Muutke küpsiste eelistusi

E-raamat: Academic Press Library in Signal Processing, Volume 6: Image and Video Processing and Analysis and Computer Vision

Editor-in-chief (University of Maryland, College Park, USA), Editor-in-chief (Professor of Machine Learning and Signal Processing, National and Kapodistrian University of Athens, Athens, Greece)
  • Formaat: PDF+DRM
  • Ilmumisaeg: 28-Nov-2017
  • Kirjastus: Academic Press Inc
  • Keel: eng
  • ISBN-13: 9780128119006
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 166,53 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Academic Press Library in Signal Processing, Volume 6: Image and Video Processing and Analysis and Computer VisionSuurem pilt
  • Formaat: PDF+DRM
  • Ilmumisaeg: 28-Nov-2017
  • Kirjastus: Academic Press Inc
  • Keel: eng
  • ISBN-13: 9780128119006
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Academic Press Library in Signal Processing, Volume 6: Image and Video Processing and Analysis and Computer Vision is aimed at university researchers, post graduate students and R&D engineers in the industry, providing a tutorial-based, comprehensive review of key topics and technologies of research in both image and video processing and analysis and computer vision. The book provides an invaluable starting point to the area through the insight and understanding that it provides.

With this reference, readers will quickly grasp an unfamiliar area of research, understand the underlying principles of a topic, learn how a topic relates to other areas, and learn of research issues yet to be resolved.

  • Presents a quick tutorial of reviews of important and emerging topics of research
  • Explores core principles, technologies, algorithms and applications
  • Edited and contributed by international leading figures in the field
  • Includes comprehensive references to journal articles and other literature upon which to build further, more detailed knowledge

Muu info

Enables readers to quickly grasp and understand hot new topics of research in image and video processing
Contributors xiii
About the Editors xv
Section Editors xvii
Introduction xxi
SECTION 1 VISUAL INFORMATION PROCESSING
Chapter 1 Multiview Video: Acquisition, Processing, Compression, and Virtual View Rendering
3(72)
Olgierd Stankiewicz
Gauthier Lafruit
Marek Domanski
1.1 Multiview Video
3(9)
1.1.1 Multiview Video and 3D Graphic Representation Formats for VR
4(1)
1.1.2 Super-Multiview Video for 3D Light Field Displays
5(1)
1.1.3 DIBR Smooth View Interpolation
5(2)
1.1.4 Basic Principles of DIBR
7(2)
1.1.5 DIBR vs. Point Clouds
9(3)
1.1.6 DIBR, Multiview Video, and MPEG Standardization
12(1)
1.2 Multiview Video Acquisition
12(17)
1.2.1 Multiview Fundamentals
12(4)
1.2.2 Depth in Stereo and Multiview Video
16(4)
1.2.3 Multicamera System
20(3)
1.2.4 Acquisition System Examples
23(6)
1.3 Multiview Video Preprocessing
29(9)
1.3.1 Geometrical Parameters
29(6)
1.3.2 Video Correction
35(3)
1.4 Depth Estimation
38(10)
1.4.1 Local Stereo Matching
39(2)
1.4.2 Global Stereo Matching
41(3)
1.4.3 Multicamera Depth Estimation
44(4)
1.5 View Synthesis and Virtual Navigation
48(6)
1.5.1 Warping
49(2)
1.5.2 View Blending
51(1)
1.5.3 Inpainting
52(1)
1.5.4 View Synthesis Reference Software
53(1)
1.6 Compression
54(11)
1.6.1 Introduction
54(4)
1.6.2 Monoscopic Video Coding and Simulcast Coding of Multiview Video
58(4)
1.6.3 Multiview Video Coding
62(1)
1.6.4 3D Video Coding
63(2)
1.7 Future Trends
65(10)
Acknowledgments
67(1)
Glossary
67(1)
References
68(6)
Further Reading
74(1)
Chapter 2 Plenoptic Imaging: Representation and Processing
75(38)
Fernando Pereira
Eduardo A.B. da Silva
Gauthier Lafruit
2.1 Introduction
75(3)
2.2 Light Representation: The Plenoptic Function Paradigm
78(4)
2.3 Empowering the Plenoptic Function: Example Use Cases
82(6)
2.3.1 Light Field Communication
83(1)
2.3.2 Light Field Editing
84(1)
2.3.3 Free Navigation
85(1)
2.3.4 Interactive All-Reality
86(2)
2.4 Plenoptic Acquisition and Representation Models
88(7)
2.4.1 Acquisition
89(2)
2.4.2 Representation
91(3)
2.4.3 Display
94(1)
2.5 Plenoptic Data Coding
95(3)
2.6 Plenoptic Data Rendering
98(3)
2.6.1 Rendering Textured Meshes and Point Clouds
98(1)
2.6.2 Interpolating a Light Field in a Microlens and/or Discrete Camera Array
98(1)
2.6.3 View Synthesis in MVV Plus Depth
99(1)
2.6.4 Refocusing With Microlens Light Field
99(2)
2.7 Plenoptic Representations Relationships
101(1)
2.8 Related Standardization Initiatives
102(3)
2.8.1 MPEGFTV
103(1)
2.8.2 JPEG PLENO
104(1)
2.9 Future Trends and Challenges
105(8)
Acknowledgments
107(1)
Glossary
107(1)
References
108(3)
Further Reading
111(2)
Chapter 3 Visual Attention, Visual Salience, and Perceived Interest in Multimedia Applications
113(50)
Yashas Rai
Patrick Le Callet
3.1 Introduction
113(2)
3.1.1 Visual Attention in the Field of Multimedia: A Rising Story
113(1)
3.1.2 From Vision Science to Engineering: Concepts Mash Up and Confusion
114(1)
3.2 Classification of Attention Mechanisms
115(5)
3.2.1 Overt and Covert Attention
115(1)
3.2.2 Types of Overt Visual Attention Mechanisms
116(4)
3.3 Computational Models of Visual Attention
120(10)
3.3.1 Top-Down Computational Attention Models
121(2)
3.3.2 Information-Theory and Decision-Theory Models
123(2)
3.3.3 Spatio-Temporal Computational Models
125(1)
3.3.4 Graph-Based Methods
126(2)
3.3.5 Scan-Path (Saccadic) Models
128(2)
3.4 Acquiring Ground Truth Visual Attention Data for Model Verification
130(17)
3.4.1 Eye-Tracking
130(8)
3.4.2 Processing the Eye-Tracking Data
138(3)
3.4.3 Testing the Computational Models
141(6)
3.5 Applications of Visual Attention
147(16)
3.5.1 Quality Assessment
147(2)
3.5.2 Visual Attention in Multimedia Delivery
149(1)
3.5.3 Applications in Medicine
150(1)
3.5.4 Visual Attention and Immersive Media: A Rising Love Story
151(1)
References
152(11)
Chapter 4 Emerging Science of QoE in Multimedia Applications Concepts, Experimental Guidelines, and Validation of Models
163(50)
Lukas Krasula
Patrick Le Callet
4.1 QoE Definition and Influencing Factors
164(2)
4.1.1 Factors Influencing QoE
164(2)
4.2 QoE Measurement
166(25)
4.2.1 Including System Influence Factors in QoE Measurement
168(1)
4.2.2 Including Context Influence Factors in QoE Measurement
169(1)
4.2.3 Including Human Influence Factors in QoE Measurement
169(1)
4.2.4 Multidimensional Perceptual Scales for QoE Measurement
170(2)
4.2.5 Direct Scaling Methods
172(5)
4.2.6 Processing of Results of Direct Scaling Methods
177(1)
4.2.7 Indirect Scaling Methods
178(4)
4.2.8 Processing of Results of Indirect Screening Methods
182(5)
4.2.9 Influence Factor's Significance Calculation
187(4)
4.3 Performance Evaluation of Objective QoE Estimators
191(14)
4.3.1 Pearson's Linear Correlation Coefficient
192(1)
4.3.2 Root-Mean-Squared Error
193(1)
4.3.3 Epsilon-Insensitive Root-Mean-Squared Error
194(1)
4.3.4 Outlier Ratio
194(1)
4.3.5 Spearman's Rank Order Correlation Coefficient
195(1)
4.3.6 Kendall's Rank Order Correlation Coefficient
195(1)
4.3.7 Resolving Power Measures
196(4)
4.3.8 ROC-Based Performance Evaluation
200(3)
4.3.9 Compensation for Multiple Comparisons
203(2)
4.4 Conclusion
205(8)
References
205(8)
SECTION 2 COMPUTATIONAL IMAGING AND 3D ANALYSIS
Chapter 5 Computational Photography
213(24)
Ashok Veeraraghavan
Aswin C. Sankaranarayanan
Adithya K. Pediredla
5.1 Introduction
213(1)
5.2 Breaking Precepts Underlying Photography
214(5)
5.2.1 Sensor Resolution ≠ Image Resolution
214(2)
5.2.2 Space-Time Bandwidth Product Can Be Greater Than the ADC Rate
216(1)
5.2.3 Depth of Field Can Be Changed Independent of Exposure Time
217(2)
5.3 Cameras With Novel Form Factors and Capabilities
219(6)
5.3.1 Lensless Imaging
219(3)
5.3.2 Ptychography
222(2)
5.3.3 Subdiffraction Limited Microscopy
224(1)
5.4 Solving Inverse Problems
225(7)
5.4.1 Time-of-Flight-Based Range Imaging
225(4)
5.4.2 Direct-Global Separation
229(2)
5.4.3 Scattering
231(1)
5.5 Conclusions
232(5)
References
233(4)
Chapter 6 Face Detection With a 3D Model
237(24)
Adrian Barbu
Nathan Lay
Gary Gramajo
6.1 Introduction
237(4)
6.1.1 Related Work
239(2)
6.2 Face Detection Using a 3D Model
241(6)
6.2.1 Energy Model
242(1)
6.2.2 Inference Algorithm
242(1)
6.2.3 Detecting Face Keypoints
243(1)
6.2.4 Generating 3D Pose Candidates
244(1)
6.2.5 Generating Face Candidates
245(1)
6.2.6 Scoring the Face Candidates
245(2)
6.2.7 Nonmaximal Suppression
247(1)
6.3 Parameter Sensitive Model
247(3)
6.3.1 Training the Parameter Sensitive Model
248(2)
6.4 Fitting 3D Models
250(1)
6.4.1 Fitting a Rigid Projection Transformation
250(1)
6.4.2 Learning a 3D Model From 2D Annotations
250(1)
6.5 Experiments
251(6)
6.5.1 Evaluation of Face Candidates
252(2)
6.5.2 Face Detection Results
254(3)
6.6 Conclusions and Future Trends
257(4)
References
258(3)
Chapter 7 A Survey on Nonrigid 3D Shape Analysis
261(44)
Hamid Laga
7.1 Introduction
261(2)
7.2 General Formulation
263(4)
7.2.1 Representations
263(1)
7.2.2 Invariance Requirements
264(2)
7.2.3 Problem Statement and Taxonomy
266(1)
7.3 Shape Spaces and Metrics
267(11)
7.3.1 Kendall's Shape Space
268(3)
7.3.2 Metrics That Capture Physical Deformations
271(4)
7.3.3 Transformation-Based Representations
275(3)
7.4 Registration and Geodesies
278(8)
7.4.1 Registration
278(4)
7.4.2 Geodesies
282(4)
7.5 Statistical Analysis Under Elastic Metrics
286(3)
7.5.1 Statistical Analysis Using Non-Euclidean Metrics
286(2)
7.5.2 Statistical Analysis by SRNF Inversion
288(1)
7.6 Examples and Applications
289(8)
7.6.1 Registration and Geodesic Deformations
289(2)
7.6.2 Elastic Coregistration of 3D Shapes
291(1)
7.6.3 Classification
292(2)
7.6.4 Random 3D Model Synthesis
294(1)
7.6.5 Other Applications
294(3)
7.7 Summary and Perspectives
297(8)
Acknowledgments
299(1)
References
299(6)
Chapter 8 Markov Models and MCMC Algorithms in Image Processing
305(42)
Xavier Descombes
8.1 Introduction: The Probabilistic Approach in Image Analysis
305(1)
8.2 Lattice-based Models and the Bayesian Paradigm
306(9)
8.2.1 Modeling
306(2)
8.2.2 Optimization
308(3)
8.2.3 Parameter Estimation
311(4)
8.3 Some Inverse Problems
315(7)
8.3.1 Denoising and Deconvolution: The Restoration Problem
315(1)
8.3.2 Segmentation Problem
316(4)
8.3.3 Texture Modeling
320(2)
8.4 Spatial Point Processes
322(8)
8.4.1 Modeling
323(2)
8.4.2 Optimizing
325(5)
8.5 Multiple Objects Detection
330(12)
8.5.1 Population Evaluation
330(4)
8.5.2 Road Network Detection
334(8)
8.6 Conclusion
342(5)
References
342(2)
Further Reading
344(3)
SECTION 3 IMAGE AND VIDEO-BASED ANALYTICS
Chapter 9 Scalable Image Informatics
347(18)
Dmitry Fedorov
B.S. Manjunath
Christian A. Lang
Kristian Kvilekval
9.1 Introduction
347(2)
9.1.1 Core Requirements
347(2)
9.2 Core Concepts
349(3)
9.2.1 Metadata Graph
351(1)
9.2.2 Versioning, Provenance, and Queries
351(1)
9.3 Basic micro-services
352(4)
9.3.1 Uniform Metadata Representation and Query Orchestration: Data Service
353(1)
9.3.2 Scalability of Micro-Services and Analysis
353(1)
9.3.3 Analysis Extensions: Module Service
354(1)
9.3.4 Uniform Representation of Heterogeneous Storage Subsystems: Blob Service
355(1)
9.3.5 Uniform Access and Operations Over Data Files: Image Service and Table Service
355(1)
9.4 Analysis Modules
356(2)
9.4.1 Python and Matlab Scripting
357(1)
9.4.2 Pipeline Support
357(1)
9.4.3 Complex Module Execution Descriptors
357(1)
9.5 Building on the Concepts: Sparse Images
358(1)
9.6 Feature Services and Machine Leaning
359(2)
9.6.1 Feature Service
359(1)
9.6.2 Connoisseur Service for Deep Learning
359(2)
9.6.3 Connoisseur Module for Domain Experts
361(1)
9.7 Application Example: Annotation and Classification of Underwater Images
361(2)
9.8 Summary
363(2)
Acknowledgments
364(1)
References
364(1)
Chapter 10 Person Re-identification
365(30)
Marco Cristani
Vittorio Murino
10.1 Introduction
365(2)
10.2 The Re-identification Problem: Scenarios, Taxonomies, and Related Work
367(4)
10.2.1 The Scenarios and Taxonomy
367(1)
10.2.2 Related Work
368(2)
10.2.3 Feature Extraction
370(1)
10.2.4 Model Learning
371(1)
10.3 Experimental Evaluation of Re-id Datasets and Their Characteristics
371(6)
10.4 The SDALF Approach
377(8)
10.4.1 Object Segmentation
378(1)
10.4.2 Symmetry-Based Silhouette Partition
379(2)
10.4.3 Symmetry-Driven Accumulation of Local Features
381(3)
10.4.4 The Matching Phase
384(1)
10.5 Metric Learning
385(5)
10.5.1 Mahalanobis Metric Learning
386(1)
10.5.2 Large Margin Nearest Neighbor
387(1)
10.5.3 Efficient Impostor-Based Metric Learning
388(1)
10.5.4 KISSME
389(1)
10.6 Conclusions and New Challenges
390(5)
References
390(5)
Chapter 11 Social Network Inference in Videos
395(30)
Ashish Gupta
Alper Yilmaz
11.1 Introduction
395(3)
11.2 Related Work
398(2)
11.3 Video Shot Segmentation
400(1)
11.4 Actor Recognition
401(1)
11.5 Learning to Group Actors
402(8)
11.5.1 Visual Features
404(3)
11.5.2 Auditory Features
407(2)
11.5.3 Grouping Criteria
409(1)
11.6 Inferring Social Communities
410(2)
11.6.1 Social Network Graph
410(1)
11.6.2 Actor Interaction Model
411(1)
11.7 Social Network Analysis
412(1)
11.7.1 Assignment to Communities
412(1)
11.7.2 Estimating Community Leader
413(1)
11.8 Experiments
413(5)
11.8.1 The Dataset
414(1)
11.8.2 Audiovisual Alignment
414(1)
11.8.3 Social Affinity
415(1)
11.8.4 Community Assignment
415(3)
11.8.5 Actor Affinity
418(1)
11.8.6 Community Leaders
418(1)
11.9 Latent Features
418(3)
11.10 Summary
421(4)
References
422(2)
Further Reading
424(1)
Index 425
Prof. Rama Chellappa received the B.E. (Hons.) degree from the University of Madras, India, in 1975 and the M.E. (Distinction) degree from Indian Institute of Science, Bangalore, in 1977. He received M.S.E.E. and Ph.D. Degrees in Electrical Engineering from Purdue University, West Lafayette, IN, in 1978 and 1981 respectively. Since 1991, he has been a Professor of Electrical Engineering and an affiliate Professor of Computer Science at University of Maryland, College Park. He is also affiliated with the Center for Automation Research (Director) and the Institute for Advanced Computer Studies (Permanent Member). In 2005, he was named a Minta Martin Professor of Engineering. Prior to joining the University of Maryland, he was an Assistant (1981-1986) and Associate Professor (1986-1991) and Director of the Signal and Image Processing Institute (1988-1990) at University of Southern California, Los Angeles. Over the last 29 years, he has published numerous book chapters, peer-reviewed journal and conference papers. He has co-authored and edited books on MRFs, face and gait recognition and collected works on image processing and analysis. His current research interests are face and gait analysis, markerless motion capture, 3D modeling from video, image and video-based recognition and exploitation and hyper spectral processing. Sergios Theodoridis is professor emeritus of machine learning and data processing with the National and Kapodistrian University of Athens, Athens, Greece. He has also served as distinguished professor with the Aalborg University Denmark and as professor with the Chinese University of Hong Kong, Shenzhen, China. In 2023, he received an honorary doctorate degree (D.Sc) from the University of Edinburgh, U.K. He has also received a number of prestigious awards, including the 2014 IEEE Signal Processing Magazine Best Paper Award, the 2009 IEEE Computational Intelligence Society Transactions on Neural Networks Outstanding Paper Award, the 2017 European Association for Signal Processing (EURASIP) Athanasios Papoulis Award, the 2014 IEEE Signal Processing Society Carl Friedrich Gauss Education Award, and the 2014 EURASIP Meritorious Service Award. He has served as president of EURASIP and vice president for the IEEE Signal Processing Society. He is a Fellow of EURASIP and a Life Fellow of IEEE. He is the coauthor of the book Pattern Recognition, 4th edition, Academic Press, 2009 and of the book Introduction to Pattern Recognition: A MATLAB Approach, Academic Press, 2010.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97801281190062e.html
Märksõnad: