Author Type

Graduate Student

Date of Award

2006

Document Type

Thesis

Publication Status

Version of Record

Submission Date

October 2026

Thesis/Dissertation Advisor [Chair]

Furht, Borko

Thesis/Dissertation Co-Chair

Marques, Oge

Abstract

Object segmentation in a video sequence is an essential task in video processing and forms the foundation of content analysis, scene understanding, object-based video encoding (e.g. MPEG-4), various surveillance and 2D-to-pseudo-3D conversion applications. Popularization and availability of video sequences with increased spatial resolution requires development of new, more efficient algorithms for object detection and segmentation. This dissertation discusses a novel neural-network-based approach to background modeling for motion-based object segmentation in video sequences. In particular, we show how Probabilistic Neural Network (PNN) architecture can be extended to form an unsupervised Bayesian classifier for the domain of video object segmentation. The constructed Background Modeling Neural Network (BNN) is capable of efficiently handling segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed neural network serve as an exclusive model of the background and are temporally updated to reflect the observed background statistics. The proposed approach is designed to enable an efficient, highly-parallelized hardware implementation. Such a system would be able to achieve real-time segmentation of high-resolution image sequences.

Extent

136 p.

Comments

College of Engineering and Computer Science|FAU Electronic Theses and Dissertations Collection|Thesis (Ph.D.)--Florida Atlantic University, 2006.|College of Engineering and Computer Science

Identifier

FADT12214

Format

pdf

Download

Share

COinS