Academic Journals Database
Disseminating quality controlled scientific knowledge

Video Shot Boundary Detection based on Multifractal Analisys

Author(s): G. J. Zajić | I. S. Reljin | B. D. Reljin

Journal: Telfor Journal
ISSN 1821-3251

Volume: 3;
Issue: 2;
Start page: 105;
Date: 2011;
Original page

Keywords: Shot boundary detection | multifractal analysis | threshold | feature vectors

Extracting video shots is an essential preprocessing step to almost all video analysis, indexing, and other content-based operations. This process is equivalent to detecting the shot boundaries in a video. In this paper we presents video Shot Boundary Detection (SBD) based on Multifractal Analysis (MA). Low-level features (color and texture features) are extracted from each frame in video sequence. Features are concatenated in feature vectors (FVs) and stored in feature matrix. Matrix rows correspond to FVs of frames from video sequence, while columns are time series of particular FV component. Multifractal analysis is applied to FV component time series, and shot boundaries are detected as high singularities of time series above pre defined treshold. Proposed SBD method is tested on real video sequence with 64 shots, with manually labeled shot boundaries. Detection accuracy depends on number FV components used. For only one FV component detection accuracy lies in the range 76-92% (depending on selected threshold), while by combining two FV components all shots are detected completely (accuracy of 100%).
RPA Switzerland

Robotic Process Automation Switzerland


Tango Rapperswil
Tango Rapperswil