A Two-Stream Unified Interpretation Network for Heterogeneous Remote Sensing Images Classification

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Modelling species distributions with remote sensing data: bridging disciplinary perspectives

Recently, low-rank representation (LRR) methods have been widely applied for hyperspectral anomaly detection, due to their potentials in separating the backgrounds and anomalies. However, existing LRR models generally convert 3-D hyperspectral images (HSIs) into 2-D matrices, inevitably leading to the destruction of intrinsic 3-D structure properties in HSIs. To this end, we propose a novel tensor low-rank and sparse representation (TLRSR) method for hyperspectral anomaly detection. A 3-D TLR model is expanded to separate the LR background part represented by a tensorial background dictionary and corresponding coefficients. This representation characterizes the multiple subspace property of the complex LR background. Based on the weighted tensor nuclear norm and the LF,1 sparse norm, a dictionary is designed to make its atoms more relevant to the background. Moreover, a principal component analysis (PCA) method can be assigned as one preprocessing step to exact a subset of HSI bands, retaining enough the HSI object information and reducing computational time of the postprocessing tensorial operations. The proposed model is efficiently solved by the well-designed alternating direction method of multipliers (ADMMs). A comparison with the existing algorithms via experiments establishes the competitiveness of the proposed method with the state-of-the-art competitors in the hyperspectral anomaly detection task.

Structure-Constrained Low-Rank and Partial Sparse Representation with Sample Selection for image classification

The low rank and sparse representation (LRSR) technique has attracted increasing attention for hyperspectral anomaly detection (HAD). Although a large quantity of research based on LRSR for HAD is proposed, the detection performance is still limited, due to the unsatisfactory dictionary construction and insufficient consideration of global and local characteristics. To tackle the above-mentioned concern, a novel HAD method, termed dual collaborative constraints regularized low-rank and sparse representation via robust dictionaries construction, is proposed in this article. Concretely, a robust dictionary construction strategy, which thoroughly excavates the potential of the density estimation model and local outlier factor, is proposed to yield pure and representative dictionary atoms. To fully exploit the global and local characteristics of hyperspectral images, dual collaborative constraints corresponding to the background and anomaly components are imposed on the LRSR model. Notably, two weighted matrices are further exerted on the representation coefficients to improve the effect of collaborative constraints, considering the fact that the surrounding pixels similar to the testing pixel should be given a large weight, otherwise the weight is expected to be small. In this way, the background and anomaly components can be well modeled. Additionally, a nonlinear transformation operation, which combines the output of the density estimation model and local outlier factor with the detection result derived from the LRSR model, is developed to suppress the background. The experiments conducted on one simulated dataset and three real datasets demonstrate the superiority of the proposed method compared with the four typical methods and four state-of-the-art methods.

With the rapid development of the remote sensing monitoring and computer vision technology, the deep learning method has made a great progress to achieve applications such as earth observation, climate change and even space exploration. However, the model trained on existing data cannot be directly used to handle the new remote sensing data, and labeling the new data is also time-consuming and labor-intensive. Unsupervised Domain Adaptation (UDA) is one of the solutions to the aforementioned problems of labeled data defined as the source domain and unlabeled data as the target domain, i.e., its essential purpose is to obtain a well-trained model and tackle the problem of data distribution discrepancy defined as the domain shift between the source and target domain. There are a lot of reviews that have elaborated on UDA methods based on natural data, but few of these studies take into consideration thorough remote sensing applications and contributions. Thus, in this paper, in order to explore the further progress and development of UDA methods in remote sensing, based on the analysis of the causes of domain shift, a comprehensive review is provided with a fine-grained taxonomy of UDA methods applied for remote sensing data, which includes Generative training, Adversarial training, Self-training and Hybrid training methods, to better assist scholars in understanding remote sensing data and further advance the development of methods. Moreover, remote sensing applications are introduced by a thorough dataset analysis. Meanwhile, we sort out definitions and methodology introductions of partial, open-set and multi-domain UDA, which are more pertinent to real-world remote sensing applications. We can draw the conclusion that UDA methods in the field of remote sensing data are carried out later than those applied in natural images, and due to the domain gap caused by appearance differences, most of methods focus on how to use generative training (GT) methods to improve the model’s performance. Finally, we describe the potential deficiencies and further in-depth insights of UDA in the field of remote sensing.

Since the National Bridge Inventory (NBI) was first conducted, structural health monitoring (SHM) of U.S. bridge infrastructure has consisted largely of time and labor-intensive surveys with subjective results. In-situ and embedded sensors, while more reliable and accurate, can be costly and in many cases infeasible for SHM because they require installation in hard-to-reach places or during construction. Remote sensing (RS) technologies such as radar, electrooptical imaging and laser scanning may offer an innovative, cost-effective method of monitoring the dynamic conditions of U.S. bridges in real-time. While some RS techniques may be costly for state agencies to deploy on their own, RS imagery is available through government agencies or commercial vendors for moderate or no cost. How can disparate RS datasets be integrated with one another and with inventory data in a way that is meaningful to bridge asset management decision makers? This paper discusses the development and functionality of the Bridge Condition Decision Support System (DSS), a web-based asset management tool for bridge managers and inspectors. The DSS seamlessly merges bridge metrics from RS data with NBI inventory data allowing decision makers to compare up-to-date bridge condition metrics from multiple inputs as a time series. It enables analysis of RS and inventory data available through user-friendly web services which can also expose virtually unlimited server-side data processing. Using open-source software, the authors developed a scalable, spatially-aware bridge condition database with a fast and flexible server application programming interface (API) and a cross-browser compatible web mapping application written in Javascript.

Remote Sensing, Geospatial Technologies and Coastal Ecosystems.- Remote Sensing, Geospatial Technologies and Coastal Ecosystems.- Conceptual and Technical Issues.- Sensors and Techniques for Observing Coastal Ecosystems.- Geographic Information Systems and Spatial Analysis for Coastal Ecosystem Research and Management.- Fuzzy Approach for Integrated Coastal Zone Management.- Spatial Data Infrastructures for Coastal Environments.- Remote Sensing of Coastal Waters.- Airborne Remote Sensing of Chlorophyll in Chesapeake Bay, USA.- Bio-Optical Characteristics and Remote Sensing in the Mid Chesapeake Bay Through Integration of Observations and Radiative Transfer Closure.- Mapping Submerged Aquatic Vegetation and Benthic Habitats.- High-Resolution Ocean Color Remote Sensing of Coral Reefs and Associated Benthic Habitats.- An Integrated Approach to Benthic Habitat Mapping Using Remote Sensing and GIS: An Example from the Hawaiian Islands.- Assessment of the Abundance of Submersed Aquatic Vegetation (SAV) Communities in the Chesapeake Bay and its Use in SAV Management.- Distribution and Spatial Change of Hudson River Estuary Submerged Aquatic Vegetation: Implications for Coastal Management and Natural Resource Protection.- Mapping Marine Macrophytes along the Atlantic Coast of Tierra Del Fuego (Argentina) by Remote Sensing.- Shoreline Change, Coastal Wetland and Watershed Characterization.- Shoreline Mapping and Coastal Change Studies Using Remote Sensing Imagery and LIDAR Data.- Remote Sensing of Coastal Mangrove Forest.- Remote Sensing Support for Tidal Wetland Vegetation Research and Management.- Assessment of Coastal-Vegetation Habitats Using Airborne Laser Remote Sensing.- Measuring Habitat Changes in Barrier Island Marshes: An Example from Southeastern North Carolina, USA.- Mapping Fire Scars and Marsh Recovery with Remote Sensing Data.- Response of Reed Mudflats in the Caspian Coastal Zone to Sea Level Fluctuations.- Integrating Satellite Imagery and Geospatial Technologies for Coastal Landscape Pattern Characterization.- Integrated Coastal Ecosystem Assessment.- Remote Sensing and Spatial Analysis of Watershed and Estuarine Processes for Conservation Planning in Elkhorn Slough, Monterey County, California.- Runoff Water Quality, Landuse and Environmental Impacts on the Bellairs Fringing Reef, Barbados.

Data clustering is an important research topic in data mining and signal processing communications. In all the data clustering methods, the subspace spectral clustering methods based on self expression model, e.g., the Sparse Subspace Clustering (SSC) and the Low Rank Representation (LRR) methods, have attracted a lot of attention and shown good performance. The key step of SSC and LRR is to construct a proper affinity or similarity matrix of data for spectral clustering. Recently, Laplacian graph constraint was introduced into the basic SSC and LRR and obtained considerable improvement. However, the current graph construction methods do not well exploit and reveal the non-linear properties of the clustering data, which is common for high dimensional data. In this paper, we introduce the classic manifold learning method, the Local Linear Embedding (LLE), to learn the non-linear structure underlying the data and use the learned local geometry of manifold as a regularization for SSC and LRR, which results the proposed LLE-SSC and LLE-LRR clustering methods. Additionally, to solve the complex optimization problem involved in the proposed models, an efficient algorithm is also proposed. We test the proposed data clustering methods on several types of public databases. The experimental results show that our methods outperform typical subspace clustering methods with Laplacian graph constraint.

Remote sensing and geographical information science (GIS) have advanced considerably in recent years. However, the potential of remote sensing and GIS within the environmental sciences is limited by uncertainty, especially in connection with the data sets and methods used. In many studies, the issue of uncertainty has been incompletely addressed. The situation has arisen in part from a lack of appreciation of uncertainty and the problems it can cause as well as of the techniques that may be used to accommodate it. This book provides general overviews on uncertainty in remote sensing and GIS that illustrate the range of uncertainties that may occur, in addition to describing the means of measuring uncertainty and the impacts of uncertainty on analyses and interpretations made. Uncertainty in Remote Sensing and GIS provides readers with comprehensive coverage of this largely undocumented subject: * Relevant to a broad variety of disciplines including geography, environmental science, electrical engineering and statistics * Covers range of material from base overviews to specific applications * Focuses on issues connected with uncertainty at various points along typical data analysis chains used in remote sensing and GIS Written by an international team of researchers drawn from a variety of disciplines, Uncertainty in Remote Sensing and GIS provides focussed discussions on topics of considerable importance to a broad research and user community. The book is invaluable reading for researchers, advanced students and practitioners who want to understand the nature of uncertainty in remote sensing and GIS, its limitations and methods of accommodating it. Table of Contents: List of Contributors. Foreword. Preface. Uncertainty in Remote Sensing and GIS: Fundamentals (P. M. Atkinson and G. M. Foody). Uncertainty in Remote Sensing (C. E. Woodcock). Toward a Comprehensive View of Uncertainty in Remote Sensing Analysis (J. L. Dungan). On the Ambiguity Induced by a Remote Sensor's PSF (J. F. Manslow and M. S. Nixon) . Pixel Unmixing at the Sub-pixel Scale Based on Land Cover Class Probabilities: Application to Urban Areas (Q. Zhan, M. Molenaar and A. Lucieer). Super-resolution Land Cover Mapping from Remotely-Sensed Imagery using a Hopfield Neural Network (A. J. Tatem, H. G. Lewis, P. M. Atkinson and M. S. Nixon). Uncertainty in Land Cover Mapping from Remotely Sensed Data using Textural Algorithms and Artificial Neural Networks (A. M. Jakomulska and J. P. Radomski). Remote Monitoring of the Impact of ENSO-related Drought on Sabah Rainforest using NOAA AVHRR Middle Infrared Reflectance: Exploring Emissivity Uncertainty (D. S. Boyd, P. C. Phipps, W. J. Duane and G. M. Foody). Land Cover Map 2000 and Meta-data at the Land Parcel Level (G. M. Smith and R. M. F uller). Analysing Uncertainty Propagation in GIS: Why is it not that Simple? (G. B.M. Heuvelink). Managing uncertainty in a Geospatial Model of Biodiversity (A. J. Warren, M. J. Collins, E. A. Johnson and P. F. Ehlers). The Effects of Uncertainty in Deposition Data on Predicting Exceedances of Acidity Critical Loads for Sensitive UK Ecosystems (E. Heywood, J. R. Hall and R. A. Wadsworth). Vertical and Horizontal Spatial Variation of Geostatistical Prediction (A. Wameling). Geostatistical Prediction and Simulation of the Lateral and Vertical Extent of Soil Horizons (B. Warr, I. O. A. Odeh and M. A. Oliver). Increasing the Accuracy of Predictions of Monthly Precipitation in Great Britain using Kriging with an External Drift (C. D. Lloyd). Conditional Simulation Applied to Uncertainty Assessment in DTMs (J. Senegas, M. Schmitt and P. Nonin). Current Status of Uncertainty Issues in Remote Sensing and GIS (G. M. Foody and P. M. Atkinson). Index.

Low-rank representation (LRR) efficiently performs the subspace segmentation and feature extraction from corrupted data. However, there are three disadvantages in existing LRR techniques. First, the inference algorithm of LRR (as a generative model) is computationally expensive. Second, LRR ignores the discriminative information for image classification. Third, although the robust representation is implemented by recovering the low-rank components and the sparse noises, it has been limited due to the constrained assumption that noises is sparse. To solve these problems, and inspired by Denoising Autoencoders (DAE) and Contractive Autoencoders (CAE), this paper proposes a discriminative low-rank representations framework (DLRR) for image classification. We directly learn a discriminative projection dictionary that results in fast inference. Simultaneously, DLRR can obtain a robust representation from any corrupted input. Our implementation of DLRR achieves state-of-the-art results on artificial dataset and dataset of Olivetti Face Patches.

The classification of optical satellite-derived remote sensing images is an important satellite remote sensing application. Due to the wide variety of artificial features and complex ground situations in urban areas, the classification of complex urban features has always been a focus of and challenge in the field of remote sensing image classification. Given the limited information that can be obtained from traditional optical satellite-derived remote sensing data of a classification area, it is difficult to classify artificial features in detail at the pixel level. With the development of technologies, such as satellite platforms and sensors, the data types acquired by remote sensing satellites have evolved from static images to dynamic videos. Compared with traditional satellite-derived images, satellite-derived videos contain increased ground object reflection information, especially information obtained from different observation angles, and can thus provide more information for classifying complex urban features and improving the corresponding classification accuracies. In this paper, first, we analyze urban-area, ground feature characteristics and satellite-derived video remote sensing data. Second, according to these characteristics, we design a pixel-level classification method based on the application of machine learning techniques to video remote sensing data that represents complex, urban-area ground features. Last, we conduct experiments on real data. The test results show that applying the method designed in this paper to classify dynamic, satellite-derived video remote sensing data can improve the classification accuracy of complex features in urban areas compared with the classification results obtained using static, satellite-derived remote sensing image data at the same resolution.

With the rapid development of satellite technology, remote sensing data has entered the era of big data, and the intelligent processing of remote sensing image has been paid more and more attention. Through the semantic research of remote sensing data, the processing ability of remote sensing data is greatly improved. This paper aims to introduce and analyze the research and application progress of remote sensing image satellite data processing from the perspective of semantic. Firstly, it introduces the characteristics and semantic knowledge of remote sensing big data; Secondly, the semantic concept, semantic construction and application fields are introduced in detail; then, for remote sensing big data, the technical progress in the study field of semantic construction is analyzed from four aspects: semantic description and understanding, semantic segmentation, semantic classification and semantic search, focusing on deep learning technology; Finally, the problems and challenges in the four aspects are discussed in detail, in order to find more directions to explore.

Despite the widespread adoption of deep learning models, shallow machine learning (SML) algorithms are still used for image classification due to simplicity, interpretability and efficiency. This study aims to bridge this gap by investigating the robustness dynamics of SML techniques under more complex scenarios, such as adversarial perturbations and geometric transformation. Five popular classification algorithms, including k-nearest neighbour and support vector machines, were employed to build classification models. Methodology involves investigating the robustness of proposed methods, first, on original and corrupted data by utilising benchmark datasets across several image domains. To strengthen the investigation, the models were trained using a new low-rank representation (LRR) strategy. This hybrid model simultaneously addresses two key limitations in classical LRR models: overcoming the sequential learning process and effectively capturing both local and global data structures. By introducing a dual regularisation mechanism, it integrates a k-nearest neighbour graph to preserve local consistency, while a global low-rank constraint ensures coherent data representation. Experimental results reveal significant drops in accuracy of most SML methods, especially under adversarial attacks and geometric transformations, but LRR approach mitigates these effects to a notable extent, boosting performance across data variations. The results also show that the proposed method outperforms state-of-the-art LRR techniques in most experiments.

Low-rank representation (LRR) has recently attracted a great deal of attention due to its pleasing efficacy in exploring low-dimensional subspace structures embedded in data. However, conventional LRR methods simply use Euclidean distance to measure the similarity of samples, ignoring the dynamic structure information of data. Meanwhile, recent studies have shown that a probabilistically motivated distance measurement (called effective distance) can model the dynamic structure information of data. In this paper, we propose an effective distance based LRR (EDLRR)method for representation learning. The proposed EDLRR method can not only represent the dynamic structure of data, but also capture the geometric information in the inherent nonlinear data. Our method mainly uses Effective Distance Computation and Effective Distance based Low-Rank Representation. We evaluate our method on datasets in the task of image classification, with results demonstrating the effectiveness of the method.