Video text abstract generation method and device
A video and text technology, applied in the field of video text abstract generation methods and devices, can solve the problems of incomplete content coverage of video text abstracts, lack of video structured analysis and semantic analysis, lack of video text abstracts, etc. Full coverage, time-saving effects
Active Publication Date: 2020-04-28
山西医学期刊社有限责任公司
View PDF9 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Document 1 (Zhao Shujuan. Method Design and Research on Lecture Video Summary Extraction Based on Multimodal Fusion [D]. Beijing: Peking University, 2014.) uses the vocabulary TFIDF value to calculate the importance of sentences, which is used to generate video text summaries. The disadvantage lies in the lack of structural analysis and semantic analysis of the video, and only using the statistical characteristics of the video text, it is easy to cause incomplete coverage of the content of the video text summary
Document 2 (Sah S, Kulhare S, Gray A, et al.Semantic Text Summarization of Long Videos[C] / / Applications of Computer Vision.IEEE,2017:989-997.) uses Image Caption deep learning technology to generate a key frame Language description, but this method is only applicable to first-person video types
Based on the above analysis, the existing video summarization system and related research lack the invention and research of video text summarization, and there is a problem of incomplete coverage of video text summarization
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
[0059] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0060] The invention provides a method for generating a video text abstract, which is used in a device for generating a video text abstract. like figure 1 As shown, the video text summarization method specifically includes the following steps:
[0061] Step 1: Segment the video, calculate the video frame difference, filter out video segments that do not contain shot boundaries, and then com...
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 relates to a video text abstract generation method and device, and the method comprises the steps: carrying out segmentation of a video, calculating a video frame difference value, filtering a video segment which does not contain a shot boundary, comparing the video frame difference value with a threshold value, and detecting a video shot boundary; performing image information entropy calculation and corner detection on the video frames to obtain significance values of the video frames, and selecting the video frame with the highest significance value in a shot as a video key frame; performing theme division on the shot text by utilizing the domain ontology to obtain a video theme unit; calculating the weights of sentences in the video theme unit, and selecting sentences in acertain proportion from high to low according to the sentence weights to generate a video text abstract. The video text abstract generated by the invention can cover main information of the video more comprehensively, help a user to browse video content quickly, save time and improve efficiency.
Description
technical field [0001] The invention belongs to the technical field of video processing, and in particular relates to a method and device for generating a video text summary. Background technique [0002] With the rapid development of the Internet and multimedia devices, video data has penetrated into many aspects of our lives, such as transportation, retail, medical care, education, and public safety. The number of videos continues to grow rapidly. Users need to quickly search for the desired video from many videos, judge whether the video meets the demand, or quickly obtain the main content of the video. Therefore, video summarization technology is needed. [0003] In addition, in the prior art, research on video summarization technology is mostly research on video key frames and thumbnail videos, and there is relatively little research on video text summarization. Video text summarization has great application potential, especially for video types containing rich text in...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/738G06F16/78
CPCY02D10/00
Inventor 韩世范刘耀帅远华黄毅曹妍武建才
Owner 山西医学期刊社有限责任公司