Computational Vision in Neural and Machine

Computational vision deals with the underlying mathematical and computational models for how visual information is processed. In this volume the editors have brought together the best and brightest minds to review the latest developments in the field. Combining research from both biology and computing, each chapter serves to enhance the developing synergy between computational and biological visual modelling communities. Whether the processing is biological or machine, there are fundamental questions related to how the information is processed. How should information be represented? How should information be transduced in order to highlight features of interest while suppressing noise and other artefacts of the image capture process? Chapters addresses these and other questions, divided into three sections that overlap between biological and computational systems: dynamical systems; attention, motion and eye-movements; and stereovision. Aimed at researchers and graduate students in computational or biological vision, neuroscience and psychology.

List of contributors	p. xiii
Computational vision in neural and machine systems	p. 1
Introduction	p. 1
The CD-ROM	p. 4
References	p. 4
Dynamical systems	p. 7
Exploring contrast-controlled adaptation processes in human vision (with help from Buffy the Vampire Slayer	p. 9
Dynamics of luminance-controlled adaption processes (light adaptation)	p. 10
Dynamics of contrast-controlled adaptation processes	p. 14
Using Buffy and Regular Steady-State backgrounds	p. 25
A new kind of complex channel with embedded contrast adaptation (the Buffy channel)	p. 34
Where are we now?	p. 42
References	p. 46
Image comparison and motion detection by a contrario methods	p. 49
Introduction	p. 49
Image comparison	p. 51
Motion detection	p. 57
Conclusions and perspectives	p. 66
References	p. 67
Computer vision in the Mars Exploration Rover (MER) mission	p. 71
Introduction	p. 71
Overview of rover hardware and mission operations	p. 72
Stereo vision-based obstacle detection and avoidance	p. 74
Visual odometry	p. 77
Descent Image Motion Estimation System (DIMES)	p. 79
Discussion	p. 82
References	p. 83
Calibration and shape recovery from videos of dynamic scenes	p. 85
Introduction	p. 85
Silhouette-based camera network calibration	p. 86
Articulated shape recovery from video	p. 94
Conclusions and discussion	p. 100
References	p. 102
Specular planar target surface recovery via coded target stereopsis	p. 105
Introduction	p. 105
Exploiting properties of planar specular surfaces	p. 106
Actively recovering 3D specular surface structure	p. 107
Discussion	p. 113
References	p. 113
Neural construction of objects from parts	p. 115
Basis function representation of object parts	p. 116
Synthesis of part signals into representations of multi-part configurations	p. 120
References	p. 124
Attention, motion, and eye movements	p. 127
Attention and action	p. 129
Introduction	p. 129
Active vision and attention in robots	p. 129
Attention and saccade generation in biological systems	p. 131
Covert attention tracking and microsaccades	p. 136
What is next?	p. 145
References	p. 144
Cueing visual search in clutter	p. 149
Background	p. 149
Detecting smooth motion paths in noise	p. 152
Self-cueing in contour formation	p. 157
Uncertainty and collinear facilitation at detection threshold	p. 160
Conclusions	p. 161
References	p. 162
Transsaccadic memory of visual features	p. 167
Introduction	p. 167
Methods	p. 168
Results	p. 172
Discussion	p. 175
References	p. 178
Modeling what attracts human gaze over dynamic natural scenes	p. 183
Introduction and rationale	p. 183
Quantifying surprise	p. 184
Computational model	p. 188
Experimental validation results	p. 194
Discussion and conclusion	p. 195
References	p. 198
Stereo	p. 201
Global stereo in polynomial time	p. 203
Introduction	p. 203
Dynamic programming stereo and its limits	p. 205
The max-flow/min-cut formulation	p. 209
An experiment	p. 215
Conclusions and future work	p. 217
References	p. 218
Computational analysis of binocular half occlusions	p. 221
Introduction	p. 221
Technical approach	p. 224
Empirical evaluation	p. 231
Summary and conclusions	p. 236
References	p. 236
Speed versus quality - measuring and optimizing stereo for telepresence	p. 241
Stereo reconstruction of the human form	p. 241
Stereo, depth and surfaces	p. 242
Quality and empirical evaluation	p. 245
Temporal coherence	p. 250
Conclusion	p. 254
References	p. 255
Binocular combination: measurements and a model	p. 257
Introduction	p. 257
Methods	p. 262
Experiment 1. Binocular combination as determined by the interocular contrast ratio, the interocular grating phase difference, and overall contrast level	p. 268
Experiment 2. Stimulus duration	p. 273
Experiment 3. Masking by spatial-frequency noise	p. 279
Experiment 4. Masking sinewave gratings of different spatial frequencies	p. 281
Experiment 5. Temporal frequency masking	p. 284
Experiment 6. Orientation masking	p. 287
Model	p. 288
Discussion	p. 299
Summary and conclusions	p. 303
References and further reading	p. 305
Author index	p. 307
Subject index	p. 315
Table of Contents provided by Ingram. All Rights Reserved.

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

FREE SHIPPING

Amazon no longer offers textbook rentals. We do!

Computational Vision in Neural and Machine Systems

Summary

Table of Contents

Supplemental Materials