Atjaunināt sīkdatņu piekrišanu

E-grāmata: Fish4Knowledge: Collecting and Analyzing Massive Coral Reef Fish Video Data

Edited by , Edited by , Edited by , Edited by , Edited by
Citas grāmatas par šo tēmu:
  • Formāts - PDF+DRM
  • Cena: 106,47 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
Fish4Knowledge: Collecting and Analyzing Massive Coral Reef Fish Video DataPalielināt
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

This bookgives a start-to-finish overview of the whole Fish4Knowledge project, in 18short chapters, each describing one aspect of the project. The Fish4Knowledgeproject explored the possibilities of big video data, in this case fromundersea video. Recording and analyzing 90 thousand hours of video from tencamera locations, the project gives a 3 year view of fish abundance in severaltropical coral reefs off the coast of Taiwan. The research system built aremote recording network, over 100 Tb of storage, supercomputer processing,video target detection and tracking, fish species recognition and analysis, alarge SQL database to record the results and an efficient retrieval mechanisms.Novel user interface mechanisms were developed to provide easy access formarine ecologists, who wanted to explore the dataset. The book is a usefulresource for system builders, as it gives an overview of the many new methodsthat were created to build the Fish4Knowledge system in a manner that

alsoallows readers to see how all the components fit together.

Overviewof the Fish4Knowledge Project.- User InformationNeeds.- Supercomputing Resources.- Marine Video Data Capture andStorage.- Logical Data Resource Storage.- Software Architecture with Flexibilityfor the Data-Intensive Fish4Knowledge Project.- Fish4Knowledge Database Structure,Creating and Sharing Scientific Data).- Intelligent Workflow Managementfor Fish4Knowledge using the SWELL System.- Fish Detection.- FishTracking.- Hierarchical Classification System with Reject Option for LiveFish Recognition.- Fish Behavior Analysis.- UnderstandingUncertainty Issues in the Exploration of Fish Counts.- Data Groundtruthingand Crowdsourcing.- Counting on Uncertainty: Obtaining Fish Counts from Machine LearningDecisions.- Experiments with the Full Fish4Knowledge Dataset.- TheFish4Knowledge Virtual World Gallery.- Conclusions.
1 Overview of the Fish4Knowledge Project
1(18)
Robert B. Fisher
Kwang-Tsao Shao
Yun-Heh Chen-Burger
1.1 Introduction
1(2)
1.2 A Quick Tour of the Project
3(7)
1.3 Background Information About the Studied Marine Environments
10(4)
1.4 Project Context, Objectives and Achievements
14(1)
1.5 Project Team
15(1)
1.6 Conclusions
16(3)
References
16(3)
2 User Information Needs
19(12)
Emma Beauxis-Aussalet
Lynda Hardman
2.1 Introduction
19(1)
2.2 Information Needs for Ecology Research on Fish Populations
20(2)
2.3 Data Collection Techniques
22(3)
2.4 Potential Biases
25(2)
2.5 Uncertainty Factors Impacting the Potential Biases
27(2)
2.6 Conclusion
29(2)
References
29(2)
3 Supercomputing Resources
31(10)
Jih-Sheng Chang
Sun-In Lin
Fang-Pang Lin
Hsiu-Mei Chou
3.1 Introduction
31(2)
3.2 Computational Platform
33(1)
3.2.1 Supercomputing Platform
33(1)
3.2.2 The Virtual Machine Cluster Platform
34(1)
3.3 Process Execution Interface
34(4)
3.3.1 Distributed Resource Management System
35(3)
3.4 Summary
38(3)
References
39(2)
4 Marine Video Data Capture and Storage
41(10)
Sun-In Lin
Fang-Pang Lin
Hsiu-Mei Chou
4.1 Introduction
41(1)
4.2 Enhanced Video Capturing System
42(2)
4.2.1 Better Video Server Management
42(1)
4.2.2 Local Buffer Space
43(1)
4.3 Massive Storage System
44(1)
4.3.1 Assembly of Storage Drives
45(1)
4.4 Improvement of Data Retrieval Efficiency
45(5)
4.4.1 Universally Unique Identifier
46(2)
4.4.2 Database Caching
48(2)
4.5 Summary
50(1)
References
50(1)
5 Logical Data Resource Storage
51(8)
Hsiu-Mei Chou
5.1 Introduction
51(2)
5.2 Data Management
53(2)
5.2.1 Design of Database
53(1)
5.2.2 Videos Database
54(1)
5.2.3 MetaData Database
54(1)
5.3 Implementation
55(2)
5.4 Future Work
57(2)
References
57(2)
6 Software Architecture with Flexibility for the Data-Intensive Fish4Knowledge Project
59(14)
Bastiaan J. Boom
6.1 Introduction
59(2)
6.2 Software Design
61(3)
6.2.1 Grand Design of Interaction
61(1)
6.2.2 Problem Verification of the Grand Design
61(1)
6.2.3 Practical Issues in Design Concerning the Database...
62(1)
6.2.4 Software Components Within the Fish4Knowledge Project
62(2)
6.3 Individual Software Components and Their Relations
64(3)
6.3.1 Fish Detection/Tracking Component
64(1)
6.3.2 Fish Recognition
64(1)
6.3.3 Fish Clustering
65(1)
6.3.4 User Interface
65(1)
6.3.5 Work-Flow
65(1)
6.3.6 Database
66(1)
6.3.7 Final Overview of the System
66(1)
6.4 Software Development Process Given the Architecture
67(2)
6.4.1 First Prototype System
67(1)
6.4.2 Final System
68(1)
6.4.3 Data Processing Status
68(1)
6.5 Lessons Learned with Current Architecture
69(2)
6.5.1 Database Definitions
69(1)
6.5.2 Dependencies
70(1)
6.5.3 Visualization
70(1)
6.6 Conclusion
71(2)
References
71(2)
7 Fish4Knowledge Database Structure, Creating and Sharing Scientific Data
73(10)
Bastiaan J. Boom
7.1 Introduction
73(1)
7.2 Relational Datastore Schema
74(2)
7.3 Linked Open Data
76(2)
7.3.1 Direct Mapping to RDF
76(1)
7.3.2 Taiwanese Coral Reef Fish Taxonomy in SKOS
77(1)
7.3.3 Interlinking and Alternative Representations of Direct Mapping Data
78(1)
7.4 Current Accessibility of Data
78(3)
7.5 Data Usage and Future Possibilities
81(1)
7.6 Summary
82(1)
References
82(1)
8 Intelligent Workflow Management for Fish4Knowledge Using the SWELL System
83(20)
Gayathri Nadarajan
Cheng-Lin Yang
Yun-Heh Chen-Burger
8.1 Introduction
83(1)
8.2 SWELL System Design
84(10)
8.2.1 Workflow Engine
86(2)
8.2.2 Workflow Monitor
88(2)
8.2.3 Workflow Evaluation
90(4)
8.3 F4K Domain Ontologies
94(7)
8.3.1 Goal Ontology
95(2)
8.3.2 Video Description Ontology
97(1)
8.3.3 Capability Ontology
98(3)
8.4 Concluding Remarks
101(2)
References
101(2)
9 Fish Detection
103(20)
Daniela Giordano
Simone Palazzo
Concetto Spampinato
9.1 Introduction
103(2)
9.2 Related Work
105(2)
9.3 The Fish Detection Approaches
107(5)
9.3.1 Background
107(2)
9.3.2 A Texton-Based Kernel Density Estimation for Video Object Segmentation
109(3)
9.4 Improving Detection Performance
112(4)
9.4.1 Perceptual Organization Model Features
113(1)
9.4.2 Motion Objectness
113(3)
9.5 Performance Analysis
116(4)
9.5.1 Fish Segmentation in Underwater Videos
116(4)
9.5.2 Post-Processing
120(1)
9.6 Conclusions
120(3)
References
121(2)
10 Fish Tracking
123(18)
Daniela Giordano
Simone Palazzo
Concetto Spampinato
10.1 Introduction
123(1)
10.2 Literature on Fish Tracking
124(1)
10.3 Underwater Object Tracking
125(2)
10.4 Tracking with Covariance Modeling
127(5)
10.4.1 Covariance-Based Tracker (COV)
127(3)
10.4.2 Covariance-Based Particle Filter (COVPF)
130(2)
10.5 Assessing Tracking Quality Online
132(3)
10.6 Results
135(3)
10.7 Conclusions
138(3)
References
139(2)
11 Hierarchical Classification System with Reject Option for Live Fish Recognition
141(20)
Phoenix X. Huang
11.1 Introduction
141(2)
11.2 Related Work
143(1)
11.3 Feature Extraction
144(3)
11.3.1 Image Pre-processing
144(2)
11.3.2 Feature Extraction
146(1)
11.4 Fish Recognition
147(5)
11.4.1 The Balance Guaranteed Optimized Tree Method
148(2)
11.4.2 Trajectory Voting Method
150(1)
11.4.3 Gaussian Mixture Model For Reject Option
150(2)
11.5 Fish Recognition Experiments
152(4)
11.5.1 Fish Recognition Experiments Using Ground Truth Data
152(3)
11.5.2 BGOTR Application to New Real Fish Videos
155(1)
11.6 Conclusion
156(5)
References
157(4)
12 Fish Behavior Analysis
161(20)
Cigdem Beyan
12.1 Introduction
161(1)
12.2 Problem Description, Definitions and Challenges
162(1)
12.3 Literature Review on Fish Behavior Understanding
163(1)
12.4 Proposed Methods
164(13)
12.4.1 A Rule Based Method for Filtering Normal Fish Trajectories
164(2)
12.4.2 Detecting Unusual Fish Trajectories Using Clustered and Labeled Data: Flat Classifier
166(4)
12.4.3 Detecting Unusual Fish Trajectories Using Hierarchical Decomposition
170(4)
12.4.4 Experiments and Results
174(3)
12.5 Concluding Remarks
177(4)
References
177(4)
13 Understanding Uncertainty Issues in the Exploration of Fish Counts
181(26)
Emma Beauxis-Aussalet
Lynda Hardman
13.1 Introduction
181(1)
13.2 Evaluating Uncertainty Due to Computer Vision Algorithms
182(6)
13.3 Visualizing Uncertainty Due to Computer Vision Algorithms
188(7)
13.3.1 Usability Issues with Computer Vision Evaluations
189(1)
13.3.2 Preliminary User Study
190(1)
13.3.3 Visualization Design for Non-expert Users
191(4)
13.4 Evaluating Uncertainty Due to In-Situ System Deployment
195(4)
13.5 Visualizing Uncertainty Due to In-Situ System Deployment
199(3)
13.6 Uncertainty Due to both Computer Vision Algorithms and In-Situ Deployment
202(2)
13.7 Future Work
204(3)
References
205(2)
14 Data Groundtruthing and Crowdsourcing
207(22)
Jiyin He
Concetto Spampinato
Bastiaan J. Boom
Isaak Kavasidis
14.1 Introduction
207(1)
14.2 Ground Truth for Fish Detection and Tracking
208(7)
14.2.1 Generating High Quality Annotations Using Collaborative Efforts
208(4)
14.2.2 Experimental Results
212(2)
14.2.3 Discussion
214(1)
14.3 A Cluster-Based Approach to Fish Recognition
215(5)
14.3.1 Introduction
215(1)
14.3.2 Ground-Truth Annotation Using Automatic Clustering
215(3)
14.3.3 Experiment
218(2)
14.3.4 Discussion
220(1)
14.4 Do You Need Experts in the Crowd? A Case Study in Fish Species Verification
220(6)
14.4.1 Experiments
222(2)
14.4.2 Results and Discussion
224(2)
14.5 Conclusion
226(3)
References
226(3)
15 Counting on Uncertainty: Obtaining Fish Counts from Machine Learning Decisions
229(10)
Bastiaan J. Boom
15.1 Introduction
229(1)
15.2 Related Work
230(1)
15.3 Method for Estimation of Counts Based on Similarity Scores of a Classifier
231(3)
15.3.1 Sampling Strategy
231(1)
15.3.2 Normal Classification Process
231(1)
15.3.3 Estimating Counts Based on Logistic Regression
232(1)
15.3.4 Limitation in Estimations
233(1)
15.4 Counting Fish with Logistic Regression
234(3)
15.4.1 Experimental Datasets for Counting Fish
234(1)
15.4.2 Results of Counting Fish with and Without Logistic Regression
235(2)
15.5 Conclusion
237(1)
15.6 Discussion
237(2)
References
238(1)
16 Experiments with the Full Fish4Knowledge Dataset
239(22)
Robert B. Fisher
16.1 Introduction
239(1)
16.2 Data
240(4)
16.3 Statistics of the Dataset
244(13)
16.4 Discussion
257(1)
16.5 Conclusions
258(3)
Reference
259(2)
17 The Fish4Knowledge Virtual World Gallery
261(8)
Yun-Heh Chen-Burger
Austin Tate
17.1 Introduction
261(1)
17.2 The Fish4Knowledge Second Life Gallery---Ground Level
262(3)
17.3 The Fish4Knowledge Second Life Gallery---Underwater Level
265(1)
17.4 The Fish4Knowledge Virtual World Gallery in OpenSimulator
266(1)
17.5 Conclusion
266(3)
18 Conclusions
269(14)
Robert B. Fisher
18.1 Summary of Achievements
269(3)
18.2 Critical Assessment
272(2)
18.3 What Lies in the Future
274(1)
18.4 Project Publications
275(8)
18.4.1 Fish Detection and Tracking
276(1)
18.4.2 Fish Species Classification and Behavior Analysis
276(2)
18.4.3 User Needs and Information Presentation
278(1)
18.4.4 System Architecture and Overview
279(1)
18.4.5 System Evaluation and Data Ground Truthing
280(1)
Reference
281(2)
Glossary 283(4)
Appendix A User Interface and Usage Scenario 287(14)
Appendix B Database Tables Related to F4K Workflow 301(2)
Appendix C F4K Database Schema 303(12)
Index 315
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97833193020892e.html
Keywords: