Presents a unified collection of state-of-the-art solutions to fundamental problems in computer vision
Examines a fast-growing topic of considerable interest to a broad audience
Contains contributions from an international selection of experts in the field
Dr. Shaogang Gong is a Professor of Visual Computation in the School of Electronic Engineering and Computer Science at Queen Mary University of London, UK. His publications include the successful Springer books
Visual Analysis of Behaviour and
Video Analytics for Business Intelligence.
Dr. Marco Cristani is an Assistant Professor in the Computer Science Department at the University of Verona, Italy.
Dr. Shuicheng Yan is an Associate Professor in the Department of Electrical and Computer Engineering at the National University of Singapore.
Dr. Chen Change Loy is a Research Assistant Professor in the Department of Information Engineering at the Chinese University of Hong Kong.
The first book of its kind dedicated to the challenge of person re-identification, this text provides an in-depth, multidisciplinary discussion of recent developments and state-of-the-art methods. Features: introduces examples of robust feature representations, reviews salient feature weighting and selection mechanisms and examines the benefits of semantic attributes; describes how to segregate meaningful body parts from background clutter; examines the use of 3D depth images and contextual constraints derived from the visual appearance of a group; reviews approaches to feature transfer function and distance metric learning and discusses potential solutions to issues of data scalability and identity inference; investigates the limitations of existing benchmark datasets, presents strategies for camera topology inference and describes techniques for improving post-rank search efficiency; explores the design rationale and implementation considerations of building a practical re-identification system.|
Re-identification offers a useful tool for non-invasive biometric validation, surveillance, and human-robot interaction in a broad range of applications from crowd traffic management to personalised healthcare.
This comprehensive volume is the first work of its kind dedicated to addressing the challenge of Person Re-Identification, presenting insights from an international selection of leading authorities in the field. Taking a strongly multidisciplinary approach, the text provides an in-depth discussion of recent developments and state-of-the-art methods drawn from the computer vision, pattern recognition and machine learning communities, embracing both fundamental research and practical applications.
Topics and features: introduces examples of robust feature representations, reviews salient feature weighting and selection mechanisms, and examines the benefits of semantic attributes; describes how to segregate meaningful body parts from background clutter; examines the use of 3D depth images, and contextual constraints derived from the visual appearance of a group; reviews approaches to feature transfer function and distance metric learning, and discusses potential solutions to issues of data scalability and identity inference; investigates the limitations of existing benchmark datasets, presents strategies for camera topology inference, and describes techniques for improving post-rank search efficiency; explores the design rationale and implementation considerations of building a practical re-identification system.
This timely collection will be of great interest to academics, industrial researchers and postgraduates involved in computer vision and machine learning, database image retrieval, big data mining, and search engines, as well as to developers keen to exploit this emerging technology for commercial applications.
The Re-Identification Challenge
Shaogang Gong, Marco Cristani, Chen Change Loy, and Timothy M. Hospedales
Part I: Features and Representations
Discriminative Image Deillegalscriptors for Person Re-Identification
Bingpeng Ma, Yu Su, and Frédéric Jurie
SDALF: Modeling Human Appearance with Symmetry-Driven Accumulation of Local Features
Loris Bazzani, Marco Cristani, and Vittorio Murino
Re-Identification by Covariance Deillegalscriptors
Slawomir Bak and François Brémond
Attributes-Based Re-Identification
Ryan Layne, Timothy M. Hospedales, and Shaogang Gong
Person Re-Identification by Attribute-Assisted Clothes Appearance
Annan Li, Luoqi Liu, and Shuicheng Yan
Person Re-Identification by Articulated Appearance Matching
Dong Seon Cheng and Marco Cristani
One-Shot Person Re-Identification with a Consumer Depth Camera
Matteo Munaro, Andrea Fossati, Alberto Basso, Emanuele Menegatti, and Luc Van Gool
Group Association: Assisting Re-Identification by Visual Context
Wei-Shi Zheng, Shaogang Gong, and Tao Xiang
Evaluating Feature Importance for Re-Identification
Chunxiao Liu, Shaogang Gong, Chen Change Loy, and Xinggang Lin
Part II: Matching and Distance Metric
Learning Appearance Transfer for Person Re-Identification
Tamar Avraham and Michael Lindenbaum
Mahalanobis Distance Learning for Person Re-Identification
Peter M. Roth, Martin Hirzer, Martin Köstinger, Csaba Beleznai, and Horst Bischof
Dictionary-Based Domain Adaptation Methods for the Re-Identification of Faces
Qiang Qiu, Jie Ni, and Rama Chellappa
From Re-Identification to Identity Inference: Labelling Consistency by Local Similarity Constraints
Svebor Karaman, Giuseppe Lisanti, Andrew D. Bagdanov, and Alberto Del Bimbo
Re-Identification for Improved People Tracking
François Fleuret, Horesh Ben Shitrit, and Pascal Fua
Part III: Evaluation and Application
Benchmarking for Person Re-Identification
Roberto Vezzani and Rita Cucchiara
Person Re-Identification: System Design and Evaluation Overview
Xiaogang Wang and Rui Zhao
People Search with Textual Queries about Clothing Appearance Attributes
Riccardo Satta, Federico Pala, Giorgio Fumera, and Fabio Roli
Large Scale Camera Topology Mapping: Application to Re-Identification
Anthony Dick, Anton van den Hengel, and Henry Detmold
Scalable Multi-Camera Tracking in a Metropolis
Yogesh Raja and Shaogang Gong
Re-identification offers a useful tool for non-invasive biometric validation, surveillance, and human-robot interaction in a broad range of applications from crowd traffic management to personalised healthcare.
This comprehensive volume is the first work of its kind dedicated to addressing the challenge of Person Re-Identification, presenting insights from an international selection of leading authorities in the field. Taking a strongly multidisciplinary approach, the text provides an in-depth discussion of recent developments and state-of-the-art methods drawn from the computer vision, pattern recognition and machine learning communities, embracing both fundamental research and practical applications.
Topics and features:
- Introduces examples of robust feature representations, reviews salient feature weighting and selection mechanisms, and examines the benefits of semantic attributes
- Describes how to segregate meaningful body parts from background clutter
- Examines the use of 3D depth images, and contextual constraints derived from the visual appearance of a group
- Reviews approaches to feature transfer function and distance metric learning, and discusses potential solutions to issues of data scalability and identity inference
- Investigates the limitations of existing benchmark datasets, presents strategies for camera topology inference, and describes techniques for improving post-rank search efficiency
- Explores the design rationale and implementation considerations of building a practical re-identification system
This timely collection will be of great interest to academics, industrial researchers and postgraduates involved in computer vision and machine learning, database image retrieval, big data mining, and search engines, as well as to developers keen to exploit this emerging technology for commercial applications.
The book is intended for researchers that work, or want to start working on this research topic. ... The book is very interesting and allows having an insight into the problem of person re-identification and its potential applications. It provides a presentation of the current state-of-the-are and recent progress on this topic. I think that researchers who intend to work on re-identification can benefit from reading this book. They will be introduced to the many interesting challenges to be faced.” (Donatello Conte, IAPR Newsletter, Vol. 37 (2), 2015)
The Re-Identification Challenge.- Part I: Features and Representations.- Discriminative Image Deillegalscriptors for Person Re-Identification.- SDALF.- Re-Identification by Covariance Deillegalscriptors.- Attributes-Based Re-Identification.- Person Re-Identification by Attribute-Assisted Clothes Appearance.- Person Re-Identification by Articulated Appearance Matching.- One-Shot Person Re-Identification with a Consumer Depth Camera.- Group Association.- Evaluating Feature Importance for Re-Identification.- Part II: Matching and Distance Metric.- Learning Appearance Transfer for Person Re-Identification.- Mahalanobis Distance Learning for Person Re-Identification.- Dictionary-Based Domain Adaptation Methods for the Re-Identification of Faces.- From Re-Identification to Identity Inference.- Re-Identification for Improved People Tracking.- Part III: Evaluation and Application.- Benchmarking for Person Re-Identification.- Person Re-Identification.- People Search with Textual Queries about Clothing Appearance Attributes.- Large Scale Camera Topology Mapping.- Scalable Multi-Camera Tracking in a Metropolis.
The book is intended for researchers that work, or want to start working on this research topic. ... The book is very interesting and allows having an insight into the problem of person re-identification and its potential applications. It provides a presentation of the current state-of-the-are and recent progress on this topic. I think that researchers who intend to work on re-identification can benefit from reading this book. They will be introduced to the many interesting challenges to be faced." (Donatello Conte, IAPR Newsletter, Vol. 37 (2), 2015)
Über den Autor
Dr. Shaogang Gong is a Professor of Visual Computation in the School of Electronic Engineering and Computer Science at Queen Mary University of London, UK. His publications include the successful Springer books Visual Analysis of Behaviour and Video Analytics for Business Intelligence. Dr. Marco Cristani is an Assistant Professor in the Computer Science Department at the University of Verona, Italy. Dr. Shuicheng Yan is an Associate Professor in the Department of Electrical and Computer Engineering at the National University of Singapore. Dr. Chen Change Loy is a Research Assistant Professor in the Department of Information Engineering at the Chinese University of Hong Kong.
Inhaltsverzeichnis
The Re-Identification Challenge
Shaogang Gong, Marco Cristani, Chen Change Loy, and Timothy M. Hospedales
Part I: Features and Representations
Discriminative Image Deillegalscriptors for Person Re-Identification
Bingpeng Ma, Yu Su, and Frédéric Jurie
SDALF: Modeling Human Appearance with Symmetry-Driven Accumulation of Local Features
Loris Bazzani, Marco Cristani, and Vittorio Murino
Re-Identification by Covariance Deillegalscriptors
Slawomir Bak and François Brémond
Attributes-Based Re-Identification
Ryan Layne, Timothy M. Hospedales, and Shaogang Gong
Person Re-Identification by Attribute-Assisted Clothes Appearance
Annan Li, Luoqi Liu, and Shuicheng Yan
Person Re-Identification by Articulated Appearance Matching
Dong Seon Cheng and Marco Cristani
One-Shot Person Re-Identification with a Consumer Depth Camera
Matteo Munaro, Andrea Fossati, Alberto Basso, Emanuele Menegatti, and Luc Van Gool
Group Association: Assisting Re-Identification by Visual Context
Wei-Shi Zheng, Shaogang Gong, and Tao Xiang
Evaluating Feature Importance for Re-Identification
Chunxiao Liu, Shaogang Gong, Chen Change Loy, and Xinggang Lin
Part II: Matching and Distance Metric
Learning Appearance Transfer for Person Re-Identification
Tamar Avraham and Michael Lindenbaum
Mahalanobis Distance Learning for Person Re-Identification
Peter M. Roth, Martin Hirzer, Martin Köstinger, Csaba Beleznai, and Horst Bischof
Dictionary-Based Domain Adaptation Methods for the Re-Identification of Faces
Qiang Qiu, Jie Ni, and Rama Chellappa
From Re-Identification to Identity Inference: Labelling Consistency by Local Similarity Constraints
Svebor Karaman, Giuseppe Lisanti, Andrew D. Bagdanov, and Alberto Del Bimbo
Re-Identification for Improved People Tracking
François Fleuret, Horesh Ben Shitrit, and Pascal Fua
Part III: Evaluation and Application
Benchmarking for Person Re-Identification
Roberto Vezzani and Rita Cucchiara
Person Re-Identification: System Design and Evaluation Overview
Xiaogang Wang and Rui Zhao
People Search with Textual Queries about Clothing Appearance Attributes
Riccardo Satta, Federico Pala, Giorgio Fumera, and Fabio Roli
Large Scale Camera Topology Mapping: Application to Re-Identification
Anthony Dick, Anton van den Hengel, and Henry Detmold
Scalable Multi-Camera Tracking in a Metropolis
Yogesh Raja and Shaogang Gong
Klappentext
The first book of its kind dedicated to the challenge of person re-identification, this text provides an in-depth, multidisciplinary discussion of recent developments and state-of-the-art methods. Features: introduces examples of robust feature representations, reviews salient feature weighting and selection mechanisms and examines the benefits of semantic attributes; describes how to segregate meaningful body parts from background clutter; examines the use of 3D depth images and contextual constraints derived from the visual appearance of a group; reviews approaches to feature transfer function and distance metric learning and discusses potential solutions to issues of data scalability and identity inference; investigates the limitations of existing benchmark datasets, presents strategies for camera topology inference and describes techniques for improving post-rank search efficiency; explores the design rationale and implementation considerations of building a practical re-identification system.
Presents a unified collection of state-of-the-art solutions to fundamental problems in computer vision
rn
Examines a fast-growing topic of considerable interest to a broad audience
rn
Contains contributions from an international selection of experts in the field
rn
