Method for shot boundary detection

Abstract

The invention discloses a method for shot boundary detection, comprising the following steps: A1, calculating a within-class discrete degree matrix S1 of a sample set V1 and a within-class discrete degree matrix S2 of a sample set V2, and calculating the total within-class discrete degree matrix Sw, wherein the Sw = S1 + S2; and then calculating the discrete degree matrix Sb between the classe V1and the classe V2, wherein the Sb=(m1-m2)(m1-m2)T; A2, establishing a shearing detection formula and carrying out shearing detection; and A3, establishing a gradually changed detection formula and carrying out gradually changed detection. Aiming at the prior algorithm, the shortages of the detection are gradually changed by using different characteristic quantity and different judging formulae after the shearing detection is performed; and in the invention, the gradually changed detection can be conveniently carried out just by using slightly modifying the Fisher judging formula in changing without using and calculating characteristic quantity nor without using a new judging formula when in gradually changed detection, therefore, the detection difficulty and complexity are reduced. Moreover, in lens shearing and gradually changed detection, a characteristic curve extremum method is used for replacing the traditional threshold value method, so that the defect of bad adaptability of the threshold value method is avoided.

Description

technical field [0001] The invention relates to the technical field of video content analysis, in particular to a shot boundary detection method. Background technique [0002] In video sequences, the boundaries of shots are divided into two categories: abrupt transition and gradual transition. A cut is when the change occurs suddenly between two consecutive frames, while a gradient is when the change occurs between multiple consecutive frames. Gradients are more complex and include fades, dissolves, and wipes. At present, researchers at home and abroad have proposed a variety of different shot boundary detection methods. The basic idea of ​​shot boundary detection is to find the rule of shot boundary change by comparing the difference between frames of video sequences. First extract the features of the video frame, these features must be able to better highlight the difference between the shot boundary and non-boundary; then use these feature quantities to construct the j...

AI Technical Summary

Problems solved by technology

[0004] At present, the lens cut has achieved good results. This is because there is no transition between the lenses during the cut, and the instant transition from one lens to another shows a very prominent non-similarity feature; while the lens gradient occurs In a period of time, the features of each frame are not obvious, and it is difficult to detect the lens gradient according to whether the feature value at a certain moment exceeds the threshold

[0005] In addition, in the lens boundary detection, there are still "noises" caused by flashes, object movement inside the lens, and the camera's own movement, which also brings interference to the existing methods.

Images