Detection of Moving Objects Using Multi-channel Kernel Fuzzy Correlogram Based Background Subtraction
Authors:
- 1 October 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 44 (6) , 870-881
Abstract
In this paper, we examine the suitability of correlogram for background subtraction, as a step towards moving object detection. Correlogram captures inter-pixel relationships in a region and is seen to be effective for modeling the dynamic backgrounds. A multi-channel correlogram is proposed using inter-channel and intra-channel correlograms to exploit full color information and the inter-pixel relations on the same color planes and across the planes. We thereafter derive a novel feature, termed multi-channel kernel fuzzy correlogram, composed by applying a fuzzy membership transformation over multi-channel correlogram. Multi-channel kernel fuzzy correlogram maps multi-channel correlogram into a reduced dimensionality space and is less sensitivity to noise. The approach handles multimodal distributions without using multiple models per pixel unlike traditional approaches. The approach does not require ideal background frames for background model initialization and can be initialized with moving objects also. Effectiveness of the proposed method is illustrated on different video sequences.Keywords
This publication has 25 references indexed in Scilit:
- Robust detection of moving objects in video sequences through rough set theory frameworkImage and Vision Computing, 2012
- Spatially correlated background subtraction, based on adaptive background maintenanceJournal of Visual Communication and Image Representation, 2012
- Stochastic approximation for background modellingComputer Vision and Image Understanding, 2011
- Background Subtraction Based on Local Orientation Histogram2008
- A Self-Organizing Approach to Background Subtraction for Visual Surveillance ApplicationsIEEE Transactions on Image Processing, 2008
- A texture-based method for modeling the background and detecting moving objectsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Statistical Modeling of Complex Backgrounds for Foreground Object DetectionIEEE Transactions on Image Processing, 2004
- Using histograms to detect and track objects in color video2002
- Generalized fuzzy indices for similarity matchingFuzzy Sets and Systems, 2001
- Features of similarity.Psychological Review, 1977