Muutke küpsiste eelistusi

E-raamat: Sea Ice Image Processing with MATLAB(R)

, (Department of Marine Technology, Norwegian University of Science and Technology (NTNU), Trondheim, Norway)
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 59,79 €*
  • * 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.
Sea Ice Image Processing with MATLAB(R)Suurem pilt

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. 

Sea Ice Image Processing with MATLAB addresses the topic of image processing for the extraction of key sea ice characteristics from digital photography, which is of great relevance for Artic remote sensing and marine operations. This valuable guide provides tools for quantifying the ice environment that needs to be identified and reproduced for such testing. This includes fit-for-purpose studies of existing vessels, new-build conceptual design and detailed engineering design studies for new developments, and studies of demanding marine operations involving multiple vessels and operational scenarios in sea ice. A major contribution of this work is the development of automated computer algorithms for efficient image analysis. These are used to process individual sea-ice images and video streams of images to extract parameters such as ice floe size distribution, and ice types. Readers are supplied with Matlab source codes of the algorithms for the image processing methods discussed in the book made available as online material.

Features

Presents the first systematic work using image processing techniques to identify ice floe size distribution from aerial images Helps identify individual ice floe and obtain floe size distributions for Arctic offshore operations and transportation Explains specific algorithms that can be combined to solve various problems during polar sea ice investigations Includes MATLAB® codes useful not only for academics, but for ice engineers and scientists to develop tools applicable in different areas such as sustainable arctic marine and coastal technology research Provides image processing techniques applicable to other fields like biomedicine, material science, etc

Arvustused

"Sea Ice Image Processing with MATLAB® is a large and important step forward in the creation of the necessary tools for the planning and execution of Arctic maritime operations. The ability to predict what kind of ice that one will encounter is of critical importance for safety, as you need to know what you are going to run into. This book provides an important insight to the cutting edge of technology being developed for sustainable operations in the polar regions." Åke Rohlén, Arctic Marine Solutions AB, Sweden

"This is a really elaborate book for the image processing to extract ice information. To my knowledge, this is the first work that describes the methods to obtain ice floe size distribution in a systematic and sophisticated way. It is still a big issue to predict the sea ice behavior in the numerical sea ice model due to the lack of our knowledge about the sub-grid scale information of sea ice, especially floe size distribution. This book aims at solving this problem and has achieved it to some extent. This work certainly contributes to this issue and sheds light on collecting observational data on an operational basis. Therefore, I sincerely hope the algorithm developed by the authors will be used by many people to improve our understanding of sea ice properties." Takenobu Toyota, Hokkaido University, Sapporo, Japan

Foreword xiii
Preface xv
Acknowledgments xix
Contributors xxi
List of Figures xxiii
List of Tables xxix
Chapter 1 Introduction 1(10)
1.1 Research background
1(2)
1.2 Sea ice parameters
3(2)
1.2.1 Ice concentration
3(1)
1.2.2 Ice types
4(1)
1.2.3 Ice floe size and floe size distribution
4(1)
1.3 Applications of digital image processing techniques for ice parameter identification
5(3)
1.3.1 Ice concentration calculation
5(1)
1.3.2 Sea ice type classification
6(1)
1.3.3 Ice floe identification
7(1)
1.4 Book scope and structure
8(3)
Chapter 2 Digital Image Processing Preliminaries 11(26)
2.1 Image types
11(5)
2.1.1 Grayscale image
11(2)
2.1.2 Color image
13(2)
2.1.2.1 The RGB color space
13(1)
2.1.2.2 The CMY and CMYK color spaces
13(2)
2.1.2.3 The HSI color space
15(1)
2.1.3 Indexed image
15(1)
2.2 Image histogram
16(1)
2.3 Basic relationships between pixels
17(3)
2.3.1 Pixel neighborhoods
17(1)
2.3.2 Adjacency
18(1)
2.3.3 Path
19(1)
2.3.4 Connectivity
19(1)
2.3.5 Region and boundary
19(1)
2.4 Distance transform
20(2)
2.4.1 Euclidean distance
21(1)
2.4.2 City-block distance
21(1)
2.4.3 Chessboard distance
22(1)
2.4.4 Performance of the distance metrics
22(1)
2.5 Convolution
22(2)
2.6 Set and logical operations
24(5)
2.6.1 Set operations on binary images
24(3)
2.6.2 Set operations on grayscale images
27(1)
2.6.3 Logical operations
28(1)
2.7 Chain code
29(3)
2.8 Image interpolation
32(5)
2.8.1 Nearest neighbor interpolation
33(1)
2.8.2 Bilinear interpolation
33(2)
2.8.3 Bicubic interpolation
35(2)
Chapter 3 Ice Pixel Detection 37(22)
3.1 Thresholding
37(9)
3.1.1 Global thresholding
38(5)
3.1.1.1 Otsu thresholding
40(3)
3.1.2 Local thresholding
43(1)
3.1.3 Multithresholding
44(2)
3.2 Clustering
46(6)
3.2.1 Clustering types
47(1)
3.2.2 K-means clustering
48(4)
3.3 Experiment results and discussion
52(7)
Chapter 4 Ice Edge Detection 59(24)
4.1 Derivative edge detection
59(7)
4.1.1 Gradient operator
59(4)
4.1.2 Laplacian
63(3)
4.2 Morphological edge detection
66(12)
4.2.1 Erosion and dilation
67(4)
4.2.1.1 Binary erosion and dilation
68(1)
4.2.1.2 Grayscale erosion and dilation
69(2)
4.2.2 Morphological closing and opening
71(2)
4.2.2.1 Morphological closing
71(2)
4.2.2.2 Morphological opening
73(1)
4.2.3 Morphological reconstruction
73(4)
4.2.3.1 Binary morphological reconstruction
73(2)
4.2.3.2 Grayscale morphological reconstruction
75(2)
4.2.4 Morphological gradient
77(1)
4.3 Experimental results and discussion
78(5)
Chapter 5 Watershed-Based Ice Floe Segmentation 83(26)
5.1 Watershed segmentation
84(12)
5.1.1 Watershed segmentation using gradients
89(1)
5.1.2 Watershed segmentation using the distance transform
90(5)
5.1.3 Marker-controlled watershed segmentation
95(1)
5.2 Combination of the watershed and neighboring-region merging algorithms
96(8)
5.2.1 Concave detection by chain code
99(11)
5.2.1.1 Boundary tracing
99(4)
5.2.1.2 Differential chain code
103(1)
5.3 Experimental results and discussion
104(5)
Chapter 6 GVF Snake-Based Ice Floe Boundary Identification and Ice Image Segmentation 109(36)
6.1 Traditional parametric snake model
110(13)
6.1.1 The energy functionals
111(4)
6.1.1.1 Internal energy
111(2)
6.1.1.2 External energy
113(2)
6.1.2 Implementation
115(7)
6.1.3 Limitations
122(1)
6.2 Gradient vector flow (GVF) snake
123(5)
6.3 Contours initialization for applying the GVF snake algorithm in ice floe boundary identification
128(7)
6.3.1 The location of initial contour
129(2)
6.3.2 The shape and size of the initial contour
131(2)
6.3.3 Automatic contour initialization based on the distance transform
133(2)
6.4 Ice image segmentation
135(2)
6.5 Discussion
137(8)
6.5.1 Stopping criterion for the snake
137(1)
6.5.2 GVF capture range
138(1)
6.5.3 Border effects
139(6)
Chapter 7 Sea Ice Type Identification 145(30)
7.1 Ice shape enhancement
145(6)
7.1.1 Morphological cleaning
146(1)
7.1.2 Connected component extraction and labeling
146(1)
7.1.3 Hole filling
147(3)
7.1.3.1 Iterative dilation-based hole filling algorithm
147(2)
7.1.3.2 Morphological reconstruction-based hole filling algorithm
149(1)
7.1.4 Ice shape enhancement algorithm
150(1)
7.2 General sea ice image processing
151(12)
7.2.1 Sea ice pixel extraction
154(1)
7.2.2 Sea ice edge detection
155(1)
7.2.3 Sea ice shape enhancement
155(4)
7.2.4 Sea ice types classification and floe size distribution
159(4)
7.3 Case studies and discussion
163(12)
7.3.1 Distorted overall sea ice image processing
163(3)
7.3.1.1 Local processing
163(1)
7.3.1.2 Geometric calibration
164(2)
7.3.1.3 Result
166(1)
7.3.2 A preliminary sensitivity study
166(10)
7.3.2.1 Snake's evolution iterations
168(1)
7.3.2.2 GVF field iterations
169(6)
Chapter 8 Sea Ice Image Processing Applications 175(20)
8.1 A shipborne camera system to acquire sea ice concentration at engineering scale
176(5)
8.1.1 Installation of cameras
176(1)
8.1.2 Methods
176(4)
8.1.3 Results and discussions
180(1)
8.2 Numerical characterization of a real ice field for parametrization of an ice simulator
181(8)
8.2.1 Sea ice numerical modeling
184(5)
8.3 Sea ice floe size statistic
189(6)
Chapter 9 Model Sea Ice Image Processing Applications 195(18)
9.1 Experimental setup and model sea ice image data
195(1)
9.2 Ice concentration
196(5)
9.2.1 Ice concentration deriving from overall tank image
197(2)
9.2.2 Ice concentration deriving from model sea ice video
199(2)
9.3 Ice floe identification
201(12)
9.3.1 Contour initialization for crowded rectangular-shaped model sea ice floes
204(1)
9.3.2 Ice floe identification for overall tank image
205(3)
9.3.2.1 Model sea ice floe modeling
207(1)
9.3.3 Ice floe identification for model sea ice video: monitoring maximum floe size
208(5)
Appendix A Geometric Calibration 213(8)
A.1 Orthorectification
213(5)
A.1.1 An analytical method
213(3)
A.1.2 A linear approximation
216(2)
A.2 Calibration of radial lens distortion calibration
218(3)
A.2.1 An analytical method for fisheye distortion
218(2)
A.2.2 A polynomial approximation
220(1)
Appendix B Ice Image Data Structure 221(6)
Glossary 227(2)
References 229(12)
Index 241
Qin Zhang received her Ph.D. degree in 2015 at the Norwegian University of Science and Technology (NTNU), Trondheim, Norway. She became a researcher in 2015 at the Center for Research-based Innovation (CRI) Sustainable Arctic Marine and Coastal Technology (SAMCoT), NTNU. Her research interests include remote sensing, image and sensory data processing.



Prof. Roger Skjetne received his MSc degree in 2000 in control engineering at the University of California at Santa Barbara, and his PhD degree in 2005 at the Norwegian University of Science and Technology (NTNU), for which his thesis was awarded the Exxon Mobil prize for best PhD thesis in applied research. Prior to his studies, he worked as an electrician for Aker Elektro AS on numerous oil installations for the North Sea. In 2004-2009 he was employed in Marine Cybernetics AS, working on Hardware-In-the-Loop (HIL) simulation for testing safety-critical marine control systems. From August 2009 he has held the position of Professor in Marine Control Engineering at the Department of Marine Technology at NTNU, where he presently is the leader of the research group on Marine Structures. His research interests are within Arctic stationkeeping operations and Ice Management systems for ships and rigs, environmentally robust control of shipboard electric power systems, and nonlinear control theory for motion control of single and groups of marine vessels. Roger Skjetne is leader of the ice management work package in the CRI Sustainable Arctic Marine and Coastal Technology (SAMCoT), associated researcher in the CoE Centre for Ships and Ocean Structures (CeSOS) and CoE Autonomous Marine Operations and Systems (AMOS), principal researcher in the CRI on Marine Operations (MOVE), and he was project manager for the KMB Arctic DP research project. He is also co-founder of the two companies BluEye Robotics and ArcISo.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97813510691826e.html
Märksõnad: