scholarly journals Selection of an algorithm for automatic classification of satellite images for the study of agricultural crops on the territory of Vietnam

2021 ◽  
Vol 937 (3) ◽  
pp. 032082
Author(s):  
B N Olzoev ◽  
H Z Huang ◽  
L A Plastinin ◽  
V E Gagin ◽  
O V Danchenko

Abstract The paper is devoted to the choice of an algorithm for automatic controlled classification of multi-zone satellite images of Landsat 8 OLI for the purposes of agricultural crop research based on the analysis of various mathematical classification algorithms and comparison of the practical results of these algorithms when using the ENVI 5.4 software package. In the period from June to August 2020, a field survey was conducted by coordinating and ground-based object recognition for the purpose of compiling decryption standards based on images. The paper analyzes four frequently used popular algorithms for automatic controlled classification – maximum likelihood, minimum distance, Mahalanobis distance, parallelepiped. As a result, it is concluded that when classifying objects with very close brightness values, the maximum likelihood algorithm gives optimal and objective results. This conclusion was confirmed by the cameral method by evaluating the reliability of the classification results. The result of the study can be used for mapping agricultural crops and solving other problems of agricultural activity in Vietnam. The methodology presented in the paper can be applied when choosing controlled classification algorithms for other groups of plant complexes and objects based on remote sensing data from space.

2019 ◽  
Vol 12 (3) ◽  
pp. 961
Author(s):  
Leovigildo Aparecido Costa Santos ◽  
Paulo Eliardo Morais de Lima

Diferentes métodos são empregados para a classificação digital de imagens, porém, podem apresentar desempenhos diferentes, sendo importante testá-los para verificar suas eficácias no mapeamento de uso e cobertura da terra com intuito de se selecionar o classificador que apresente os melhores resultados e maior veracidade em relação à verdade de campo. O objetivo deste estudo foi avaliar e comparar os desempenhos de quatro algoritmos de classificação supervisionada para o mapeamento do uso e cobertura da terra da bacia hidrográfica do Rio Caldas – GO, utilizando imagens Landsat-8. Para tanto, foram utilizadas as cenas de órbita/ponto 222/71 e 222/72, com datas de passagem em 24/10/2017 e 22/10/2017, mosaicadas para formar uma única imagem de dimensões que abrangesse toda a área de interesse. A composição RGB utilizada foi das bandas 6, 5 e 4 (R=6, G=5, B=4). Para a realização do processamento digital da imagem foi empregado o software ENVI versão 5.0 e à elaboração de mapas temáticos o QGIS 2.18. Os algoritmos testados foram: Paralelepípedo, Distância de Mahalanobis, Distância Mínima e Máxima-verossimilhança. Como parâmetros de comparação foram utilizados os coeficientes de Kappa, acurácias global e matrizes de confusão. Os melhores resultados para a classificação de uso e cobertura foram obtidos pelo método da Máxima-verossimilhança (MaxVer), os piores pelo método do Paralelepípedo, os outros classificadores apresentaram resultados intermediários entre o melhor e o pior. Com os resultados obtidos pela classificação por MaxVer, constatou-se que atualmente a maior parte do solo da bacia é ocupada pelas classes Pastagem (63,14%) e Vegetação nativa (22,07%). Comparison between different supervised classification algorithms in Landsat-8 images in the thematic mapping of the caldas river basin, GoiásA B S T R A C TDifferent methods are used for a digital classification of images, however, they can present different performances, being important to test them to verify their efficiencies in the mapping of land use and coverage in order to select the classifier that presents the best results and greater truthfulness In relation to the truth of the field. The objective of this study was to evaluate and compare the performance of four supervised classification algorithms for the mapping of the land use and land cover of the Caldas river basin - GO, using Landsat-8 images. To do so, they were like the orbit / dot scenes 222/71 and 222/72, with passing date on 10/24/2017 and 10/22/2017, mosaicked to form a single image of dimensions covering an entire area of interest . An RGB composition used for bands 6, 5 and 4 (R = 6, G = 5, B = 4). For the realization of digital image processing and the use of ENVI version 5.0 software and the development of thematic maps, QGIS 2.18. The algorithms tested were: Parallelepiped, Mahalanobis Distance, Minimum Distance and Maximum Likelihood. As the comparison parameter is used by Kappa coefficients, global accuracy and matrices of confusion. The best results for a classification of use and coverage are obtained by the Maximum-likelihood method (MaxVer), the most common methods, the other classifiers presented the intermediates between the best and the worst. With the results obtained by classification by MaxVer, it was verified that at the moment it is part of the soil of the basin is occupied by classes Pasture (63.14%) and native vegetation (22.07%).Keywords: Use and coverage; remote sensing; geoprocessing; Landsat.


Author(s):  
Jones Remo Barbosa Vale ◽  
Jamer Andrade da Costa ◽  
Jefferson Ferreira dos Santos ◽  
Elton Luis Silva da Silva ◽  
Artur Trindade Favacho

COMPARATIVE ANALYSIS THE METHODS OF SUPERVISED CLASSIFICATION APPLIED TO THE MAPPING OF SOIL COVER IN THE MUNICIPALITY OF MEDICILÂNDIA, PARÁANÁLISIS COMPARATIVO DE MÉTODOS DE CLASIFICACIÓN SUPERVISADA APLICADA AL MAPEO DE LA COBERTURA DEL SUELO EN EL MUNICIPIO DE MEDICILÂNDIA, PARÁAs imagens de satélite são produtos gerados por sensoriamento remoto e, estão associadas aos fenômenos e eventos que ocorrem na superfície a partir do registro e da análise das interações entre a radiação eletromagnética e os alvos. O objetivo do trabalho é comparar métodos de classificação supervisionada de imagens de satélite para o mapeamento da cobertura do solo. A área de estudo compreende o município de Medicilândia, localizado no sudoeste paraense. Para a realização do trabalho foram utilizados imagens do satélite Landsat 8, sensor OLI-TIRS, cenas 226/062 e 227/062. Foram realizados os testes de classificação, utilizando três classificadores: Distância Mínima, Distância Mahalanobis e Máxima Verossimilhança. Na etapa de classificação foram identificadas as seguintes classes: água, nuvem, sombra de nuvem, solo exposto, vegetação primária e vegetação secundária. Para fins de avaliação da fidedignidade da classificação de cada método foram calculados, o Índice Kappa e a Exatidão Global. A classificação pelo método Máxima Verossimilhança obteve maior exatidão apresentando Índice Kappa de 0,920 e Exatidão Global 96% quando comparada à classificação pelos métodos Distância Mínima e Distância Mahalanobis, que apresentaram Índice Kappa de 0,842 e 0,845 e Exatidão Global 92% respectivamente. As técnicas de classificação supervisionada são ferramentas essenciais no processo de mapeamento da cobertura do solo de grandes áreas, visto que dispondo-se de recursos limitados, imagens de baixo custo e de sistemas livres para processamento e integração das informações, é possível obter parâmetros com altos níveis de precisão, sendo fundamentais para subsidiar o planejamento territorial e ambiental.Palavras-chave: Sensoriamento Remoto; Classificação de Imagens de Satélite; Cobertura do Solo.ABSTRACTThe satellite images are products generated by remote sensing and are associated with phenomena and events that occur on the surface from the recording and analysis of interactions between electromagnetic radiation and targets. The objective of this work is to compare methods of supervised classification of satellite images for the mapping of the soil cover. The study area comprises the municipality of Medicilândia, located in southwest of Para. In order to perform the work, were used images from the Landsat 8 satellite, OLI-TIRS sensor, scenes 226/062 and 227/062. The classification tests were performed using three classifiers: Minimum Distance, Mahalanobis Distance and Maximum Likelihood. In the classification processe were identified the following classes: water, cloud, cloud shadow, exposed soil, primary vegetation and secondary vegetation. For the purposes of evaluating the reliability of the classification of each method were calculated, Kappa Index and Global Accuracy. The classification by the Maximum Likelihood method obtained a greater accuracy presenting Kappa Index of 0,920 and Global Accuracy 96% when compared to the classification by the Minimum Distance and Mahalanobis Distance, which presented Kappa Index of 0,842 and 0,845 and Global Accuracy 92% respectively. The supervised classification techniques are essential tools in the mapping process of large-area soil cover, since with limited resources, low-cost images and free systems for processing and integrating information, it is possible to obtain parameters with high levels of precision, being fundamental to subsidize territorial and environmental planning.Keywords: Remote Sensing; Classification of Satellite Images; Soil Cover.RESUMENLas imágenes de satélite son productos generados por la detección remota y están asociados a los fenómenos y eventos que ocurren en la superficie a partir del registro y del análisis de las interacciones entre la radiación electromagnética y los blancos. El objetivo del trabajo es comparar métodos de clasificación supervisada de imágenes de satélite para el mapeo de la cobertura del suelo. El área de estudio comprende el municipio de Medicilândia, ubicado en el suroeste paraense. Para la realización del trabajo se utilizaron imágenes del satélite Landsat 8, sensor OLI-TIRS, escenas 226/062 y 227/062. Se utilizaron tres clasificadores: Distancia Mínima, Distancia Mahalanobis y Máxima Verosimilitud. En la etapa de clasificación se identificaron las siguientes clases: agua, nube, sombra de nube, suelo expuesto, vegetación primaria y vegetación secundaria. Para evaluar la confianza de la clasificación de cada método se ha calculado, el Índice Kappa y la Exactitud Global. La clasificación por Máxima Verosimilitud obtuvo mayor exactitud presentando Índice Kappa de 0,920 y Exactitud Global 96% cuando comparada a la clasificación por Distancia Mínima y Distancia Mahalanobis, que presentaron Índice Kappa de 0,842 y 0,845 y Exactitud Global 92% respectivamente. Las técnicas de clasificación supervisada son herramientas esenciales en el proceso de mapeo de la cobertura del suelo de grandes áreas, ya que disponiendo de recursos limitados, imágenes de bajo costo y de sistemas libres para procesamiento e integración de la información, es posible obtener parámetros con altos niveles de precisión, siendo fundamentales para subsidiar la planificación territorial y ambiental.Palabras clave: Sensoramiento Remoto; Clasificación de Imágenes de Satélite; Cobertura del Suelo.


2021 ◽  
Vol 10 (2) ◽  
pp. 58
Author(s):  
Muhammad Fawad Akbar Khan ◽  
Khan Muhammad ◽  
Shahid Bashir ◽  
Shahab Ud Din ◽  
Muhammad Hanif

Low-resolution Geological Survey of Pakistan (GSP) maps surrounding the region of interest show oolitic and fossiliferous limestone occurrences correspondingly in Samanasuk, Lockhart, and Margalla hill formations in the Hazara division, Pakistan. Machine-learning algorithms (MLAs) have been rarely applied to multispectral remote sensing data for differentiating between limestone formations formed due to different depositional environments, such as oolitic or fossiliferous. Unlike the previous studies that mostly report lithological classification of rock types having different chemical compositions by the MLAs, this paper aimed to investigate MLAs’ potential for mapping subclasses within the same lithology, i.e., limestone. Additionally, selecting appropriate data labels, training algorithms, hyperparameters, and remote sensing data sources were also investigated while applying these MLAs. In this paper, first, oolitic (Samanasuk), fossiliferous (Lockhart and Margalla) limestone-bearing formations along with the adjoining Hazara formation were mapped using random forest (RF), support vector machine (SVM), classification and regression tree (CART), and naïve Bayes (NB) MLAs. The RF algorithm reported the best accuracy of 83.28% and a Kappa coefficient of 0.78. To further improve the targeted allochemical limestone formation map, annotation labels were generated by the fusion of maps obtained from principal component analysis (PCA), decorrelation stretching (DS), X-means clustering applied to ASTER-L1T, Landsat-8, and Sentinel-2 datasets. These labels were used to train and validate SVM, CART, NB, and RF MLAs to obtain a binary classification map of limestone occurrences in the Hazara division, Pakistan using the Google Earth Engine (GEE) platform. The classification of Landsat-8 data by CART reported 99.63% accuracy, with a Kappa coefficient of 0.99, and was in good agreement with the field validation. This binary limestone map was further classified into oolitic (Samanasuk) and fossiliferous (Lockhart and Margalla) formations by all the four MLAs; in this case, RF surpassed all the other algorithms with an improved accuracy of 96.36%. This improvement can be attributed to better annotation, resulting in a binary limestone classification map, which formed a mask for improved classification of oolitic and fossiliferous limestone in the area.


2017 ◽  
Vol 10 (1) ◽  
pp. 1 ◽  
Author(s):  
Clement Kwang ◽  
Edward Matthew Osei Jnr ◽  
Adwoa Sarpong Amoah

Remote sensing data are most often used in water bodies’ extraction studies and the type of remote sensing data used also play a crucial role on the accuracy of the extracted water features. The performance of the proposed water indexes among the various satellite images is not well documented in literature. The proposed water indexes were initially developed with a particular type of data and with advancement and introduction of new satellite images especially Landsat 8 and Sentinel, therefore the need to test the level of performance of these water indexes as new image datasets emerged. Landsat 8 and Sentinel 2A image of part Volta River was used. The water indexes were performed and then ISODATA unsupervised classification was done. The overall accuracy and kappa coefficient values range from 98.0% to 99.8% and 0.94 to 0.98 respectively. Most of water bodies enhancement indexes work better on Sentinel 2A than on Landsat 8. Among the Landsat based water bodies enhancement ISODATA unsupervised classification, the modified normalized water difference index (MNDWI) and normalized water difference index (NDWI) were the best classifier while for Sentinel 2A, the MNDWI and the automatic water extraction index (AWEI_nsh) were the optimal classifier. The least performed classifier for both Landsat 8 and Sentinel 2A was the automatic water extraction index (AWEI_sh). The modified normalized water difference index (MNDWI) has proved to be the universal water bodies enhancement index because of its performance on both the Landsat 8 and Sentinel 2A image.


2019 ◽  
Vol 37 (1) ◽  
pp. 1
Author(s):  
Tiago Rafael de Barros Pereira ◽  
Helenice Vital ◽  
André Giskard Aquino da Silva ◽  
Cecília Alves de Oliveira

ABSTRACT. The main scope of this paper is the analysis of seafloor classification using acoustic remote sensing data. These data were acquired in a hydroacoustic survey of bathymetry and sonography using an interferometric swath bathymetry system. The study area is a sector of the internal northeast Brazilian shelf adjacent to the Ponta Negra beach - Natal (RN). The objective of the work is to identify and draw the different textural patterns, which characterize the seafloor of the study area. In addition, two approaches for textural classification of sonograms were compared and evaluated, which were: Automatic Gray Level Co-occurrence Matrix (GLCM) classification available in SonarWiz software; and the semi-automatic Maximum Likelihood, available in ArcGIS software. The comparison tested the capacity for identifying and drawing the textural patterns distribution. The automated classification identified 4 patterns while on the semi-automated 5 patterns were identified. It was made the correlation between the textural patterns found in each classification, besides the correlation between textural patterns and the levels of intensity of reflectance presents on the sonogram.Keywords: sonography, textural classification, textural patterns, hydroacoustic. RESUMO. Este trabalho foi realizado a partir da análise de dados geofísicos adquiridos em levantamento hidroacústico de batimetria e sonografia utilizando um sonar interferométrico EdgeTech 4600. A área de estudo é uma porção da plataforma interna do nordeste brasileiro adjacente Natal (RN). O objetivo deste trabalho é identificar e delimitar os diferentes padrões texturais que caracterizam o substrato marinho da área de estudo. Adicionalmente, são avaliadas e comparadas duas abordagens distintas de classificação textural de sonogramas, sendo elas: a classificação automática GLCM disponível no software SonarWiz, e a classificação semi-automática máxima verossimilhança (Maximum Likelihood) disponível no software ArcGIS. A comparação foi realizada com base na capacidade de identificação e delimitação da distribuição dos padrões texturais. A utilização da classificação automática identificou 4 padrões, enquanto que, na classificação semi-automática 6 padrões foram identificados. Foi feita a correlação entre os padrões texturais encontrados em cada classificação, além da correlação entre os padrões texturais e os níveis de intensidade de reflectância presente no sonograma.Palavras-chave: sonografia, classificação textural, padrões de textura, hidroacústica.


AGROFOR ◽  
2019 ◽  
Vol 3 (3) ◽  
Author(s):  
Bojan ĐURIN ◽  
Anita PTIČEK SIROČIĆ ◽  
Nikola SAKAČ ◽  
Marko ŠRAJBEK

Selection of a particular agricultural crop for the food production is a complexproblem. This is usually conditioned not only by the financial claims, but also otherrequirements should be taken into the account, i.e. environmental criteria,sustainability, etc. Fuzzy Logicis one of the many appropriate tools/procedures forsolving such task(s).Such a procedure will be implemented within decision-makingalgorithm for the selection of an appropriate agricultural crop. The paper deals withthe implementation of the mentioned tool/procedure for selection and ranking ofthe particular sort of crops, regarding different decision-making structures. Withinthis, there is an intention to reduce all possible biases and subjectivities tominimum by using Fuzzy Logic. This will be applied with input parameters, whichare extracted and correlated with real requirements and conditions regarding actualneeds of the market and farmers. Along with the offered agricultural crops andpossibility of their selection, final ranking and selection of the most appropriatecrop can be supported for different possible scenarios (dry or wet period of theyear, accents on the financial, environmental of other criteria, available financialresources, market availability, etc.). Presented methodology will contribute to thefinal goal, which is systematic agricultural planting and sustainability of the foodproduction.


Author(s):  
Tigran Shahbazyan

The article considers the methodology of monitoring specially protected natural areas using remote sensing data. The research materials are satellite images of the Landsat 5 and Landsat 8 satellites, obtained from the resource of the US Geological Survey. The key areas of the study were 3 specially protected areas located within the boundaries of the forest-steppe landscapes of the Stavropol upland, the reserves «Alexandrovskiy», «Russkiy Les», «Strizhament». The space survey materials were selected for the period 1991–2020, and the data from the summer seasons were used. The NDVI index is chosen as the method of processing the spectral channels of satellite imagery. To integrate long-term satellite imagery into a single raster image, the method of variance of the variation series for the NDVI index was used. The article describes an algorithm for processing satellite images, which allows us to identify the features of the dynamics of the vegetation state of the studied territory for the period 1991–2020. The bitmap image constructed by means of the variance of the NDVI index was classified by the quantile method, to translate numerical values into classes with qualitative characteristics. There were 4 classes of the territory according to the degree of dynamism of the vegetation state: “stable”, “slightly variable”, “moderately variable”, “highly variable”. The paper highlights the factors of landscape transformation, including natural and anthropogenic ones. In the course of the study, the determining influence of anthropogenic factors of transformation was noted. The greatest impact is on the reserve «Alexandrovskiy», the least on the reserve «Russkiy Les», in the reserve «Strizhament» the impact is expressed locally. The paper identifies the leading anthropogenic factors of vegetation transformation, based on their influence on vegetation.


Sign in / Sign up

Export Citation Format

Share Document