Lens boundary detection method

Abstract

The invention discloses a lens boundary detection method which comprises the following steps of: 1) video frame character representation: calculating a non-uniform block histogram of each frame in the video in an HSV color space based on a general parallel calculation architecture as the characteristic representation of the video frame; 2) obtaining of similarity sequence, wherein the similarity of adjacent video frames is obtained by calculating the weight sum of the histogram distances of corresponding blocks, and the similarity sequence is a sequence consisting of the similarities of all adjacent video frames in the video; and 3) identification of lens boundary: for the detection of lens shear boundary, calculating the threshold by use of an adaptive threshold algorithm based on the similarity sequence, wherein the place with a similarity bigger than the threshold is the lens shear place. The detection of lens gradient boundary comprises the following steps of: finding the candidate gradient boundary by use of the inversion pair counting algorithm, and forming unified expression by use of Fourier function fitting; and comparing the candidate boundary with the standard gradient model to determine the gradient boundary and identity the gradient type thereof.

Description

technical field [0001] The invention relates to a lens boundary detection method based on adaptive threshold and Fourier function fitting, in particular to a detection method for lens gradient boundaries of special effects of fading in, fading out and ablation. Background technique [0002] With the rapid development of multimedia information technology, a large amount of video data began to pour into people's daily life, common such as news, advertisements, movies and so on. The emergence of massive video data has greatly promoted the progress of video archiving, cataloging and indexing technology. As the basis of the above technologies, automatic detection of shot boundaries has been extensively researched and applied in recent years. There are two basic types of shot boundaries. One is the shear boundary, which refers to switching directly from one shot to another without any continuous transition in the middle. There are both content and color between adjacent frames. ...

AI Technical Summary

Problems solved by technology

These methods have achieved good results for shear boundary detection, but these methods are usually plagued by threshold selection problems. Too large or too small thresholds will affect the accuracy and recall of detection. The current shear boundary detection hopes to It can get rid of the annoyance of threshold setting and automatically complete the detection; for the lens gradient boundary, the detection result still cannot meet people's expectations, until now it faces two main problems: the first is how to accurately locate the gradient boundary; the second is how to accurately locate the gradient boundary. Identify the type of gradient boundary

Images