Author: Mohammad Rezaee Publisher: ISBN: Category : Languages : en Pages : 0
Book Description
The incorporation of spatial and spectral information within multispectral satellite images is the key for accurate land cover mapping, specifically for discrimination of heterogeneous land covers. Traditional methods only use basic features, either spatial features (e.g. edges or gradients) or spectral features (e.g. mean value of Digital Numbers or Normalized Difference Vegetation Index (NDVI)) for land cover classification. These features are called low level features and are generated manually (through so-called feature engineering). Since feature engineering is manual, the design of proper features is time-consuming, only low-level features in the information hierarchy can usually be extracted, and the feature extraction is application-based (i.e., different applications need to extract different features). In contrast to traditional land-cover classification methods, Deep Learning (DL),adapting the artificial neural network (ANN) into a deep structure, can automatically generate the necessary high-level features for improving classification without being limited to low-level features. The higher-level features (e.g. complex shapes and textures) can be generated by combining low-level features through different level of processing. However, despite recent advances of DL for various computer vision tasks, especially for convolutional neural networks (CNNs) models, the potential of using DL for land-cover classification of multispectral remote sensing (RS) images have not yet been thoroughly explored. The main reason is that a DL network needs to be trained using a huge number of images from a large scale of datasets. Such training datasets are not usually available in RS. The only few available training datasets are either for object detection in an urban area, or for scene labeling. In addition, the available datasets are mostly used for land-cover classification based on spatial features. Therefore, the incorporation of the spectral and spatial features has not been studied comprehensively yet. This PhD research aims to mitigate challenges in using DL for RS land cover mapping/object detection by (1) decreasing the dependency of DL to the large training datasets, (2) adapting and improving the efficiency and accuracy of deep CNNs for heterogeneous classification, (3) incorporating all of the spectral bands in satellite multispectral images into the processing, and (4) designing a specific CNN network that can be used for a faster and more accurate detection of heterogeneous land covers with fewer amount of training datasets. The new developments are evaluated in two case studies, i.e. wetland detection and tree species detection, where high resolution multispectral satellite images are used. Such land-cover classifications are considered as challenging tasks in the literature. The results show that our new solution works reliably under a wide variety of conditions. Furthermore, we are releasing the two large-scale wetland and tree species detection datasets to the public in order to facilitate future research, and to compare with other methods.
Author: Nagesh Kumar Uba Publisher: ISBN: Category : Land use Languages : en Pages : 44
Book Description
Large datasets of sub-meter aerial imagery represented as orthophoto mosaics are widely available today, and these data sets may hold a great deal of untapped information. This imagery has a potential to locate several types of features; for example, forests, parking lots, airports, residential areas, or freeways in the imagery. However, the appearances of these things vary based on many things including the time that the image is captured, the sensor settings, processing done to rectify the image, and the geographical and cultural context of the region captured by the image. This thesis explores the use of deep convolutional neural networks to classify land use from very high spatial resolution (VHR), orthorectified, visible band multispectral imagery. Recent technological and commercial applications have driven the collection a massive amount of VHR images in the visible red, green, blue (RGB) spectral bands, this work explores the potential for deep learning algorithms to exploit this imagery for automatic land use/ land cover (LULC) classification. The benefits of automatic visible band VHR LULC classifications may include applications such as automatic change detection or mapping. Recent work has shown the potential of Deep Learning approaches for land use classification; however, this thesis improves on the state-of-the-art by applying additional dataset augmenting approaches that are well suited for geospatial data. Furthermore, the generalizability of the classifiers is tested by extensively evaluating the classifiers on unseen datasets and we present the accuracy levels of the classifier in order to show that the results actually generalize beyond the small benchmarks used in training. Deep networks have many parameters, and therefore they are often built with very large sets of labeled data. Suitably large datasets for LULC are not easy to come by, but techniques such as refinement learning allow networks trained for one task to be retrained to perform another recognition task. Contributions of this thesis include demonstrating that deep networks trained for image recognition in one task (ImageNet) can be efficiently transferred to remote sensing applications and perform as well or better than manually crafted classifiers without requiring massive training data sets. This is demonstrated on the UC Merced dataset, where 96% mean accuracy is achieved using a CNN (Convolutional Neural Network) and 5-fold cross validation. These results are further tested on unrelated VHR images at the same resolution as the training set.
Author: Mohammad Awrangjeb Publisher: MDPI ISBN: 3039283820 Category : Science Languages : en Pages : 442
Book Description
Building extraction from remote sensing data plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. Even though significant research has been carried out for more than two decades, the success of automatic building extraction and modeling is still largely impeded by scene complexity, incomplete cue extraction, and sensor dependency of data. Most recently, deep neural networks (DNN) have been widely applied for high classification accuracy in various areas including land-cover and land-use classification. Therefore, intelligent and innovative algorithms are needed for the success of automatic building extraction and modeling. This Special Issue focuses on newly developed methods for classification and feature extraction from remote sensing data for automatic building extraction and 3D
Author: Yuanming Shu Publisher: ISBN: Category : Languages : en Pages : 119
Book Description
Developing methods to automatically extract objects from high spatial resolution (HSR) remotely sensed imagery on a large scale is crucial for supporting land user and land cover (LULC) mapping with HSR imagery. However, this task is notoriously challenging. Deep learning, a recent breakthrough in machine learning, has shed light on this problem. The goal of this thesis is to develop a deep insight into the use of deep learning to develop reliable automated object extraction methods for applications with HSR imagery. The thesis starts by re-examining the knowledge the remote sensing community has achieved on the problem, but in the context of deep learning. Attention is given to object-based image analysis (OBIA) methods, which are currently considered to be the prevailing framework for this problem and have had a far-reaching impact on the history of remote sensing. In contrast to common beliefs, experiments show that object-based methods suffer seriously from ill-defined image segmentation. They are less effective at leveraging the power of the features learned by deep convolutional neural networks (CNNs) than conventionally patch-based methods. This thesis then studies ways to further improve the accuracy of object extraction with deep CNNs. Given that vector maps are required as the final format in many applications, the focus is on addressing the issues of generating high-quality vector maps with deep CNNs. A method combining bottom-up deep CNN prediction with top-down object modeling is proposed for building extraction. This method also exhibits the potential to extend to other objects of interest. Experiments show that implementing the proposed method on a single GPU results in the capability of processing 756 km2 of 12 cm aerial images in about 30 hours. By post-editing on top of the resulting automated extraction, high-quality building vector maps can be produced about 4-times faster than conventional manual digitization methods.
Author: Linmi Tao Publisher: Springer Nature ISBN: 9813344202 Category : Computers Languages : en Pages : 207
Book Description
This book focuses on deep learning-based methods for hyperspectral image (HSI) analysis. Unsupervised spectral-spatial adaptive band-noise factor-based formulation is devised for HSI noise detection and band categorization. The method to characterize the bands along with the noise estimation of HSIs will benefit subsequent remote sensing techniques significantly. This book develops on two fronts: On the one hand, it is aimed at domain professionals who want to have an updated overview of how hyperspectral acquisition techniques can combine with deep learning architectures to solve specific tasks in different application fields. On the other hand, the authors want to target the machine learning and computer vision experts by giving them a picture of how deep learning technologies are applied to hyperspectral data from a multidisciplinary perspective. The presence of these two viewpoints and the inclusion of application fields of remote sensing by deep learning are the original contributions of this review, which also highlights some potentialities and critical issues related to the observed development trends.
Author: Haibo He Publisher: John Wiley & Sons ISBN: 1118646339 Category : Technology & Engineering Languages : en Pages : 222
Book Description
The first book of its kind to review the current status and future direction of the exciting new branch of machine learning/data mining called imbalanced learning Imbalanced learning focuses on how an intelligent system can learn when it is provided with imbalanced data. Solving imbalanced learning problems is critical in numerous data-intensive networked systems, including surveillance, security, Internet, finance, biomedical, defense, and more. Due to the inherent complex characteristics of imbalanced data sets, learning from such data requires new understandings, principles, algorithms, and tools to transform vast amounts of raw data efficiently into information and knowledge representation. The first comprehensive look at this new branch of machine learning, this book offers a critical review of the problem of imbalanced learning, covering the state of the art in techniques, principles, and real-world applications. Featuring contributions from experts in both academia and industry, Imbalanced Learning: Foundations, Algorithms, and Applications provides chapter coverage on: Foundations of Imbalanced Learning Imbalanced Datasets: From Sampling to Classifiers Ensemble Methods for Class Imbalance Learning Class Imbalance Learning Methods for Support Vector Machines Class Imbalance and Active Learning Nonstationary Stream Data Learning with Imbalanced Class Distribution Assessment Metrics for Imbalanced Learning Imbalanced Learning: Foundations, Algorithms, and Applications will help scientists and engineers learn how to tackle the problem of learning from imbalanced datasets, and gain insight into current developments in the field as well as future research directions.
Author: Saurabh Prasad Publisher: Springer Nature ISBN: 3030386171 Category : Computers Languages : en Pages : 464
Book Description
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.
Author: Taskin Kavzoglu Publisher: CRC Press ISBN: 104009905X Category : Technology & Engineering Languages : en Pages : 444
Book Description
The third edition of the bestselling Classification Methods for Remotely Sensed Data covers current state-of-the-art machine learning algorithms and developments in the analysis of remotely sensed data. This book is thoroughly updated to meet the needs of readers today and provides six new chapters on deep learning, feature extraction and selection, multisource image fusion, hyperparameter optimization, accuracy assessment with model explainability, and object-based image analysis, which is relatively a new paradigm in image processing and classification. It presents new AI-based analysis tools and metrics together with ongoing debates on accuracy assessment strategies and XAI methods. New in this edition: Provides comprehensive background on the theory of deep learning and its application to remote sensing data. Includes a chapter on hyperparameter optimization techniques to guarantee the highest performance in classification applications. Outlines the latest strategies and accuracy measures in accuracy assessment and summarizes accuracy metrics and assessment strategies. Discusses the methods used for explaining inherent structures and weighing the features of ML and AI algorithms that are critical for explaining the robustness of the models. This book is intended for industry professionals, researchers, academics, and graduate students who want a thorough and up-to-date guide to the many and varied techniques of image classification applied in the fields of geography, geospatial and earth sciences, electronic and computer science, environmental engineering, etc.
Author: Florence Tupin Publisher: John Wiley & Sons ISBN: 1118898923 Category : Technology & Engineering Languages : en Pages : 277
Book Description
Dedicated to remote sensing images, from their acquisition to their use in various applications, this book covers the global lifecycle of images, including sensors and acquisition systems, applications such as movement monitoring or data assimilation, and image and data processing. It is organized in three main parts. The first part presents technological information about remote sensing (choice of satellite orbit and sensors) and elements of physics related to sensing (optics and microwave propagation). The second part presents image processing algorithms and their specificities for radar or optical, multi and hyper-spectral images. The final part is devoted to applications: change detection and analysis of time series, elevation measurement, displacement measurement and data assimilation. Offering a comprehensive survey of the domain of remote sensing imagery with a multi-disciplinary approach, this book is suitable for graduate students and engineers, with backgrounds either in computer science and applied math (signal and image processing) or geo-physics. About the Authors Florence Tupin is Professor at Telecom ParisTech, France. Her research interests include remote sensing imagery, image analysis and interpretation, three-dimensional reconstruction, and synthetic aperture radar, especially for urban remote sensing applications. Jordi Inglada works at the Centre National d’Études Spatiales (French Space Agency), Toulouse, France, in the field of remote sensing image processing at the CESBIO laboratory. He is in charge of the development of image processing algorithms for the operational exploitation of Earth observation images, mainly in the field of multi-temporal image analysis for land use and cover change. Jean-Marie Nicolas is Professor at Telecom ParisTech in the Signal and Imaging department. His research interests include the modeling and processing of synthetic aperture radar images.
Author: Zhuo Chen Publisher: ISBN: Category : Land cover Languages : en Pages : 98
Book Description
With the spread of urban culture, urbanisation is progressing rapidly and globally. Accurate and update land cover (LC) information becomes increasingly critical for protecting ecosystems, climate change studies and sustainable human-environment development. It has been verified that combining spectral information from remotely sensed imagery and 3D spatial information from airborne laser scanning (ALS) point clouds has achieved better LC classification accuracy than that obtained by using either of them solely. However, data fusions can introduce multiple errors. To solve this problem, multispectral ALS developed recently is able to acquire point cloud data with multiple spectral channels simultaneously. Moreover, deep neural networks have been proved to be a better option for LC classification than those statistical classification approaches. This study aims to develop a workflow for automated pixel-wise LC classification from multispectral ALS data using deep-learning methods. A total of six input datasets with a multi-tiered architecture and three deep-learning classification networks (i.e. 1D CNN, 2D CNN, and 3D CNN) have been established to seek the optimal scheme that lead to highest classification accuracy. The highest overall classification accuracy of 97.2% has been achieved using the proposed 3D CNN and the designed input dataset. In regard to the proposed CNNs, the overall accuracy (OA) of the 2D and 3D CNNs was, on average, 8.4% higher than that of the 1D CNN. Although the OA of the 2D CNN was at most 0.3% lower than that of the 3D CNN, the run time of the 3D CNN was five times longer than the 2D CNN. Thus, the 2D CNN was the best choice for the multispectral ALS LC classification when considering efficiency. For different input datasets, the OA of the designed input datasets was, on average, 3.8% higher than that of the classic input datasets. Results also showed that the multispectral ALS data is superior to both multispectral optical imagery and single-wavelength ALS data for LC classification. In conclusion, this thesis suggests that LC classification can be improved with the use of multispectral ALS data and deep-learning methods.
Author: Mohammad Rezaee
Author: Nagesh Kumar Uba
Author: Mohammad Awrangjeb
Author: Yuanming Shu
Author: Linmi Tao
Author: Haibo He
Author: Saurabh Prasad
Author: Taskin Kavzoglu
Author: Florence Tupin
Author: Zhuo Chen