Robust Target Localization and Segmentation

Omar Arif

ISBN 10: 3843350388 / ISBN 13: 9783843350389

Published by LAP LAMBERT Academic Publishing Sep 2010, 2010

About this Item

This item is printed on demand - Print on Demand Titel. Neuware -This work aims to contribute to the area of visual tracking, which is the process of identifying an object of interest through a sequence of successive images. The thesis explores kernel-based statistical methods. Two algorithms are developed for visual tracking that are robust to noise and occlusions. In the first algorithm, a kernel PCA-based eigenspace representation is used. The de-noising and clustering capabilities of the kernel PCA procedure lead to a robust algorithm. In the second method, a robust density comparison framework is developed that is applied to visual tracking, where an object is tracked by minimizing the distance between a model distribution and given candidate distributions. The superior performance of kernel-based algorithms comes at a price of increased storage and computational requirements. A novel method is developed that takes advantage of the universal approximation capabilities of generalized radial basis function neural networks to reduce the computational and storage requirements for kernel-based methods.VDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 116 pp. Englisch.

Seller Inventory # 9783843350389

Bibliographic Details

• Title: Robust Target Localization and Segmentation
• Publisher: LAP LAMBERT Academic Publishing Sep 2010
• Publication Date: 2010
• Language: English
• ISBN 10: 3843350388
• ISBN 13: 9783843350389
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 220W x 150H x 8D millimeters 220 millimeters width by 150 millimeters height by 8 millimeters depth
• Weight: 191 grams

About this title

Synopsis

This work aims to contribute to the area of visual tracking, which is the process of identifying an object of interest through a sequence of successive images. The thesis explores kernel-based statistical methods. Two algorithms are developed for visual tracking that are robust to noise and occlusions. In the first algorithm, a kernel PCA-based eigenspace representation is used. The de-noising and clustering capabilities of the kernel PCA procedure lead to a robust algorithm. In the second method, a robust density comparison framework is developed that is applied to visual tracking, where an object is tracked by minimizing the distance between a model distribution and given candidate distributions. The superior performance of kernel-based algorithms comes at a price of increased storage and computational requirements. A novel method is developed that takes advantage of the universal approximation capabilities of generalized radial basis function neural networks to reduce the computational and storage requirements for kernel-based methods.

About the Author

Omar Arif carries out research in the areas of computer vision, machine learning and image processing. He completed his BE in computer engineering from National University of Sciences and Tech, Pakistan and MS and PHD in electrical engineering from Georgia Tech, USA.