Lens edge detection method based on TextTiling

A lens boundary detection and boundary technology, which is applied in image data processing, instruments, calculations, etc., can solve the problem of not being able to detect video boundaries, and achieve the effects of avoiding fluctuations and improving accuracy

Inactive Publication Date: 2017-12-01
GUANGDONG POLYTECHNIC NORMAL UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] Sahouria et al. used Principal Component Analysis (PCA) to reduce the dimensionality of features extracted from video frames, but this algorithm cannot detect specific video boundaries, but is used to discover high-dimensional video scenes

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
  • Lens edge detection method based on TextTiling
  • Lens edge detection method based on TextTiling
  • Lens edge detection method based on TextTiling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The drawings are for illustrative purposes only, and should not be construed as limitations on this patent; in order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0041] For those skilled in the art, it is understandable that some well-known structures and descriptions thereof may be omitted in the drawings. The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0042] Aiming at the problem of shot boundary detection accuracy, the present invention proposes a shot boundary detection method based on TextTiling. The method uses principal component analysis to extract the features of video frames, and takes sliding windows as units to project frames in each window. To the feature subspace formed by the respective windows, the distance between adjacent frames and the depth v...

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 lens edge detection method based on TextTiling. The method includes: extracting characteristics of a video frame by employing a principal component analysis method, projecting a frame in each window to a characteristic sub-space formed by each window by employing a slide window as the unit, and calculating the distance between adjacent frames and depth values of potential edges to recognize video lens edges. According to the method, the possibility of the appearance of lens shot cut is further evaluated through introduction of the depth values by employing the TextTiling method, and the precision of edge recognition of the lens is improved; besides, the fluctuation caused by local color difference of an inter-frame color histogram is avoided through extraction of the characteristics of the video frame by means of the PCA, and frame expression is more accurate.

Description

technical field [0001] The present invention relates to the field of video shot boundary detection, and more particularly, relates to a shot boundary detection method based on TextTiling. Background technique [0002] Video shot boundary detection is the primary work and one of the key technologies in content-based video retrieval. In recent years, many scholars in related fields at home and abroad have done a lot of fruitful work. Typical algorithms are as follows: [0003] (1) Edge-based algorithm [0004] The basic idea of ​​the edge-based algorithm is that when the lens changes, the edge of the object in the lens changes accordingly, so the boundary of the lens can be detected according to the change of the edge. Zabih et al. proposed an edge-based scene segmentation algorithm, which uses the Canny algorithm to extract the edge features of frames to calculate the edge changes of adjacent frames, and judges whether the edge changes cause lens changes through a suitable ...

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 & AuthorityApplications(China)
IPC IPC(8): G06T7/13G06T7/136G06T7/90
CPCG06T7/13G06T7/136G06T7/90G06T2207/10016G06T2207/10024
Inventor贾西平谢彬彬陈荣军柏柯嘉廖秀秀欧阳佳刘少鹏张倩
OwnerGUANGDONG POLYTECHNIC NORMAL UNIV