Neural Network Approach to Background Modeling for Video Object Segmentation

Authors:
D. Culibrk;O. Marques;D. Socek;H. Kalva;B. Furht
Affiliations:
Florida Atlantic Univ., Boca Raton;-;-;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
2007

Citing 0
Cited 8

A Local Discriminative Model for Background Subtraction

Proceedings of the 30th DAGM symposium on Pattern Recognition
Multivalued Background/Foreground Separation for Moving Object Detection

WILF '09 Proceedings of the 8th International Workshop on Fuzzy Logic and Applications
Multiscale background modelling and segmentation

DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
Simplified SOM-neural model for video segmentation of moving objects

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
An experimental evaluation of foreground detection algorithms in real scenes

EURASIP Journal on Advances in Signal Processing - Special issue on video analysis for human behavior understanding
Background extraction using improved mode algorithm for visual surveillance applications

International Journal of Computational Science and Engineering
Background subtraction with dirichlet processes

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Scalable-Width Temporal Edge Detection for Recursive Background Recovery in adaptive background modeling

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel background modeling and subtraction approach for video object segmentation. A neural network (NN) architecture is proposed to form an unsupervised Bayesian classifier for this application domain. The constructed classifier efficiently handles the segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed NN serve as a model of the background and are temporally updated to reflect the observed statistics of background. The segmentation performance of the proposed NN is qualitatively and quantitatively examined and compared to two extant probabilistic object segmentation algorithms, based on a previously published test pool containing diverse surveillance-related sequences. The proposed algorithm is parallelized on a subpixel level and designed to enable efficient hardware implementation.