A near-duplicate video detection method based on Topritz kernel partial least squares

A technology of nuclear partial least squares and video detection, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as weak space transformation, improve accuracy, quickly and accurately find resources, and reduce computing consumption Effect

Inactive Publication Date: 2018-12-07
JIANGSU UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods are strong in coping with temporal transformations, but weak in strong spatial transformations

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 near-duplicate video detection method based on Topritz kernel partial least squares
  • A near-duplicate video detection method based on Topritz kernel partial least squares
  • A near-duplicate video detection method based on Topritz kernel partial least squares

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and 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.

[0036] In order to evaluate the performance of the near-repetition video detection method (KPLS_FFT) based on Toeplitz Kernel Partial Least Squares proposed by the present invention, this method is compared with four existing near-repetition video detection methods, which are : A method based on global features (BCS), a sequence matching method based on edit distance (SE), a self-similar belt method (SSBelt), and a retrieval method based on canonical correlation analysis (CCA).

[0037] To measure detection accuracy, the present invention uses a Precision-Recall (PR) curve. in,

[0038]

[003...

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 near-duplicate video detection method based on Topritz kernel partial least squares. The method comprises the following steps: performing fast circulating matrix transformation on an original video X and an inquiry video Y in a Fourier domain respectively; performing fast circulating matrix transformation on a query video Y in a Fourier domain; correlating the original video X and the query video Y with each other by using partial least square method to get the feature problem; obtaining an eigenvalue and an eigenvector by solving the eigenvalue problem.; using chi-square test to eliminate the value in statistical randomness lambda; calculating a DoC value to determine whether the original video X and the query video Y are close to each other; in resource searching, utilizing the kernel partial least square to improve the precision of searching. The Topritz matrix is used to improve the speed of searching in a Fourier domain, so as to reduce the computationalcost and improve the efficiency of resource searching.

Description

technical field [0001] The invention belongs to the field of video detection, in particular to a near-repetitive video detection method based on Toeplitz kernel partial least squares. Background technique [0002] With the development of the Internet, a large number of video-related applications and services continue to emerge on the Internet, such as video sharing, video recommendation, and video broadcasting. The Internet is full of massive video data and shows a trend of rapid growth. There are a large number of potential near-duplicate videos in the video data, so how to detect and remove these near-duplicate videos attracts a lot of research. [0003] There are mainly three existing near-duplicate video detection methods, namely: video-level, frame-level and mixed-level near-duplicate video detection methods. [0004] First of all, it was proposed that the Multi Feature Hashing (MFH) method based on the supervision method is a typical video-level near-duplicate video d...

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 Applications(China)
IPC IPC(8): G06F17/30
Inventor 陶佳丽张建明沈项军
Owner JIANGSU UNIV
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