System and method for automatic extraction and generation of audiovisual product content abstract

A content abstraction and automatic extraction technology, applied in the field of computer vision and natural language understanding, can solve the problems of disturbing the story structure, lack of focus in key frame selection, and unable to reflect the semantic structure of video content well.

Inactive Publication Date: 2014-03-19
上海紫竹高新数字创意港有限公司
View PDF4 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its advantage is that it is easy to implement and relatively objective, and it is still the most widely used technology in the industry, such as the preview method of Youku and LeTV Video; the disadvantage is that the selection of key frames has no focus, and it does not conform to the non-uniformity of the temporal and spatial structure of the story , cannot reflect the semantic structure of the video content well
However, compared with audio-visual media information, this technology basically disrupts the original story structure

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
  • System and method for automatic extraction and generation of audiovisual product content abstract
  • System and method for automatic extraction and generation of audiovisual product content abstract
  • System and method for automatic extraction and generation of audiovisual product content abstract

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to describe the technical content of the present invention more clearly, further description will be given below in conjunction with specific embodiments.

[0052] Such as figure 1 As shown, the system for realizing the automatic extraction and generation of audio-visual product content summaries of the present invention includes:

[0053] The audio-visual media decoding module is used to decode audio-visual media and extract audio streams, video streams and encoded text streams;

[0054] A speech processing module for extracting audio features from the audio stream and performing speech recognition on features that conform to the speech features;

[0055] The text extraction module is used to detect and confirm the position of subtitles in audio-visual media and segment and recognize subtitles according to the speech recognition results to extract text keywords;

[0056] The scene segmentation module is used to extract key frames between shots according to a...

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 system and a method for automatic extraction and generation of an audiovisual product content abstract. The system comprises an audiovisual media decoding module, a voice processing module, a text extracting module, a scene segmenting module and a scene semantic annotation and abstract generating module, wherein the scene semantic annotation and abstract generating module is used for generating a text abstract of audiovisual media according to text keywords extracted by the text extracting module and generating a video abstract of the audiovisual media according to scenes aggregated by the scene segmenting module. With adoption of the structure, the system and the method for automatic extraction and generation of the audiovisual product content abstract has the advantages that text keyword information is blended in a conventional scene segmentation algorithm, accordingly, obvious semantic features are provided while the scene is segmented, an audiovisual multimedia content abstract based on semantics is approached by one step, the problem that the text abstract is irrelevant with low-level features is solved simultaneously, so that the text abstract and the video abstract are in accordance semantically, and the system and the method are suitable for large-scale popularization and application.

Description

technical field [0001] The present invention relates to the fields of computer vision and natural language understanding, in particular to the field of extracting audio-visual product content abstracts, and specifically refers to a system and method for automatically extracting and generating audio-visual product content abstracts. Background technique [0002] With the rapid development of network and multimedia technology, multimedia data has exploded. Faced with massive audio-visual media data, people urgently need technologies that can quickly retrieve and browse multimedia data. However, the richness and diversity of audio-visual media data, as well as the unique spatio-temporal high-dimensional structure of feature data, make how to effectively express, store, and manage massive videos become a research hotspot in academia and a focus of industry. focus. Video summarization technology came into being. [0003] Video abstract (Video Abstract), that is, to analyze the...

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): G06F17/30G06F17/27
CPCG06F16/739H04N21/8549
Inventor 董建磊张树民
Owner 上海紫竹高新数字创意港有限公司
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