{"product_id":"change-detection-and-image-time-series-analysis-2-supervised-methods-hardback-9781789450576","title":"Change Detection and Image Time Series Analysis 2; Supervised Methods (Hardback) 9781789450576","description":"\u003cfont face=\"Georgia\"\u003e\r\n\u003cp\u003e\u003cfont size=\"6\"\u003eChange Detection and Image Time Series Analysis 2\u003c\/font\u003e\u003cbr\u003e\r\n\u003cfont size=\"5\"\u003eSupervised Methods\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\u003cp\u003e\u003cfont size=\"4\"\u003eAbdourrahmane M. Atto (Edited by), A Atto (Author), Francesca Bovolo (Edited by), Lorenzo Bruzzone (Edited by)\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e9781789450576, Wiley\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eHardback, published 4 January 2022\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e272 pages\u003cbr\u003e1 x 1 x 1 cm, 0.454 kg\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\r\n\u003cp align=\"justify\"\u003e\u003cstrong\u003e\u003cfont size=\"3\"\u003e\u003ci\u003eChange Detection and Image Time Series Analysis 2\u003c\/i\u003e presents supervised machine-learning-based methods for temporal evolution analysis by using image time series associated with Earth observation data. Chapter 1 addresses the fusion of multisensor, multiresolution and multitemporal data. It proposes two supervised solutions that are based on a Markov random field: the first relies on a quad-tree and the second is specifically designed to deal with multimission, multifrequency and multiresolution time series.\u003cbr\u003e\u003cbr\u003eChapter 2 provides an overview of pixel based methods for time series classification, from the earliest shallow learning methods to the most recent deep-learning-based approaches.\u003cbr\u003e\u003cbr\u003eChapter 3 focuses on very high spatial resolution data time series and on the use of semantic information for modeling spatio-temporal evolution patterns.\u003cbr\u003e\u003cbr\u003eChapter 4 centers on the challenges of dense time series analysis, including pre processing aspects and a taxonomy of existing methodologies. Finally, since the evaluation of a learning system can be subject to multiple considerations,\u003cbr\u003e\u003cbr\u003eChapters 5 and 6 offer extensive evaluations of the methodologies and learning frameworks used to produce change maps, in the context of multiclass and\/or multilabel change classification issues.\u003c\/font\u003e\u003c\/strong\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e\u003cp\u003eContents\u003c\/p\u003e \u003cp\u003ePreface ix\u003c\/p\u003e \u003cp\u003eAbdourrahmane M. ATTO, Francesca BOVOLO and Lorenzo BRUZZONE\u003c\/p\u003e \u003cp\u003eList of Notations\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 Hierarchical Markov Random Fields for High Resolution Land Cover Classification of Multisensor and Multiresolution Image Time Series 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIhsen HEDHLI, Gabriele MOSER, Sebastiano B. SERPICO\u003c\/p\u003e \u003cp\u003eand Josiane ZERUBIA\u003c\/p\u003e \u003cp\u003e1.1. Introduction 1\u003c\/p\u003e \u003cp\u003e1.1.1. The role of multisensor data in time series classification 1\u003c\/p\u003e \u003cp\u003e1.1.2. Multisensor and multiresolution classification 2\u003c\/p\u003e \u003cp\u003e1.1.3.Previouswork 5\u003c\/p\u003e \u003cp\u003e1.2. Methodology 9\u003c\/p\u003e \u003cp\u003e1.2.1. Overview of the proposed approaches 9\u003c\/p\u003e \u003cp\u003e1.2.2. Hierarchical model associated with the first proposed method 10\u003c\/p\u003e \u003cp\u003e1.2.3. Hierarchical model associated with the second proposed method 13\u003c\/p\u003e \u003cp\u003e1.2.4. Multisensor hierarchical MPM inference 14\u003c\/p\u003e \u003cp\u003e1.2.5. Probability density estimation through finite mixtures 17\u003c\/p\u003e \u003cp\u003e1.3.Examplesofexperimentalresults 19\u003c\/p\u003e \u003cp\u003e1.3.1.Resultsofthefirstmethod 19\u003c\/p\u003e \u003cp\u003e1.3.2.Resultsofthesecondmethod 22\u003c\/p\u003e \u003cp\u003e1.4.Conclusion 26\u003c\/p\u003e \u003cp\u003exiii\u003c\/p\u003e \u003cp\u003e1.5.Acknowledgments 26\u003c\/p\u003e \u003cp\u003e1.6.References 27\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Pixel-based Classification Techniques for Satellite Image Time Series 33\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eCharlotte PELLETIER and Silvia VALERO\u003c\/p\u003e \u003cp\u003e2.1. Introduction 33\u003c\/p\u003e \u003cp\u003e2.2. Basic concepts in supervised remote sensing classification 35\u003c\/p\u003e \u003cp\u003e2.2.1. Preparing data before it is fed into classification algorithms 35\u003c\/p\u003e \u003cp\u003e2.2.2. Key considerations when training supervised classifiers 39\u003c\/p\u003e \u003cp\u003e2.2.3. Performance evaluation of supervised classifiers 41\u003c\/p\u003e \u003cp\u003e2.3.Traditionalclassificationalgorithms 45\u003c\/p\u003e \u003cp\u003e2.3.1. Support vector machines 45\u003c\/p\u003e \u003cp\u003e2.3.2. Random forests 51\u003c\/p\u003e \u003cp\u003e2.3.3. k-nearest neighbor 56\u003c\/p\u003e \u003cp\u003e2.4. Classification strategies based on temporal feature representations 59\u003c\/p\u003e \u003cp\u003e2.4.1. Phenology-based classification approaches 60\u003c\/p\u003e \u003cp\u003e2.4.2 Dictionary-based classificationapproaches 61\u003c\/p\u003e \u003cp\u003e2.4.3 Shapelet-based classificationapproaches 62\u003c\/p\u003e \u003cp\u003e2.5.Deeplearningapproaches 63\u003c\/p\u003e \u003cp\u003e2.5.1. Introduction to deep learning 64\u003c\/p\u003e \u003cp\u003e2.5.2.Convolutionalneuralnetworks 68\u003c\/p\u003e \u003cp\u003e2.5.3.Recurrentneuralnetworks 71\u003c\/p\u003e \u003cp\u003e2.6.References 75\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Semantic Analysis of Satellite Image Time Series 85\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eCorneliu Octavian DUMITRU and Mihai DATCU\u003c\/p\u003e \u003cp\u003e3.1. Introduction 85\u003c\/p\u003e \u003cp\u003e3.1.1.TypicalSITSexamples 89\u003c\/p\u003e \u003cp\u003e3.1.2. Irregular acquisitions 90\u003c\/p\u003e \u003cp\u003e3.1.3.Thechapterstructure 96\u003c\/p\u003e \u003cp\u003e3.2.WhyaresemanticsneededinSITS? 96\u003c\/p\u003e \u003cp\u003e3.3.Similaritymetrics 97\u003c\/p\u003e \u003cp\u003e3.4. Feature methods 98\u003c\/p\u003e \u003cp\u003e3.5. Classification methods 98\u003c\/p\u003e \u003cp\u003e3.5.1.Activelearning 99\u003c\/p\u003e \u003cp\u003e3.5.2.Relevancefeedback 100\u003c\/p\u003e \u003cp\u003e3.5.3. Compression-based pattern recognition 100\u003c\/p\u003e \u003cp\u003e3.5.4.LatentDirichletallocation 101\u003c\/p\u003e \u003cp\u003e3.6.Conclusion 102\u003c\/p\u003e \u003cp\u003evii\u003c\/p\u003e \u003cp\u003e3.7.Acknowledgments 105\u003c\/p\u003e \u003cp\u003e3.8.References 105\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Optical Satellite Image Time Series Analysis for Environment Applications: From Classical Methods to Deep Learning and Beyond 109\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eMatthieu MOLINIER, Jukka MIETTINEN,DinoIENCO,ShiQIU and Zhe ZHU\u003c\/p\u003e \u003cp\u003e4.1. Introduction 109\u003c\/p\u003e \u003cp\u003e4.2. Annual time series 111\u003c\/p\u003e \u003cp\u003e4.2.1. Overview of annual time series methods 111\u003c\/p\u003e \u003cp\u003e4.2.2 Examples of annual times series analysis applications for environmentalmonitoring 112\u003c\/p\u003e \u003cp\u003e4.2.3.Towardsdensetimeseriesanalysis 116\u003c\/p\u003e \u003cp\u003e4.3. Dense time series analysis using all available data 117\u003c\/p\u003e \u003cp\u003e4.3.1. Making dense time series consistent 118\u003c\/p\u003e \u003cp\u003e4.3.2. Change detection methods 121\u003c\/p\u003e \u003cp\u003e4.3.3.Summaryandfuturedevelopments 125\u003c\/p\u003e \u003cp\u003e4.4. Deep learning-based time series analysis approaches 126\u003c\/p\u003e \u003cp\u003e4.4.1 Recurrent Neural Network (RNN) for Satellite Image TimeSeries 129\u003c\/p\u003e \u003cp\u003e4.4.2 Convolutional Neural Networks (CNN) for Satellite Image TimeSeries 131\u003c\/p\u003e \u003cp\u003e4.4.3. Hybrid models: Convolutional Recurrent Neural Network (ConvRNN) models for Satellite Image Time Series 134\u003c\/p\u003e \u003cp\u003e4.4.4. Synthesis and future developments 136\u003c\/p\u003e \u003cp\u003e4.5. Beyond satellite image time series and deep learning: convergence between time series and video approaches 136\u003c\/p\u003e \u003cp\u003e4.5.1 Increased image acquisition frequency: from time series to spacebornetime-lapseandvideos 137\u003c\/p\u003e \u003cp\u003e4.5.2. Deep learning and computer vision as technology enablers 138\u003c\/p\u003e \u003cp\u003e4.5.3.Futuresteps 139\u003c\/p\u003e \u003cp\u003e4.6.References 140\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 A Review on Multi-temporal Earthquake Damage Assessment Using Satellite Images 155\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eGülşen TAŞKIN, EsraERTEN and Enes Oğuzhan ALATAŞ\u003c\/p\u003e \u003cp\u003e5.1. Introduction 155\u003c\/p\u003e \u003cp\u003e5.1.1. Research methodology and statistics 159\u003c\/p\u003e \u003cp\u003e5.2. Satellite-based earthquake damage assessment 165\u003c\/p\u003e \u003cp\u003e5.3. Pre-processing of satellite images before damage assessment 167\u003c\/p\u003e \u003cp\u003e5.4. Multi-source image analysis 168\u003c\/p\u003e \u003cp\u003e5.5. Contextual feature mining for damage assessment 169\u003c\/p\u003e \u003cp\u003e5.5.1.Texturalfeatures 170\u003c\/p\u003e \u003cp\u003e5.5.2. Filter-based methods 173\u003c\/p\u003e \u003cp\u003e5.6. Multi-temporal image analysis for damage assessment 175\u003c\/p\u003e \u003cp\u003e5.6.1. Use of machine learning in damage assessment problem 176\u003c\/p\u003e \u003cp\u003e5.6.2. Rapid earthquake damage assessment 180\u003c\/p\u003e \u003cp\u003e5.7. Understanding damage following an earthquake using satellite-based SAR 181\u003c\/p\u003e \u003cp\u003e5.7.1. SAR fundamental parameters and acquisition vector 185\u003c\/p\u003e \u003cp\u003e5.7.2. Coherent methods for damage assessment 188\u003c\/p\u003e \u003cp\u003e5.7.3. Incoherent methods for damage assessment 192\u003c\/p\u003e \u003cp\u003e5.7.4. Post-earthquake-only SAR data-based damage assessment 195\u003c\/p\u003e \u003cp\u003e5.7.5 Combination of coherent and incoherent methods for damage assessment 196\u003c\/p\u003e \u003cp\u003e5.7.6.Summary 198\u003c\/p\u003e \u003cp\u003e5.8. Use of auxiliary data sources 200\u003c\/p\u003e \u003cp\u003e5.9.Damagegrades 200\u003c\/p\u003e \u003cp\u003e5.10.Conclusionanddiscussion 203\u003c\/p\u003e \u003cp\u003e5.11.References 205\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Multiclass Multilabel Change of State Transfer Learning from Image Time Series 223\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eAbdourrahmane M. ATTO,HélaHADHRI, FlavienVERNIER\u003c\/p\u003e \u003cp\u003eand Emmanuel TROUVÉ\u003c\/p\u003e \u003cp\u003e6.1. Introduction 223\u003c\/p\u003e \u003cp\u003e6.2. Coarse- to fine-grained change of state dataset 225\u003c\/p\u003e \u003cp\u003e6.3. Deep transfer learning models for change of state classification 232\u003c\/p\u003e \u003cp\u003e6.3.1.Deeplearningmodellibrary 232\u003c\/p\u003e \u003cp\u003e6.3.2.GraphstructuresfortheCNNlibrary 234\u003c\/p\u003e \u003cp\u003e6.3.3. Dimensionalities of the learnables for the CNN library 236\u003c\/p\u003e \u003cp\u003e6.4.Changeofstateanalysis 237\u003c\/p\u003e \u003cp\u003e6.4.1 Transfer learning adaptations for the change of state classificationissues 238\u003c\/p\u003e \u003cp\u003e6.4.2.Experimentalresults 239\u003c\/p\u003e \u003cp\u003e6.5.Conclusion 243\u003c\/p\u003e \u003cp\u003e6.6.Acknowledgments 244\u003c\/p\u003e \u003cp\u003e6.7.References 244\u003c\/p\u003e \u003cp\u003eList of Authors 247\u003c\/p\u003e \u003cp\u003eIndex 249\u003c\/p\u003e \u003cp\u003eSummary of Volume 1 253\u003c\/p\u003e\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eSubject Areas: Electronics \u0026amp; communications engineering [\u003ca title=\"See our other books on Electronics \u0026amp; communications engineering\" href=\"https:\/\/freshlyprintedbooks.co.uk\/search?q=%22Electronics%20\u0026amp;%20communications%20engineering%20%5BTJ%5D%22\"\u003eTJ\u003c\/a\u003e]\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003c\/font\u003e","brand":"Wiley-ISTE","offers":[{"title":"Brand New","offer_id":52446813159704,"sku":"9781789450576","price":122.19,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0730\/2037\/5320\/files\/9781789450576.jpg?v=1785114497","url":"https:\/\/freshlyprintedbooks.co.uk\/products\/change-detection-and-image-time-series-analysis-2-supervised-methods-hardback-9781789450576","provider":"Freshly Printed Books","version":"1.0","type":"link"}