Unlock instant, AI-driven research and patent intelligence for your innovation.

A video saliency analysis method and device

An analysis method and remarkable technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of inability to obtain accurate and comprehensive video data, and achieve the effect of improving accuracy

Inactive Publication Date: 2018-01-05
CHINA AGRI UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defect that accurate and comprehensive video data saliency cannot be obtained in the prior art, the present invention provides a video saliency analysis method and device

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
  • A video saliency analysis method and device
  • A video saliency analysis method and device
  • A video saliency analysis method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical solution of the present invention will be further described in detail in conjunction with the accompanying drawings and embodiments.

[0042] figure 1 A schematic flow chart showing the video saliency analysis method in this embodiment, as figure 1 As shown, a video saliency analysis method provided in this embodiment includes:

[0043] S1, for the video stream to be analyzed, extract all key frames.

[0044] Wherein, the extraction of the key frame can be performed according to the distance between adjacent frames, for example, a frame is arbitrarily extracted from the acquired video as the first key frame, and then the key frame adjacent to the first key frame is judged Whether the grayscale distance of the frame is greater than the preset threshold, if greater, the adjacent frame is the second key frame, otherwise, the next frame is judged, and it is executed in sequence until all the key frames in the video are extracted.

[0045] The method for ext...

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 the technical field of video data mining, in particular to a video saliency analysis method and device. The video saliency analysis method includes: for the video stream to be analyzed, extracting all key frames; for each of the key frames, obtaining a saliency map corresponding to the key frame; obtaining the audio descriptor of the video stream to be analyzed; The acquired saliency maps corresponding to all the key frames are associated with the audio descriptors of the video stream to be analyzed to obtain the video saliency map of the video stream. Extract the saliency map by combining the static saliency including color and brightness with the spatial motion change characteristics of the video image, and manage and match it with the audio data, so as to obtain the comprehensive saliency of the video data, effectively The accuracy of video saliency analysis is greatly improved.

Description

technical field [0001] The invention relates to the technical field of video data mining, in particular to a video saliency analysis method and device. Background technique [0002] With the development of digital technology, video data has also shown explosive growth. How to quickly perform semantic analysis and information acquisition on videos will help improve the storage, classification and retrieval speed of massive videos, and improve management efficiency. [0003] The existing video saliency analysis method mainly divides each frame of the video into superpixel units, then calculates the measure of each superpixel unit, and fuses the obtained measure values ​​to obtain the saliency map of the superpixel unit , and finally perform bilateral Gaussian filtering on the saliency map of the superpixel unit to obtain the video saliency map. [0004] However, the prior art does not involve the influence of brightness information and audio information on video saliency anal...

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 Patents(China)
IPC IPC(8): G06F17/30
Inventor 高万林陈雪瑞贾敬敦张港红于丽娜任延昭徐东波朱佳佳陶红燕
Owner CHINA AGRI UNIV