Librería Portfolio

Background modeling and foreground detection are important steps in video processing used to detect robustly moving objects in challenging environments. This requires effective methods for dealing with dynamic backgrounds and illumination changes as well as algorithms that must meet real-time and low memory requirements.

Incorporating both established and new ideas, Background Modeling and Foreground Detection for Video Surveillance provides a complete overview of the concepts, algorithms, and applications related to background modeling and foreground detection. Leaders in the field address a wide range of challenges, including camera jitter and background subtraction.

The book presents the top methods and algorithms for detecting moving objects in video surveillance. It covers statistical models, clustering models, neural networks, and fuzzy models. It also addresses sensors, hardware, and implementation issues and discusses the resources and datasets required for evaluating and comparing background subtraction algorithms. The datasets and codes used in the text, along with links to software demonstrations, are available on the book's website.

A one-stop resource on up-to-date models, algorithms, implementations, and benchmarking techniques, this book helps researchers and industry developers understand how to apply background models and foreground detection methods to video surveillance and related areas, such as optical motion capture, multimedia applications, teleconferencing, video editing, and human-computer interfaces. It can also be used in graduate courses on computer vision, image processing, real-time architecture, machine learning, or data mining.



Table of Contents
Introduction and Background
Traditional Approaches in Background Modeling for Static Cameras Thierry Bouwmans
Recent Approaches in Background Modeling for Static Cameras Thierry Bouwmans
Background Model Initialization for Static Cameras Lucia Maddalena and Alfredo Petrosino
Background Subtraction for Moving Cameras Ahmed Elgammal and Ali Elqursh

Traditional and Recent Models
Statistical Models for Background Subtraction Ahmed Elgammal
Non-Parametric Background Segmentation with Feedback and Dynamic Controllers Philipp Tiefenbacher, Martin Hofmann, and Gerhard Rigoll
ViBe: A Disruptive Method for Background Subtraction Marc Van Droogenbroeck and Olivier Barnich
Online Learning by Stochastic Approximation for Background Modeling Ezequiel López-Rubio and Rafael M. Luque-Baena
Sparsity-Driven Background Modeling and Foreground Detection Jun-zhou Huang, Chen Chen, and Xinyi Cui
Robust Detection of Moving Objects through Rough Set Theory Framework Pojala Chiranjeevi and Somnath Sengupta

Applications in Video Surveillance
Background Learning with Support Vectors: Efficient Foreground Detection and Tracking for Automated Visual Surveillance Alireza Tavakkoli, Mircea Nicolescu, Junxian Wang, and George Bebis
Incremental Learning of an Infinite Beta-Liouville Mixture Model for Video Background Subtraction Wentao Fan and Nizar Bouguila
Spatio-Temporal Background Models for Object Detection Satoshi Yoshinaga, Yosuke Nonaka, Atsushi Shimada, Hajime Nagahara, and Rin-ichiro Taniguchi
Background Modeling and Foreground Detection for Maritime Video Surveillance Domenico Bloisi
Hierarchical Scene Model for Spatial-color Mixture of Gaussians Christophe Gabard, Catherine Achard, and Laurent Lucat
Online Robust Background Modeling via Alternating Grassmannian Optimization Jun He, Laura Balzano, and Arthur Szlam

Sensors, Hardware, and Implementations
Ubiquitous Imaging (Light, Thermal, Range, Radar) Sensors for People Detection: An Overview Zoran Zivkovic
RGB-D Cameras for Background-Foreground Segmentation Massimo Camplani and Luis Salgado
Non-Parametric GPU Accelerated Background Modeling of Complex Scenes Ashutosh Morde and Sadiye Guler
GPU Implementation for Background-Foreground-Separation via Robust PCA and Robust Subspace Tracking Clemens Hage, Florian Seidel, and Martin Kleinsteuber
Background Subtraction on Embedded Hardware Enrique J. Fernandez-Sanchez, Rafael Rodriguez-Gomez, Javier Diaz, and Eduardo Ros
Resource-Efficient Salient Foreground Detection for Embedded Smart Cameras Senem Velipasalar and Mauricio Casares

Benchmarking and Evaluation
BGS Library: A Library Framework for Algorithms Evaluation in Foreground/Background Segmentation Andrews Sobral and Thierry Bouwmans
Overview and Benchmarking of Motion Detection Methods Pierre-Marc Jodoin, Sébastien Piérard, Yi Wang, and Marc Van Droogenbroeck
Evaluation of Background Models with Synthetic and Real Data Antoine Vacavant, Laure Tougne, Thierry Chateau, and Lionel Robinault

Index