Visual understanding and diagnosis method of interactive video abstract model

A video summary, interactive technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve difficult problems

Pending Publication Date: 2020-04-24
ZHEJIANG UNIV OF TECH
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, it is difficult to simultaneously apply a model

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
  • Visual understanding and diagnosis method of interactive video abstract model
  • Visual understanding and diagnosis method of interactive video abstract model
  • Visual understanding and diagnosis method of interactive video abstract model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] specific implementation plan

[0039] The present invention will be further described below in conjunction with accompanying drawing.

[0040] refer to Figure 1 to Figure 7 , a visual understanding and diagnosis method of an interactive video summarization model, the present invention uses D3.js to draw the front-end interface, and the background data is obtained through Java.

[0041] The visual comprehension and diagnosis method of the interactive video summarization model comprises the following steps:

[0042] 1) model analysis; by extracting the visual features and semantic features of each frame in the video summary data set video, the present invention inputs the features into the machine learning model to obtain the corresponding salience score, and the corresponding flow chart is as follows figure 1 shown;

[0043] (1-1) Descriptive feature extraction; in order to help researchers understand each frame in the video more deeply, the present invention divides...

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 discloses a visual understanding and diagnosis method for an interactive video abstract model, and the method comprises the following steps: carrying out the feature extraction of an original video set, obtaining five descriptive feature scores, taking the extracted features as a verification set, and obtaining a significance score through machine learning training; through the abovesteps, performing interactive visual analysis of multi-feature inspection and multi-level exploration through the video view, the projection view, the detail view and the continuous frame view. A user is helped to explore and analyze video content and internal relations existing in a video abstraction model. According to the invention, data are obtained through a model analysis method, and a visual understanding and diagnosis method of an interactive video abstract model is designed to help understand the internal relation existing in the video abstract model. And a set of visual analysis system is provided to help a user to explore and analyze video contents, and the model is deeply explored from three aspects of videos, events and frames through a video view, a projection view, a sequence frame view and a detail view.

Description

technical field [0001] The invention relates to a method for visual understanding and diagnosis of an interactive video summarization model. Background technique [0002] With the rapid development of multimedia network technology and the popularization of video capture devices, it directly leads to the increase of storage resource consumption and the increase of video content classification and indexing costs. Faced with such a dilemma, video summarization is often considered as an effective way to solve this problem. Video summarization generates concise summary videos in an automatic or semi-automatic manner by extracting meaningful segments or key frames from the original video. Video summarization can preserve the diversity of the original video while reducing storage space and transmission time, helping users quickly browse or retrieve videos. [0003] At this stage, in the research of video summarization, researchers usually combine typical machine learning methods ...

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): G06K9/00
CPCG06V20/47G06V20/41
Inventor 孙国道朱琳吴昊徐超清梁浩然徐斌伟梁荣华
Owner ZHEJIANG UNIV OF TECH
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