Shaogang Gong - Böcker

This book presents a comprehensive treatment of visual analysis of behaviour from computational-modelling and algorithm-design perspectives. Topics: covers learning-group activity models, unsupervised behaviour profiling, hierarchical behaviour discovery, learning behavioural context, modelling rare behaviours, and “man-in-the-loop” active learning; examines multi-camera behaviour correlation, person re-identification, and “connecting-the-dots” for abnormal behaviour detection; discusses Bayesian information criterion, Bayesian networks, “bag-of-words” representation, canonical correlation analysis, dynamic Bayesian networks, Gaussian mixtures, and Gibbs sampling; investigates hidden conditional random fields, hidden Markov models, human silhouette shapes, latent Dirichlet allocation, local binary patterns, locality preserving projection, and Markov processes; explores probabilistic graphical models, probabilistic topic models, space-time interest points, spectral clustering, and support vector machines.

This book presents a comprehensive treatment of visual analysis of behaviour from computational-modelling and algorithm-design perspectives. Topics: covers learning-group activity models, unsupervised behaviour profiling, hierarchical behaviour discovery, learning behavioural context, modelling rare behaviours, and “man-in-the-loop” active learning; examines multi-camera behaviour correlation, person re-identification, and “connecting-the-dots” for abnormal behaviour detection; discusses Bayesian information criterion, Bayesian networks, “bag-of-words” representation, canonical correlation analysis, dynamic Bayesian networks, Gaussian mixtures, and Gibbs sampling; investigates hidden conditional random fields, hidden Markov models, human silhouette shapes, latent Dirichlet allocation, local binary patterns, locality preserving projection, and Markov processes; explores probabilistic graphical models, probabilistic topic models, space-time interest points, spectral clustering, and support vector machines.

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.

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.

Face recognition is a task that the human vision system seems to perform almost effortlessly, yet the goal of building computer-based systems with comparable capabilities has proven to be difficult. The task implicitly requires the ability to locate and track faces through often complex and dynamic scenes. Recognition is difficult because of variations in factors such as lighting conditions, viewpoint, body movement and facial expression. Although evidence from psychophysical and neurobiological experiments provides intriguing insights into how we might code and recognise faces, its bearings on computational and engineering solutions are far from clear. The study of face recognition has had an almost unique impact on computer vision and machine learning research at large. It raises many challenging issues and provides a good vehicle for examining some difficult problems in vision and learning. Many of the issues raised are relevant to object recognition in general.This book describes the latest models and algorithms that are capable of performing face recognition in a dynamic setting. The key question is how to design computer vision and machine learning algorithms that can operate robustly and quickly under poorly controlled and changing conditions. Consideration of face recognition as a problem in dynamic vision is perhaps both novel and important. The algorithms described have numerous potential applications in areas such as visual surveillance, verification, access control, video-conferencing, multimedia and visually mediated interaction.The book will be of special interest to researchers and academics involved in machine vision, visual recognition and machine learning. It should also be of interest to industrial research scientists and managers keen to exploit this emerging technology and develop automated face and human recognition systems. It is also useful to postgraduate students studying computer science, electronic engineering, information or systems engineering, and cognitive psychology.

During the last 30 years, face recognition and related problems such as face detection/tracking and facial expression recognition have attracted researchers from both the engineering and psychology communities. In addition, extensive research has been carried out to study hand and body gestures. The understanding of how humans perceive these important cues has significant scientific value and extensive applications. For example, human-computer interaction, visual surveillance, and smart video indexing are active application areas. Aiming towards putting such amazing perception capability onto computer systems, researchers have made substantial progress. However, technological challenges still exist in many aspects. Following a format similar to the IEEE International Workshop on Analysis and Modeling of Faces and Gestures (AMFG) 2003, this one-day workshop (AMFG 2005) provided a focused international forum to bring together well-known researchers and research groups to review the status of recognition, analysis and modeling of faces and gestures, to discuss the challenges that we are facing, and to explore future directions. Overall, 30 papers were selected from 90 submitted manuscripts. The topics of these papers range from feature representation, robust recognition, learning, and 3D modeling to psychology. In addition, two invited talks were given, by Prof. Kanade and Dr. Phillips. The technical program was organized into four oral sessions and two poster sessions. This workshop would not have been possible without the timely reviews provided by the members of the Technical Program Committee under a tight schedule. October 2005 Wenyi Zhao Shaogang Gong Xiaoou Tang

The 2007 IEEE International Workshop on Analysis and Modeling of Faces and Gestures(AMFG)isthethirdworkshopofitstypeorganizedinconjunctionwith ICCV, this time in Rio de Janeiro, Brazil. Our primary goal is to bring together researchersand research groupsto review the status of recognition, analysis and modeling of face, gesture, activity, and behavior; to discuss the challenges that we are facing; and to explore future directions. This year we received 55 submissions. Each paper was reviewed by three program committee members. The whole reviewing process was double blind. However,due to size limit, we were only able to accommodate 22 papers, among which 8 are orals and 14 are posters. The topics covered by these accepted papers include feature representation, 3D face, robust recognition under pose and illumination variations,video-basedface recognition,learning,facial motion analysis, body pose estimation, and sign recognition. A special word of thanks goes to Dr. Feng Zhao, our organizing chair, for his dedication and great e?orts in maintaining both the online submission system and workshop website and in handling most of the author contacts. We are indebted to the advisory committee members for their valuable suggestions and to the program committee members for their hard work and timely reviews. Finally, we thank Cognitec System GmbH and Siemens Corporate Research for their sponsorship. October 2007 S. Kevin Zhou Wen-Yi Zhao Xiaoou Tang Shaogang Gong Organization AMFG 2007 was held in conjunction with ICCV 2007. Workshop Chairs S. Kevin Zhou Siemens Corporate Research Wen-Yi Zhao Intuitive Surgical, Inc.

Closed Circuit TeleVision (CCTV) cameras have been increasingly deployed pervasively in public spaces including retail centres and shopping malls. Intelligent video analytics aims to automatically analyze content of massive amount of public space video data and has been one of the most active areas of computer vision research in the last two decades. Current focus of video analytics research has been largely on detecting alarm events and abnormal behaviours for public safety and security applications. However, increasingly CCTV installations have also been exploited for gathering and analyzing business intelligence information, in order to enhance marketing and operational efficiency. For example, in retail environments, surveillance cameras can be utilised to collect statistical information about shopping behaviour and preference for marketing (e.g., how many people entered a shop; how many females/males or which age groups of people showed interests to a particular product; how long did they stay in the shop; and what are the frequent paths), and to measure operational efficiency for improving customer experience. Video analytics has the enormous potential for non-security oriented commercial applications. This book presents the latest developments on video analytics for business intelligence applications. It provides both academic and commercial practitioners an understanding of the state-of-the-art and a resource for potential applications and successful practice.