Group and Crowd Behavior for Computer Vision - 1st Edition - ISBN: 9780128092767, 9780128092804

Group and Crowd Behavior for Computer Vision

1st Edition

Authors: Vittorio Murino Marco Cristani Shishir Shah Silvio Savarese
eBook ISBN: 9780128092804
Hardcover ISBN: 9780128092767
Imprint: Academic Press
Published Date: 10th April 2017
Page Count: 438
Tax/VAT will be calculated at check-out
140.00
129.00
111.00
149.94
Unavailable
File Compatibility per Device

PDF, EPUB, VSB (Vital Source):
PC, Apple Mac, iPhone, iPad, Android mobile devices.

Mobi:
Amazon Kindle eReader.

Institutional Access

Secure Checkout

Personal information is secured with SSL technology.

Free Shipping

Free global shipping
No minimum order.

Description

Group and Crowd Behavior for Computer Vision provides a multidisciplinary perspective on how to solve the problem of group and crowd analysis and modeling, combining insights from the social sciences with technological ideas in computer vision and pattern recognition.

The book answers many unresolved issues in group and crowd behavior, with Part One providing an introduction to the problems of analyzing groups and crowds that stresses that they should not be considered as completely diverse entities, but as an aggregation of people.

Part Two focuses on features and representations with the aim of recognizing the presence of groups and crowds in image and video data. It discusses low level processing methods to individuate when and where a group or crowd is placed in the scene, spanning from the use of people detectors toward more ad-hoc strategies to individuate group and crowd formations.

Part Three discusses methods for analyzing the behavior of groups and the crowd once they have been detected, showing how to extract semantic information, predicting/tracking the movement of a group, the formation or disaggregation of a group/crowd and the identification of different kinds of groups/crowds depending on their behavior.

The final section focuses on identifying and promoting datasets for group/crowd analysis and modeling, presenting and discussing metrics for evaluating the pros and cons of the various models and methods. This book gives computer vision researcher techniques for segmentation and grouping, tracking and reasoning for solving group and crowd modeling and analysis, as well as more general problems in computer vision and machine learning.

Key Features

  • Presents the first book to cover the topic of modeling and analysis of groups in computer vision
  • Discusses the topics of group and crowd modeling from a cross-disciplinary perspective, using social science anthropological theories translated into computer vision algorithms
  • Focuses on group and crowd analysis metrics
  • Discusses real industrial systems dealing with the problem of analyzing groups and crowds

Readership

Computer scientists and electronic researchers in computer vision and pattern recognition; graduate students in these fields

Table of Contents

Chapter 1: The Group and Crowd Analysis Interdisciplinary Challenge

  • Abstract
  • 1.1. The Study of Groups and Crowds
  • 1.2. Scope of the Book
  • 1.3. Summary of Important Points
  • References

Part 1: Features and Representations

Chapter 2: Social Interaction in Temporary Gatherings

  • Abstract
  • 2.1. Introduction: Group and Crowd Behavior in Context
  • 2.2. Social Interaction: A Typology and Some Definitions
  • 2.3. Temporary Gatherings: A Taxonomy and Some Examples
  • 2.4. Conclusion: Microsociology Applied to Computer Vision
  • 2.5. Further Reading
  • References

Chapter 3: Group Detection and Tracking Using Sociological Features

  • Abstract
  • 3.1. Introduction
  • 3.2. State-of-the-Art
  • 3.3. Sociological Features
  • 3.4. Detection Models
  • 3.5. Group Tracking
  • 3.6. Experiments
  • 3.7. Discussion
  • 3.8. Conclusions
  • References

Chapter 4: Exploring Multitask and Transfer Learning Algorithms for Head Pose Estimation in Dynamic Multiview Scenarios

  • Abstract
  • 4.1. Introduction
  • 4.2. Related Work
  • 4.3. TL and MTL for Multiview Head Pose Estimation
  • 4.4. Conclusions
  • References

Chapter 5: The Analysis of High Density Crowds in Videos

  • Abstract
  • 5.1. Introduction
  • 5.2. Literature Review
  • 5.3. Data-Driven Crowd Analysis in Videos
  • 5.4. Density-Aware Person Detection and Tracking in Crowds
  • 5.5. CrowdNet: Learning a Representation for High Density Crowds in Videos
  • 5.6. Conclusions and Directions for Future Research
  • References

Chapter 6: Tracking Millions of Humans in Crowded Spaces

  • Abstract
  • 6.1. Introduction
  • 6.2. Related Work
  • 6.3. System Overview
  • 6.4. Human Detection in 3D
  • 6.5. Tracklet Generation
  • 6.6. Tracklet Association
  • 6.7. Experiments
  • 6.8. Conclusions
  • References

Chapter 7: Subject-Centric Group Feature for Person Reidentification

  • Abstract
  • Acknowledgments
  • 7.1. Introduction
  • 7.2. Related Works
  • 7.3. Methodology
  • 7.4. Results
  • 7.5. Conclusion
  • References

Part 2: Group and Crowd Behavior Modeling

Chapter 8: From Groups to Leaders and Back

  • Abstract
  • 8.1. Introduction
  • 8.2. Modeling and Observing Groups and Their Leaders in Literature
  • 8.3. Technical Preliminaries and Structured Output Prediction
  • 8.4. The Tools of the Trade in Social and Structured Crowd Analysis
  • 8.5. Results on Visual Localization of Groups and Leaders
  • 8.6. The Predictive Power of Leaders in Social Groups
  • 8.7. Conclusion
  • References

Chapter 9: Learning to Predict Human Behavior in Crowded Scenes

  • Abstract
  • 9.1. Introduction
  • 9.2. Related Work
  • 9.3. Forecasting with Social Forces Model
  • 9.4. Forecasting with Recurrent Neural Network
  • 9.5. Experiments
  • 9.6. Conclusions
  • References

Chapter 10: Deep Learning for Scene-Independent Crowd Analysis

  • Abstract
  • 10.1. Introduction
  • 10.2. Large Scale Crowd Datasets
  • 10.3. Crowd Counting and Density Estimation
  • 10.4. Attributes for Crowded Scene Understanding
  • 10.5. Conclusion
  • References

Chapter 11: Physics-Inspired Models for Detecting Abnormal Behaviors in Crowded Scenes

  • Abstract
  • 11.1. Introduction
  • 11.2. Crowd Anomaly Detection: A General Review
  • 11.3. Physics-Inspired Crowd Models
  • 11.4. Violence Detection
  • 11.5. Experimental Results
  • 11.6. Conclusions
  • References

Chapter 12: Activity Forecasting

  • Abstract
  • 12.1. Introduction
  • 12.2. Overview
  • 12.3. Activity Forecasting as Optimal Control
  • 12.4. Single Agent Trajectory Forecasting in Static Environment
  • 12.5. Multiagent Trajectory Forecasting
  • 12.6. Dual-Agent Interaction Forecasting
  • 12.7. Final Remarks
  • References

Part 3: Metrics, Benchmarks and Systems

Chapter 13: Integrating Computer Vision Algorithms and Ontologies for Spectator Crowd Behavior Analysis

  • Abstract
  • Acknowledgments
  • 13.1. Introduction
  • 13.2. Computer Vision and Ontology
  • 13.3. An Extension of the dolce Ontology for Spectator Crowd
  • 13.4. Reasoning on the Temporal Alignment of Stands and Playground
  • 13.5. Concluding Remarks
  • References

Chapter 14: SALSA: A Multimodal Dataset for the Automated Analysis of Free-Standing Social Interactions

  • Abstract
  • 14.1. Introduction
  • 14.2. Literature Review
  • 14.3. Spotting the Research Gap
  • 14.4. The SALSA Dataset
  • 14.5. Experiments on SALSA
  • 14.6. Conclusions and Future Work
  • References

Chapter 15: Zero-Shot Crowd Behavior Recognition

  • Abstract
  • 15.1. Introduction
  • 15.2. Related Work
  • 15.3. Methodology
  • 15.4. Experiments
  • 15.5. Further Analysis
  • 15.6. Conclusions
  • References

Chapter 16: The GRODE Metrics

  • Abstract
  • 16.1. Introduction
  • 16.2. Metrics in the Literature
  • 16.3. The GRODE Metrics
  • 16.4. Experiments
  • 16.5. Conclusions
  • References

Chapter 17: Realtime Pedestrian Tracking and Prediction in Dense Crowds

  • Abstract
  • Acknowledgments
  • 17.1. Introduction
  • 17.2. Related Work
  • 17.3. Pedestrian State
  • 17.4. Mixture Motion Model
  • 17.5. Realtime Pedestrian Path Prediction
  • 17.6. Implementation and Results
  • 17.7. Conclusion
  • References

Details

No. of pages:
438
Language:
English
Copyright:
© Academic Press 2017
Published:
Imprint:
Academic Press
eBook ISBN:
9780128092804
Hardcover ISBN:
9780128092767

About the Author

Vittorio Murino

Full professor at the University of Verona, Italy, and director of the PAVIS (Pattern Analysis and Computer Vision) department at the Istituto Italiano di Tecnologia. He took the Laurea degree in Electronic Engineering in 1989 and a Ph.D. in Electronic Engineering and Computer Science in 1993 at the University of Genova, Italy.

His main research interests include: computer vision and pattern recognition/machine learning, in particular, probabilistic techniques for image and video processing, with applications on video surveillance, biomedical image analysis and bioinformatics.

Affiliations and Expertise

Professor, University of Verona, Italy, and director, PAVIS (Pattern Analysis and Computer Vision), Istituto Italiano di Tecnologia

Marco Cristani

Associate Professor at the University of Verona, External Collaborator at the Istituto Italiano di Tecnologia, Genova, Italy and Associate Member at the National Research Council. After the Master Degree (with thesis developed partially at the Instituto Superior Tecnico, Lisboa under the supervision of Prof Mario Figueiredo), he took the PhD in Computer Science at the Department of Computer Science of the University of Verona in 2006. During the period 2004-2005 he has been Research Scholar at the University of Southern California, under the guidance of Prof. Ram Nevatia. He has been and is currently scientific collaborator of a number of national and European projects. His research interests include statistical pattern recognition, and especially generative modelling, applied to video surveillance, social signalling and multimedia in general.

Affiliations and Expertise

Associate Professor, University of Verona, External Collaborator, Istituto Italiano di Tecnologia, Genova, Italy and Associate Member, National Research Council

Shishir Shah

Studied Mechanical Engineering as an undergraduate at The University of Texas at Austin, where he received his B.S. degree in 1994. He received his M.S. and Ph.D. degrees in Electrical and Computer Engineering from The University of Texas at Austin for his thesis on Vision-based Mobile Robot Navigation and Probabilistic Feature Integration for Object Recognition, respectively.

His current research focuses on human behavior modeling and analysis, scene understanding, video analytics, biometrics, and microscopy image analysis. His long-term interests are centered on the broader area of knowledge driven intelligent systems capable of seamless incorporation of semantic information through statistical decision priors and data driven feedback, with the intent of developing ‘visual decision’ capabilities that would include cognitive functions for reasoning and learning.

Affiliations and Expertise

Professor of Computer Science, University of Houston, Houston, USA

Silvio Savarese

Assistant Professor of Computer Science at Stanford University. He earned his Ph.D. in Electrical Engineering from the California Institute of Technology in 2005 and was a Beckman Institute Fellow at the University of Illinois at Urbana-Champaign from 2005–2008. He joined Stanford in 2013 after being Assistant and then Associate Professor (with tenure) of Electrical and Computer Engineering at the University of Michigan, Ann Arbor, from 2008 to 2013. His research interests include computer vision, object recognition and scene understanding, shape representation and reconstruction, human activity recognition and visual psychophysics.

Affiliations and Expertise

Assistant Professor of Computer Science, Stanford University, Stanford, USA