Biologically inspired computer vision : fundamentals and applications / edited by Gabriel Cristobal, Laurent Perrinet and Matthias S. Keil ; contributors Alexandre Alahi [and thirty two others].

Format:

Book

Contributor:

Cristóbal, Gabriel, editor.

Perrinet, Laurent, editor.

Keil, Matthias S., editor.

Alahi, Alexandre, contributor.

Language:

English

Subjects (All):

Computer vision.

Natural computation.

Physical Description:

1 online resource (565 p.)

Edition:

1st ed.

Place of Publication:

Weinheim, Germany : Wiley-VCH Verlag GmbH & Co. KGaA, 2016.

Language Note:

English

Summary:

As the state-of-the-art imaging technologies became more and more advanced, yielding scientific data at unprecedented detail and volume, the need to process and interpret all the data has made image processing and computer vision increasingly important. Sources of data that have to be routinely dealt with today's applications include video transmission, wireless communication, automatic fingerprint processing, massive databanks, non-weary and accurate automatic airport screening, robust night vision, just to name a few. Multidisciplinary inputs from other disciplines such as physics, computational neuroscience, cognitive science, mathematics, and biology will have a fundamental impact in the progress of imaging and vision sciences. One of the advantages of the study of biological organisms is to devise very different type of computational paradigms by implementing a neural network with a high degree of local connectivity. This is a comprehensive and rigorous reference in the area of biologically motivated vision sensors. The study of biologically visual systems can be considered as a two way avenue. On the one hand, biological organisms can provide a source of inspiration for new computational efficient and robust vision models and on the other hand machine vision approaches can provide new insights for understanding biological visual systems. Along the different chapters, this book covers a wide range of topics from fundamental to more specialized topics, including visual analysis based on a computational level, hardware implementation, and the design of new more advanced vision sensors. The last two sections of the book provide an overview of a few representative applications and current state of the art of the research in this area. This makes it a valuable book for graduate, Master, PhD students and also researchers in the field.

Contents:

Intro

Related Titles

Title Page

Copyright

Table of Contents

List of Contributors

Foreword

Part I: Fundamentals

Chapter 1: Introduction

1.1 Why Should We Be Inspired by Biology?

1.2 Organization of Chapters in the Book

1.3 Conclusion

Acknowledgments

References

Chapter 2: Bioinspired Vision Sensing

2.1 Introduction

2.2 Fundamentals and Motivation: Bioinspired Artificial Vision

2.3 From Biological Models to Practical Vision Devices

2.4 Conclusions and Outlook

Chapter 3: Retinal Processing: From Biology to Models and Applications

3.1 Introduction

3.2 Anatomy and Physiology of the Retina

3.3 Models of Vision

3.4 Application to Digital Photography

3.5 Conclusion

Chapter 4: Modeling Natural Image Statistics

4.1 Introduction

4.2 Why Model Natural Images?

4.3 Natural Image Models

4.4 Computer Vision Applications

4.5 Biological Adaptations to Natural Images

4.6 Conclusions

Chapter 5: Perceptual Psychophysics

5.1 Introduction

5.2 Laboratory Methods

5.3 Psychophysical Threshold Measurement

5.4 Classic Psychophysics: Theory and Methods

5.5 Signal Detection Theory

5.6 Psychophysical Scaling Methods

5.7 Conclusions

Part II: Sensing

Chapter 6: Bioinspired Optical Imaging

6.1 Visual Perception

6.2 Polarization Vision - Object Differentiation/Recognition

6.3 High-Speed Motion Detection

6.4 Conclusion

Chapter 7: Biomimetic Vision Systems

7.1 Introduction

7.2 Scaling Laws in Optics

7.3 The Evolution of Vision Systems

7.4 Manufacturing of Optics for Miniaturized Vision Systems

7.5 Examples for Biomimetic Compound Vision Systems

Chapter 8: Plenoptic Cameras

8.1 Introduction.

8.2 Light Field Representation of the Plenoptic Function

8.3 The Plenoptic Camera

8.4 Applications of the Plenoptic Camera

8.5 Generalizations of the Plenoptic Camera

8.6 High-Performance Computing with Plenoptic Cameras

8.7 Conclusions

Part III: Modelling

Chapter 9: Probabilistic Inference and Bayesian Priors in Visual Perception

9.1 Introduction

9.2 Perception as Bayesian Inference

9.3 Perceptual Priors

9.4 Outstanding Questions

Chapter 10: From Neuronal Models to Neuronal Dynamics and Image Processing

10.1 Introduction

10.2 The Membrane Equation as a Neuron Model

10.3 Application 1: A Dynamical Retinal Model

10.4 Application 2: Texture Segregation

10.5 Application 3: Detection of Collision Threats

10.6 Conclusions

Chapter 11: Computational Models of Visual Attention and Applications

11.1 Introduction

11.2 Models of Visual Attention

11.3 A Closer Look at Cognitive Models

11.4 Applications

11.5 Conclusion

Chapter 12: Visual Motion Processing and Human Tracking Behavior

12.1 Introduction

12.2 Pursuit Initiation: Facing Uncertainties

12.3 Predicting Future and On-Going Target Motion

12.4 Dynamic Integration of Retinal and Extra-Retinal Motion Information: Computational Models

12.5 Reacting, Inferring, Predicting: A Neural Workspace

12.6 Conclusion

Chapter 13: Cortical Networks of Visual Recognition

13.1 Introduction

13.2 Global Organization of the Visual Cortex

13.3 Local Operations: Receptive Fields

13.4 Local Operations in V1

13.5 Multilayer Models

13.6 A Basic Introductory Model

13.7 Idealized Mathematical Model of V1: Fiber Bundle

13.8 Horizontal Connections and the Association Field.

13.9 Feedback and Attentional Mechanisms

13.10 Temporal Considerations, Transformations and Invariance

13.11 Conclusion

Chapter 14: Sparse Models for Computer Vision

14.1 Motivation

14.2 What Is Sparseness? Application to Image Patches

14.3 SparseLets: A Multiscale, Sparse, Biologically Inspired Representation of Natural Images

14.4 SparseEdges: Introducing Prior Information

14.5 Conclusion

Chapter 15: Biologically Inspired Keypoints

15.1 Introduction

15.2 Definitions

15.3 What Does the Frond-End of the Visual System Tell Us?

15.4 Bioplausible Keypoint Extraction

15.5 Biologically Inspired Keypoint Representation

15.6 Qualitative Analysis: Visualizing Keypoint Information

15.7 Conclusions

Part IV: Applications

Chapter 16: Nightvision Based on a Biological Model

16.1 Introduction

16.2 Why Is Vision Difficult in Dim Light?

16.3 Why Is Digital Imaging Difficult in Dim Light?

16.4 Solving the Problem of Imaging in Dim Light

16.5 Implementation and Evaluation of the Night-Vision Algorithm

16.6 Conclusions

Acknowledgment

Chapter 17: Bioinspired Motion Detection Based on an FPGA Platform

17.1 Introduction

17.2 A Motion Detection Module for Robotics and Biology

17.3 Insect Motion Detection Models

17.4 Overview of Robotic Implementations of Bioinspired Motion Detection

17.5 An FPGA-Based Implementation

17.6 Experimental Results

17.7 Discussion

17.8 Conclusion

Chapter 18: Visual Navigation in a Cluttered World

18.1 Introduction

18.2 Cues from Optic Flow: Visually Guided Navigation

18.3 Estimation of Self-Motion: Knowing Where You Are Going

18.4 Object Detection: Understanding What Is in Your Way.

18.5 Estimation of TTC: Time Constraints from the Expansion Rate

18.6 Steering Control: The Importance of Representation

18.7 Conclusions

Index

End User License Agreement.

Notes:

Description based upon print version of record.

Includes bibliographical references at the end of each chapters and index.

Description based on online resource; title from PDF title page (ebrary, viewed November 5, 2015).

ISBN:

9783527680474

3527680470

9783527680498

3527680497

9783527680863

3527680861

OCLC:

923139008