Classification Methods For Remotely Sensed Data

Imbalanced training sets are known to produce suboptimal maps for supervised classification. Therefore, one challenge in mapping land cover is acquiring training data that will allow classification with high overall accuracy (OA) in which each class is also mapped onto similar user’s accuracy. To solve this problem, we integrated local adaptive region and box-and-whisker plot (BP) techniques into an iterative algorithm to expand the size of the training sample for selected classes in this article. The major steps of the proposed algorithm are as follows. First, a very small initial training sample (ITS) for each class set is labeled manually. Second, potential new training samples are found within an adaptive region by conducting local spectral variation analysis. Lastly, three new training samples are acquired to capture information regarding intraclass variation; these samples lie in the lower, median, and upper quartiles of BP. After adding these new training samples to the ITS, classification is retrained and the process is continued iteratively until termination. The proposed approach was applied to three very high-resolution (VHR) remote-sensing images and compared with a set of cognate methods. The comparison demonstrated that the proposed approach produced the best result in terms of OA and exhibited superiority in balancing user’s accuracy. For example, the proposed approach was typically 2%-10% more accurate than the compared methods in terms of OA and it generally yielded the most balanced classification.

/pdf/iterative-training-sample-expansion-to-increase-and-balance-w862h7ehtc.pdf

Iterative Training Sample Expansion to Increase and Balance the Accuracy of Land Classification From VHR Imagery

Remote sensing is the method used to detect and measure target characteristics using electromagnetic energy in the form of heat, light and radio waves. Different applications where remote sensing is used are agriculture, disaster management, urban planning, water resource management, etc. The process of producing thematic map from remotely sensed imagery is called image classification. In one or more spectral bands digital numbers are used to represent spectral information. This information is used for digital image classification. Individual pixels are classified using this spectral information. For classification multispectral satellite images are used. Image classification can be supervised and unsupervised. The paper deals with the supervised classifiers namely minimum distance, support vector machine, maximum likelihood, and parallelepiped. The performance of these classifiers is judged on the basis of kappa coefficient and overall accuracy.

Supervised classification of satellite images

Advancements and new techniques in information technologies are making it possible to manage, analyze and present large-scale environmental modeling results and spatial data acquired from various sources. However, it is a major challenge to make this data accessible because of its unstructured, incomplete and varied nature. Extracting information and making accurate inferences from various data sources rapidly is critical for natural disaster preparedness and response. Critical information about disasters needs to be provided in a structured and easily accessible way in a context-specific manner. This paper introduces a group of information-centric ontologies that encompass the flood domain and describes how they can be benefited to access, analyze, and visualize flood-related data with natural language queries. The presented methodology enables the easy integration of domain knowledge into expert systems and voice-enabled intelligent applications that can be accessed through web-based information platforms, instant messaging apps, automated workflow systems, home automation devices, and augmented and virtual reality platforms. A case study is described to demonstrate the usage of presented ontologies in such intelligent systems.

https://par.nsf.gov/servlets/purl/10192015

Towards an information centric flood ontology for information management and communication

Satellite image classification has a vital role for the extraction and analysis of the useful satellite image information. This paper comprises the study of the satellite images classification and Remote Sensing along with a brief overview of the previous studies that are proposed in this field. In this paper, the existing work has been explained utilizing the classification techniques on satellite images of Alwar region in India that covers decent land cover features like Vegetation, Water, Urban, Barren, and Rocky regions. The post- implementation of the classification algorithms, the classified image is obtained displaying different classes that are represented by different colours. Each feature is represented by a different colour and can be easily perceived from the image obtained after classification. The focus of this study is on enhancing the classification accuracy by using proper classifiers along with the novel feature extraction techniques and pre-processing steps. Work of different authors is being discussed in a tabular form defining the methods and outcomes of the respective studies.

/pdf/a-review-of-remotely-sensed-satellite-image-classification-3jkm01017n.pdf

A review of remotely sensed satellite image classification

Satellite image classification process involves grouping the image pixel values into meaningful categories Several satellite image classification methods and techniques are available Satellite image classification methods can be broadly classified into three categories 1) automatic 2) manual and 3) hybrid All three methods have their own advantages and disadvantages Majority of the satellite image classification methods fall under first category Satellite image classification needs selection of appropriate classification method based on the requirements The current research work is a study on satellite image classification methods and techniques The research work also compares various researcher’s comparative results on satellite image classification methods

https://research.ijcaonline.org/volume119/number8/pxc3903779.pdf

Satellite Image Classification Methods and Techniques: A Review

The data from pre, post and during disasters play a very important and vital role while immediate decision making in emergency management. Data availability, analysis, and exchange build up a critical knowledge base that helps in taking the right decision at the right time. Voluminous data is available through various sources in heterogeneous formats. It is a very big challenge for utilization of such massive heterogeneous data in disaster management situations. Disaster data is widely available in various documents and formats. Past disasters, anticipated disasters and during the disasters, a large amount of data is getting exchanged in various documents between different agencies. Effective techniques to extract and gather the data from heterogeneous documents helps in right data extraction and build up a knowledge base to formulate ease of analysis and modeling. Ontology based semantic technology is a powerful mechanism that supports information integration, exchange, share, reuse and build a knowledge base from heterogeneous information sources. The current research work focuses on three aspects of knowledge base system for effective disaster management. The current research work implemented a mechanism to extract relevant information from semi-structured and structured heterogeneous documents using NLP, representing extracted information in homogeneous and machine understandable format using RDF and map the RDF triples to appropriate concepts of the disaster management domain ontologies. This is very novel and effective means of data usage mechanism to help and guide policy makers, disaster mitigation agencies and society at large.

Ontology and NLP support for building disaster knowledge base

Abstract Ontology is a formal, explicit specification of a shared conceptualization. Ontology provides domain vocabulary, domain knowledge, common understanding, shareability, information interoperability, reusability, concept hierarchy, and relationships that support semantic information retrieval. Ontology improves performance of the system by addressing interoperability issues due to semantic and syntactic heterogeneity. Vast numbers of application domain experts are using ontologies in diverse applications. Use of effective and efficient ontology storage system results improved performance in applications and enables semantic information retrieval. Many prominent researchers and software agencies have proposed and developed several ontology storage methods and tools with various features. The choice of a specific storage model/tool always depend on the specific purpose of the application and the nature of features that are available in the storage model/tool to be utilized in the specific applications. The familiarity of various ontology storage models and tools with the respective features helps user to choose an appropriate storage structure aiming at high-performance applications. The current research work is a comprehensively authentic study carryout out on various ontology storage models and tools with their respective features, which are very essential for optimum performance.

Ontology Storage Models and Tools: An Authentic Survey

The capability of semantic technology leads to adaption of semantic technology to multiple applications of various domains. Due to vast number of applications, the size of RDF triple store is increasing. Effective semantic query execution has become a challenge due to the structure of RDF triple store. Effective indexing and partitioning leads to good sematic query performance against RDF triple store. The current research work has focused on various indexing techniques and proposed a predicate centric partitioning and multiple RDF indexing method for database triple store. A detailed analysis process is been executed to measure and compare the query performance. The current method is evaluated using standard benchmark and real datasets with various indexing techniques. Later the methodology is applied to R&D project management dataset. A set of twenty seven queries has been derived by considering various user requirements that cover most of the SPARQL constructs. The method is implemented and a detailed evaluation has been successfully carried out. The query time is evaluated on R&D project management dataset. The test results indicate that the proposed method provides considerable improvement in overall query performance.

/pdf/effective-partitioning-and-multiple-rdf-indexing-for-106b5pz271.pdf

Effective Partitioning and Multiple RDF Indexing for Database Triple Store

The advancement of technology in the area of satellite remote sensing has been generating voluminous amount of satellite images at regular intervals regularly The satellite image analysis derive very useful, invaluable and essential inputs for various applications such as disaster management, civil aviation, meteorology, ocean observation systems, earth science studies and defense applications, etc The satellite image analysis technique provides the necessary inputs for image preprocessing systems as a basic prerequisite and essential ingredient Over the past several years many satellite image preprocessing tools have been developed with various features The choice of satellite image preprocessing tools basically depend on the purpose of image analysis, the features of satellite image preprocessing tools and the specific need and application Due to a large number of applications of satellite images, user has a wide ranging choice to select optimally the right preprocessing tool for the right application Thus, the present study helps in aiding the proper understanding and selection of the various satellite image preprocessing tools and their features for any specific application To facilitate this scheme, the current study has identified various satellite image preprocessing tools and prominent features of the desired tool Briefly, the study presents a clear understanding with specific examples on the various available tools and features for the user specific application for the desired satellite images The various features of the satellite image preprocessing tools have been presented in detail for ready reference, guidance and usage

/pdf/an-engineering-evaluation-on-the-glimpse-of-satellite-image-22ar1s982w.pdf

Suresh Babu Golla

Papers

Satellite Image Classification Methods and Techniques: A Review

Ontology and NLP support for building disaster knowledge base

Ontology Storage Models and Tools: An Authentic Survey

Effective Partitioning and Multiple RDF Indexing for Database Triple Store

An Engineering Evaluation on the Glimpse of Satellite Image Pre-processing Utility Tools