scholarly journals A new approach to the application of conflict redistribution rule in Satellite Image Classification

2020 ◽  
pp. 12-16
Author(s):  
Sofiia Alpert
Keyword(s):  
Remote Sensing ◽  
Image Classification ◽  
Satellite Images ◽  
Satellite Image ◽  
Classification Methods ◽  
New Approach ◽  
Remote Sensing Classification ◽  
Satellite Image Classification ◽  
Bodies Of Evidence

Nowadays solution of different scientific problems using satellite images, generally includes a classification procedure. Classification is one of the most important procedures used in remote sensing, because it involves a lot of mathematical operations and data preprocessing. The processing of information and combining of conflicting data is a very difficult problem in classification tasks. Nowadays many classification methods are applied in remote sensing. Classification of conflicting data has been a key problem, both from a theoretical and practical point of view. But a lot of known classification methods can not deal with highly conflicted data and uncertainty. The main purpose of this article is to apply proportional conflict redistribution rule (PRC5) for satellite image classification in conditions of uncertainty, when conflicting sources of evidence give incomplete and vague information. This rule can process conflicting data and combine conflicting bodies of evidence (spectral bands). Proportional conflict redistribution rule can redistribute the partial conflicting mass proportionally on non-empty sets involved in the conflict. It was noticed, that this rule can provide a construction of aggregated estimate under conflict. It calculates all partial conflicting masses separately. It was also shown, that proportional conflict redistribution rule is the most mathematically exact redistribution of conflicting mass to non-empty set. But this rule consists of difficult calculation procedures. The more hypotheses and more masses are involved in the fusion, the more difficult is to implement proportional conflict redistribution rule, therefore special computer software should be used. It was considered an example of practical use of the proposed conflict redistribution rule. It also was noticed, that this new approach to the application of conflict redistribution rule in satellite image classification can be applied for analysis of satellite images, solving practical and ecological tasks, assessment of agricultural lands, classification of forests, in searching for oil and gas.

scholarly journals Object-Based and Rule-Based Classification of Synthetic Aperture Radar Images

2019 ◽  
Vol 8 (10) ◽  
pp. 2458-2463
Keyword(s):  
Image Classification ◽  
Satellite Images ◽  
Satellite Image ◽  
Accurate Information ◽  
Barren Land ◽  
Radar Images ◽  
Satellite Image Classification ◽  
Object Based ◽  
Terrain Features

Since thousands of years, the land is the basic and very important requirement for humans to survive and grow. The surface area of the earth provided by nature contains many different geographical locations divided into oceans, mountains, rivers, barren land, fertile land, ice caps and many more. The huge land masses and water bodies need to be observed and analyzed for optimum utilization of resources. Remote sensing is the best possible way to observe the earth's surface from a distance through different satellites and sensors. But most of the satellite images are not clear up to the extent to classify different terrain features accurately. Hence classification of image is needed to observe different terrain features in original images. In this study, the aim is to propose a branch of natural computation for SAR image classification into different terrain features with better information retrieval and accuracy measures as compared to traditional methods for satellite image classification. The object-based analysis has been used to extract spectral reflectance of five texture measures namely urban, rocky, vegetation, water and barren to generate training set. Minimum distance to mean classifier has been used with one of the Nature Inspired computation technique i.e. bacterial foraging optimization algorithm for the satellite image classification, to extract the more accurate information about land area of Alwar district, Rajasthan, India. In the proposed study a high-quality thematic map has been generated with the 7-band multi-spectral, medium-resolution satellite images. This approach provides the greater speed and accuracy in its computation with 97.43% overall accuracy (OA) and 0.96 Kappa co-efficient.

scholarly journals SATELLITE IMAGE CLASSIFICATION OF BUILDING DAMAGES USING AIRBORNE AND SATELLITE IMAGE SAMPLES IN A DEEP LEARNING APPROACH

2018 ◽  
Vol IV-2 ◽  
pp. 89-96 ◽  
Author(s):  
D. Duarte ◽  
F. Nex ◽  
N. Kerle ◽  
G. Vosselman
Keyword(s):  
Remote Sensing ◽  
Image Classification ◽  
Binary Classification ◽  
Satellite Image ◽  
Classification Problem ◽  
Aerial Image ◽  
Management Service ◽  
Feature Maps ◽  
Satellite Image Classification

The localization and detailed assessment of damaged buildings after a disastrous event is of utmost importance to guide response operations, recovery tasks or for insurance purposes. Several remote sensing platforms and sensors are currently used for the manual detection of building damages. However, there is an overall interest in the use of automated methods to perform this task, regardless of the used platform. Owing to its synoptic coverage and predictable availability, satellite imagery is currently used as input for the identification of building damages by the International Charter, as well as the Copernicus Emergency Management Service for the production of damage grading and reference maps. Recently proposed methods to perform image classification of building damages rely on convolutional neural networks (CNN). These are usually trained with only satellite image samples in a binary classification problem, however the number of samples derived from these images is often limited, affecting the quality of the classification results. The use of up/down-sampling image samples during the training of a CNN, has demonstrated to improve several image recognition tasks in remote sensing. However, it is currently unclear if this multi resolution information can also be captured from images with different spatial resolutions like satellite and airborne imagery (from both manned and unmanned platforms). In this paper, a CNN framework using residual connections and dilated convolutions is used considering both manned and unmanned aerial image samples to perform the satellite image classification of building damages. Three network configurations, trained with multi-resolution image samples are compared against two benchmark networks where only satellite image samples are used. Combining feature maps generated from airborne and satellite image samples, and refining these using only the satellite image samples, improved nearly 4 % the overall satellite image classification of building damages.

Classification of EgyptSat-1 Images Using Deep Learning Methods

2020 ◽  
Vol 10 (1) ◽  
pp. 37-46 ◽  
Author(s):  
Hatem Keshk ◽  
Xu-Cheng Yin
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
High Performance ◽  
Satellite Images ◽  
Satellite Image ◽  
Aerial Photographs ◽  
Average Accuracy

Background: Deep Learning (DL) neural network methods have become a hotspot subject of research in the remote sensing field. Classification of aerial satellite images depends on spectral content, which is a challenging topic in remote sensing. Objective: With the aim to accomplish a high performance and accuracy of Egyptsat-1 satellite image classification, the use of the Convolutional Neural Network (CNN) is raised in this paper because CNN is considered a leading deep learning method. CNN is developed to classify aerial photographs into land cover classes such as urban, vegetation, desert, water bodies, soil, roads, etc. In our work, a comparison between MAXIMUM Likelihood (ML) which represents the traditional supervised classification methods and CNN method is conducted. Conclusion: This research finds that CNN outperforms ML by 9%. The convolutional neural network has better classification result, which reached 92.25% as its average accuracy. Also, the experiments showed that the convolutional neural network is the most satisfactory and effective classification method applied to classify Egyptsat-1 satellite images.

scholarly journals GEOSPATIAL MACHINE LEARNING DATASETS STRUCTURING AND CLASSIFICATION TOOL: CASE STUDY FOR MAPPING LULC FROM RASAT SATELLITE IMAGES

2019 ◽  
Vol XLII-4/W16 ◽  
pp. 39-46
Author(s):  
S. K. M. Abujayyab ◽  
I. R. Karaş
Keyword(s):  
Machine Learning ◽  
Image Classification ◽  
Satellite Images ◽  
Satellite Image ◽  
Land Use Land Cover ◽  
Limited Memory ◽  
Performance Accuracy ◽  
Satellite Image Classification ◽  
Classification Tool

Abstract. Remote sensing satellite images plays a significant role in mapping land use/land cover LULC. Machine learning ML provide robust functions for satellite image classification. The objective of this paper is to extend the capability of GIS specialists in geospatial area with minimum knowledge in computer science to easily perform ML satellite image classification. A framework consisting 7 stages established. Tools of steps developed in two programing environments, which are ArcGIS for geospatial datasets structuring and Anaconda for ML training and classification. During the development, authors constrained to reduce the complexity of big data of satellite images and limited memory of computers to make tools available for implementation in PC. In addition, automation and improving the performance accuracy. TensorFlow-Keras library employed to perform the classification using neural networks. A case study using RASAT satellite image in Ankara-Turkey utilized to perform the analysis. The developed classifier gained 80% performance accuracy. The complete RASAT satellite image processed and smoothly classified based on blocks methods. The developed tools successfully tested and applied in geospatial area and can be effectively execute in PC by GIS specialist.

Sign in / Sign up

Export Citation Format

Share Document