Video collection generation method and device, electronic equipment and storage medium

A collection and video technology, applied in the information field, can solve problems such as high technical requirements, low efficiency, inaccuracy, etc., to achieve the effect of reducing technical requirements, simplifying generation, and reducing manual errors

Active Publication Date: 2019-04-19
SHENZHEN SENSETIME TECH CO LTD
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing technology, the generation of video collections requires staff to watch each video and then manually intercept and stitch them into video collections. On the one hand, this method is inefficient, and on the other hand, it is caused by complicated video scenes or a large number of

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 collection generation method and device, electronic equipment and storage medium
  • Video collection generation method and device, electronic equipment and storage medium
  • Video collection generation method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0203] This example provides a method for automatically generating video highlights, using football videos as an example for illustration but not limited to football videos. For example, in this example, a deep learning framework is used to solve the problem of automatically generating football video highlights. Through the powerful learning ability of the deep neural network, the video image and audio information are modeled separately. Use the text recognition function to detect the score position and real-time score in the game screen through statistical features, and output the score information. This example proposes a deep learning-based multimodal approach to more accurately locate highlights in football match videos.

[0204] A video collection for this example could include the following steps:

[0205] Step 1: Cut the video with the lens cutting method.

[0206] Step 2: Extract frames for each cut video (9 frames for each shot), and extract the audio of each video...

example 2

[0217] Such as Figure 5 As shown, this embodiment provides a method for generating video highlights, including:

[0218]Use the video lens cutting model to cut the video into separate shots; in some scenes, the shots are also numbered to mark the order of these separated shots in the video;

[0219] Extracting the image frames of the lens to obtain n image frames extracted, optionally, one lens contains more than n image frames;

[0220] Using the neural network to classify n image frames and averaging the classification results, the final image classification results are obtained based on the average;

[0221] From the perspective of image content, the primary classification result of shot classification is obtained based on the image classification result;

[0222] Extract the audio of each shot, and all the audio contained in a shot may include one or more audio frames;

[0223] Using convolutional neural network to classify audio, from the perspective of audio content,...

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 provides a video collection generation method and device, electronic equipment and a storage medium. The method comprises the following steps: classifying according tothe content of a video frame to obtain a classification result; Determining a specific video segment containing predetermined content according to the classification result; And generating a video collection based on the specific video segment.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a method and device for generating a video collection, electronic equipment and a storage medium. Background technique [0002] A video collection is the editing of different videos or video segments with similar content into one video. For example, for a ball game, the video highlight may be a goal highlight. In the existing technology, the generation of video collections requires staff to watch each video and then manually intercept and stitch them into video collections. On the one hand, this method is inefficient, and on the other hand, it is caused by complicated video scenes or a large number of videos. The editing of various types of artificial video highlights has high technical requirements for the staff; and due to problems such as artificial fatigue, it will cause omissions to varying degrees; on the other hand, it may also cause various inaccurate proble...

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
IPC IPC(8): G06F16/738G06F16/75
Inventor 卢宇范宏伟罗思伟
Owner SHENZHEN SENSETIME 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