265
Inventor 杨旭静靳潇杰
Owner BEIJING BYTEDANCE NETWORK 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