Video copy detection method based on compact video representation

A video copy detection and video technology, which is applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of being out of practicality, increasing calculation time, and decreasing the accuracy of results, so as to improve accuracy and recall rate , the number of features is reduced, and the effect of avoiding performance burden

Active Publication Date: 2017-05-10
DALIAN UNIV OF TECH
View PDF3 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, although the frame images of the same second are similar but have different details, if only one or two frames are used to represent the one-second segment, part of the information will be lost, which will reduce the description abil

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 copy detection method based on compact video representation
  • Video copy detection method based on compact video representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] Example: Video Copy Detection for Complex Databases

[0030] 1. Extract all the frames in the library video as key frames.

[0031] 2. Use the convolutional neural network, and use the pre-trained public model VGG-16 model to calculate the key frames obtained in step 1, and extract the 4096-dimensional features of the fc6 layer.

[0032] 3. Sampling 100,000 eigenvectors, and performing principal component analysis algorithm and dictionary training in ksvd algorithm. Among them, the dictionary dimension of principal component analysis is 256*4096, and the dictionary dimension of ksvd is 256*1024, that is, n=256, m =1024.

[0033] 4. Use the trained principal component analysis dictionary to reduce the dimensionality of all the features in step 2 and perform whitening processing to obtain 256-dimensional frame features.

[0034] 5. Use the omp algorithm and the dictionary of ksvd to calculate the frame features obtained in step 4, and calculate a 1024-dimensional sparse...

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 belongs to the field of digital media and provides a video copy detection method based on compact video representation. The method comprises following steps: densely extracting keyframes of video library and inquiring video; extracting the image sparse features of the keyframes of the video library and the inquiring video; by means of the pooling mode, the image sparse features of the video library and the inquiring video are merged to form concise video features. The beneficial effects of the invention are: by means of the method, video information can be accurately described; feature data is effectively reduced; the retrieval is accelerated greatly; the method combines deep learning method and traditional method; on the premise of accurate matching, machine performance load is reduced and the problems in the prior art are solved.

Description

technical field [0001] The invention belongs to the field of digital media, and mainly relates to a video copy detection method based on compact video representation. Background technique [0002] As video copyright issues are getting more and more attention, how to quickly identify whether a video is a copy of another video has become a key technology in the field of digital media. The copied video can be the original video, a small fragment intercepted from the original video, or a fragment of the original video spliced ​​with other irrelevant videos. At the same time, the copied video may be inserted into irrelevant occlusions (subtitles, logos, etc.), changing the aspect ratio, changing the color and brightness, changing the resolution, picture-in-picture, re-recording and other deformation methods. Using an effective representation to describe the video, so that the computer can quickly and accurately determine whether a query video is a copy of the library video, and ...

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): G06F17/30
CPCG06F16/783G06F16/7847
Inventor 李豪杰王领暴雨
Owner DALIAN 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