Detection of Moving Objects Using Multi-channel Kernel Fuzzy Correlogram Based Background Subtraction

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 i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics Vol. 44; no. 6; pp. 870 - 881
Main Authors: Chiranjeevi, Pojala, Sengupta, Somnath
Format: Journal Article
Language:English
Published: United States IEEE 01.06.2014
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Background subtraction
Clustering algorithms
Color
Computational modeling
Current measurement
Fuzzy
fuzzy distance measure
Fuzzy logic
Fuzzy set theory
Image color analysis
inter-channel correlogram
Kernel
kernel fuzzy c-mean algorithm
Kernels
multi-channel correlogram
multi-channel kernel fuzzy correlogram
Planes
Subtraction
Vectors
multi-channel kernel fuzzy correlogram
fuzzy distance measure
Background subtraction
kernel fuzzy c-mean algorithm
multi-channel correlogram
inter-channel correlogram
ISSN:2168-2267, 2168-2275, 2168-2275
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2168-2267
2168-2275
2168-2275
DOI:10.1109/TCYB.2013.2274330