COMPORTAMENTO DO SOFTWARE TERRAVIEW NA CLASSIFICAÇÃO SUPERVISIONADA EM DIFERENTES BACIAS

2016 ◽  
Vol 31 (3) ◽  
pp. 282
Author(s):  
Mikael Timóteo Rodrigues ◽  
Lincoln Gehring Cardoso ◽  
Sérgio Campos ◽  
Bruno Timóteo Rodrigues ◽  
Zacarias Xavier de Barros

O objetivo principal desse trabalho é averiguar a atuação do software TerraView 4.2.2 desempenhando a classificação supervisiona por meio do padrão espectral em imagem Landsat 5, associada a comparação do uso da terra das bacias hidrográficas dos rios Lavapés e Capivara, inseridas no município de Botucatu/SP utilizando-se técnicas de sensoriamento remoto e geoprocessamento. As áreas de treinamento supervisionado foram definidas a partir de nove classes para bacia do Lavapés e sete para bacia do Capivara, fundamentais para o estudo e análise do uso e ocupação da terra, como mata, solo, culturas - agricultura, corpos d´água e malha urbana dentre outras classes encontradas. Tais áreas de treinamento supervisionado foram definidas por meio de polígonos que representaram as respectivas classes de uso e ocupação da terra, considerando a cor, brilho, padrão e textura emitida por cada pixel da imagem. A diferença de resultados entre as duas bacias avaliadas foi notória, onde a bacia do Capivara apresentou melhores resultados, seguramente por apresentar um número menor de classes de uso da terra e uma menor área urbana, assim causando menos confusões para o algoritmo. Outro fator evidente foi à clara diferença dos produtos derivados a partir da classificação gerada e posteriormente pós-classificados com o filtro majoritário (majority filter), onde sempre após a reclassificação a acurácia foi elevada, apresentado menos erros de omissão e comissão nas matrizes e suavização dos mapas classificados, com a eliminação de classes de 10 e 75 pixels por região, o que abrandou consideravelmente a estética dos mapas e consequentemente a diminuição de erros. PALAVRAS-CHAVE: Geoprocessamento, Sensoriamento Remoto, Processamento de Imagens, Uso do solo. BEHAVIOR TERRAVIEW SOFTWARE IN SUPERVISED CLASSIFICATION IN DIFFERENT WATERSHEDSABSTRACT: The main objective of this study is to ascertain the performance of the TerraView 4.2.2 software performing the classification oversees through the spectral pattern on Landsat 5, associated with comparing the land use of the Lavapés and Capivara’s watersheds, set in Botucatu/São Paulo using remote sensing and GIS. The areas of supervised training were set from nine classes for Lavapés watershed, and seven for Capivara watershed, fundamental for the study and analysis of the use and occupation of land as forest, soil, crops – Agriculture, Water Bodies and Mesh urban, found among other classes. Such areas of supervised training were defined by polygons representing the respective classes of use and occupation of land, considering the color, brightness, pattern and texture emitted by each pixel of the image. The difference in results between the two watersheds was evaluated notorious, where the Capivara watershed showed better results, surely by having a smaller number of land use classes and a smaller urban area, thus causing less confusion for the algorithm. Another obvious factor was the clear difference of products derived from the classification generated and subsequently post-classed with the majority filter, where ever after reclassification accuracy has always been high, presented less errors of omission and commission in the headquarters and smoothing of classified maps, with the elimination of 10 and 75 pixels per region classes, which greatly slowed the aesthetics of maps and therefore decrease errors.KEYWORDS: Geoprocessing, Remote Sensing, Image Processing, Use of the soil.

2019 ◽  
Vol 3 (2) ◽  
pp. 29
Author(s):  
Zachary Gichuru Mainuri ◽  
John M. Mironga ◽  
Samuel M. Mwonga

Drivers of land use change were captured by the use of DPSIR model where Drivers (D) represented human needs, Pressures (P), human activities, State (S), the ecosystem, Impact (I) services from the ecosystem and Response (R), the decisions taken by land users. Land sat MSS and Land sat ETM+ (path 185, row 31) were used in this study. The Land sat ETM+ image (June 1987, May, 2000 and July, 2014) was downloaded from USGS Earth Resources Observation Systems data website. Remote sensing image processing was performed by using ERDAS Imagine 9.1. Two land use/land cover (LULC) classes were established as forest and shrub land. Severe land cover changes was found to have occurred from 1987-2000, where shrub land reduced by -19%, and forestry reduced by -72%. In 2000 – 2014 shrub land reduced by-45%, and forestry reduced by -64%. Forestry and shrub land were found to be consistently reducing.


2021 ◽  
Vol 11 (6) ◽  
Author(s):  
Chaitanya B. Pande ◽  
Kanak N. Moharir ◽  
S. F. R. Khadri

AbstractIn this paper, we focus on the assessment of land-use and land-cover change detection mapping to the effective planning and management policies of environment, land-use policy and hydrological system in the study area. In this study the soil and water conservation project has been applied during the five years and after five years what changes have been found in the land-use and land-cover classes and vegetation. In this view, this land-use and land-cover mapping is a more important role to decide the policy for watershed planning and management project in the semiarid region. In an emerging countries, fast industrialization and urbanization impose a significant threat to the natural atmosphere. The remote sensing and GIS techniques are crucial roles in the study of land-use and land-cover mapping during the years of 2007, 2014, and 2017. The main objective of this is to prepare the land-use and NDVI maps in the years of 2008, 2014 and 2017; these maps have prepared from satellite data using the supervised classification method. A normalized difference vegetation index map (NDVI) was done by using Landsat 8 and LISS-III satellite data. NDVI values play a major role in monitoring the vegetation and variation in land-use and land-cover classes. In these maps, four types of land are divided into four classes as agriculture, built-up, wasteland, and water body. The results of study show that agriculture land of 18.71% (158.24 Ha), built-up land of 0.62% (5.31 Ha), wasteland of 40.33% (341.02 Ha), and water body land of 17.39% (147 Ha) are increased. Land-use and land-cover maps and NDVI values show that agriculture land of 22.97% (194.29 Ha), 5.46% (14.59 Ha), and 0.08% (0.22 Ha) decreases during the years of 2008, 2014, and 2017. The results directly indicate that the supervised classification method has been the accurate identified feature in the land-use map classes. This classification method has been given the better accuracy (95%) from spatiotemporal satellite data. The accuracy was also tally with ground-truth and Google earth information. These results can be a very useful for the land-use policy, watershed planning, and management with natural resources, animals, and ecological systems.


2018 ◽  
Vol 41 (2) ◽  
pp. 103-112
Author(s):  
Payam Sajadi ◽  
◽  
Saumitra Mukherjee ◽  
Kamran Chapi ◽  
◽  
...  

This research aimed to analyze the land use/ land cover (LULC) change in Qorveh-Dehgolan Basin (Kurdistan, Iran) from 2000 to 2017 (four sets of data) using Landsat (7 and 8) images. Supervised classification using maximum likelihood generated four series of LULC maps by ENVI 5.3 software. Overall, six major classes including bare soil, water body, vegetation cover, agriculture land, grassland, and settlements were identified and mapped.The LULC style has changed over 17 years. It was determined that the waterbody class has continuously reduced about 173.66 km2 from 2000 to 2017 by 63%. The agriculture class has considerably increased from 2000 to 2017 about 129.43 km2 and finally, the area of settlement class increased about 54.06. km2. The overall accuracy was 81.50%, 85.0%, 92.00%, 92.00% for the years of 2000, 2006, 2013 and 2017 respectively.


Sign in / Sign up

Export Citation Format

Share Document