| Description |
1 online resource (464 pages) |
| Series |
Advances in Computer Vision and Pattern Recognition |
|
Advances in computer vision and pattern recognition.
|
| Contents |
Intro -- Contents -- 1 Introduction -- 2 Machine Learning Methods for Spatial and Temporal Parameter Estimation -- 2.1 Introduction -- 2.1.1 Remote Sensing as a Diagnostic Tool -- 2.1.2 Data and Model Challenges -- 2.1.3 Goals and Outline -- 2.2 Gap Filling and Multi-sensor Fusion -- 2.2.1 Proposed Approach -- 2.2.2 LMC-GP -- 2.2.3 Data and Setup -- 2.2.4 Results -- 2.3 Distribution Regression for Multiscale Estimation -- 2.3.1 Kernel Distribution Regression -- 2.3.2 Data and Setup -- 2.3.3 Results -- 2.4 Global Parameter Estimation in the Cloud -- 2.4.1 Data and Setup -- 2.4.2 Results |
|
2.5 Conclusions -- References -- 3 Deep Learning for Hyperspectral Image Analysis, Part I: Theory and Algorithms -- 3.1 Introduction -- 3.1.1 History of Deep Learning in Computer Vision -- 3.1.2 History of Deep Learning for HSI Tasks -- 3.1.3 Challenges -- 3.2 Feed-Forward Neural Networks -- 3.2.1 Perceptron -- 3.2.2 Multi-layer Neural Networks -- 3.2.3 Learning and Gradient Computation -- 3.3 Deep Neural Networks -- 3.3.1 Autoencoders -- 3.3.2 Stacked Autoencoders -- 3.3.3 Recurrent Neural Networks -- 3.3.4 Long Short-Term Memory -- 3.4 Convolutional Neural Networks |
|
3.4.1 Building Blocks of CNNs -- 3.4.2 CNN Flavors for HSI -- 3.5 Software Tools for Deep Learning -- 3.6 Conclusion -- References -- 4 Deep Learning for Hyperspectral Image Analysis, Part II: Applications to Remote Sensing and Biomedicine -- 4.1 Introduction -- 4.2 Applications of Hyperspectral Imaging -- 4.2.1 Remote Sensing Case Study: Urban Land Cover Classification -- 4.2.2 Biomedical Application: Tissue Histology -- 4.3 Practical Considerations and Related Work -- 4.3.1 Practical Considerations -- 4.3.2 Related Developments in the Community -- 4.4 Experimental Setup -- 4.4.1 CNNs |
|
4.4.2 RNNs -- 4.4.3 CRNNs -- 4.5 Quantitative and Qualitative Results -- 4.5.1 Remote Sensing Results -- 4.5.2 Biomedical Results -- 4.5.3 Source Code and Data -- 4.6 Design Choices and Hyperparameters -- 4.6.1 Convolutional Layer Hyperparameters -- 4.6.2 Pooling Layer Hyperparameters -- 4.6.3 Training Hyperparameters -- 4.6.4 General Model Hyperparameters -- 4.6.5 Regularization Hyperparameters -- 4.7 Concluding Remarks -- References -- 5 Advances in Deep Learning for Hyperspectral Image Analysis-Addressing Challenges Arising in Practical Imaging Scenarios |
|
5.1 Deep Learning-Challenges presented by Hyperspectral Imagery -- 5.2 Robust Learning with Limited Labeled Data -- 5.2.1 Unsupervised Feature Learning -- 5.2.2 Semi-supervised learning -- 5.2.3 Active learning -- 5.3 Knowledge Transfer Between Sources -- 5.3.1 Transfer Learning and Domain Adaptation -- 5.3.2 Transferring Knowledge-Beyond Classification -- 5.4 Data Augmentation -- 5.5 Future Directions -- References -- 6 Addressing the Inevitable Imprecision: Multiple Instance Learning for Hyperspectral Image Analysis |
| Summary |
This book reviews the state of the art in algorithmic approaches addressing the practical challenges that arise with hyperspectral image analysis tasks, with a focus on emerging trends in machine learning and image processing/understanding. It presents advances in deep learning, multiple instance learning, sparse representation based learning, low-dimensional manifold models, anomalous change detection, target recognition, sensor fusion and super-resolution for robust multispectral and hyperspectral image understanding. It presents research from leading international experts who have made foundational contributions in these areas. The book covers a diverse array of applications of multispectral/hyperspectral imagery in the context of these algorithms, including remote sensing, face recognition and biomedicine. This book would be particularly beneficial to graduate students and researchers who are taking advanced courses in (or are working in) the areas of image analysis, machine learning and remote sensing with multi-channel optical imagery. Researchers and professionals in academia and industry working in areas such as electrical engineering, civil and environmental engineering, geosciences and biomedical image processing, who work with multi-channel optical data will find this book useful. Dr. Saurabh Prasad is an Associate Professor at the Department of Electrical and Computer Engineering at the University of Houston, TX, USA. Dr. Jocelyn Chanussot is a Professor in the Signal and Images Department at Grenoble Institute of Technology, France |
| Notes |
6.1 Motivating Examples for Multiple Instance Learning in Hyperspectral Analysis |
|
Print version record |
| Subject |
Hyperspectral imaging.
|
|
Image processing.
|
|
image processing.
|
|
Artificial intelligence.
|
|
Geographical information systems (GIS) & remote sensing.
|
|
Imaging systems & technology.
|
|
Image processing.
|
|
Computers -- Intelligence (AI) & Semantics.
|
|
Technology & Engineering -- Remote Sensing & Geographic Information Systems.
|
|
Technology & Engineering -- Electronics -- General.
|
|
Computers -- Computer Graphics.
|
|
Hyperspectral imaging
|
|
Image processing
|
| Form |
Electronic book
|
| Author |
Prasad, Saurabh, 1980-
|
|
Chanussot, Jocelyn.
|
| ISBN |
3030386171 |
|
9783030386177 |
|
