AR4-50 MODEL, THE EXTRACTION OF SPECTRAL VALUES INTO REMOTE SENSING IMAGE DATA-BASED LAND USE CLASS (original) (raw)
Related papers
Ar4-50 Model, the Extractor of Spectral Values Into Remote Sensing Image Data-based Land Use Class
2013
Th is study attempted to develop a n extraction model of spectral values of land objects into land use/land cover classes o n remote sensing image in the provision of land database f or planning , evaluation , and monitoring in agriculture and forestry . This study employed an Isodata method and Knowledge -Based Systems ( KBS) using the Landsat 7 ETM + image in the coverage area of 117,799.06 ha , and the SPOT 5 XS image in the coverage area of 113,241.37 ha in Palu , Sigi and Donggala . The study found two image models labelled as AR4 - 50 and SBP - AR4 - 50. The s eparability image AR4 - 50 model has an average capability for separating land object pixels which are statistically 1811.98 to 1972.08 ( moderate -good ), with the class accuracy of land use/land cover using the image homogeneity model of SBP - AR4 - 50, which is totally ( confusion matrix ) 72.15 % -87.17 %, the accuracy level of land map generator for agricultural land/forestry is in good - excellent category on...
Jurnal Inotera, 2021
Tapaktuan is the capital and administrative center of South Aceh Regency, which is a sub-district level city area known as Naga City. Tapaktuan is designated as a sub-district to be used for the expansion of the capital's land. Consideration of land suitability is needed so that the development of settlements in Tapaktuan District is directed. The purpose of this study is to determine the level of land use change from 2014 to 2018 by using remote sensing technology in the form of Landsat-8 OLI satellite data through image classification methods by determining the training area of the image which then automatically categorizes all pixels in the image into land cover class. The results obtained are the results of the two image classification tests stating the accuracy of the interpretation of more than 80% and the results of the classification of land cover divided into seven forms of land use, namely plantations, forests, settlements, open land, and clouds. From these classes, th...
International Journal of Environment and Geoinformatics
There are several remotely sensed images of varied resolutions available. As a result, several classification techniques exist, which are roughly classified as pixel-based and object-based classification methods. Based on the foregoing, this study provided an integrated method of deriving land use from a coarse satellite image. Location coordinates of the land uses were acquired with a handheld Global Positioning System (GPS) instrument as primary data. The study classified the image quantitatively (pixel-based) into built-up, water, riparian, cultivated, and uncultivated land cover classes with no mixed pixels, and then qualitatively into educational, commercial, health, residential, and security land use classes that were conflicting due to spectral similarity. The total accuracy and kappa coefficient of the pixel-based land cover classification were 92.5% and 94% respectively. The results showed that residential land use occupied an area of 5500.01ha, followed by educational (280...
Identification of Land-Use and Vegetation Types in Fateh Jang Area, Using Landsat-TM Data
sciencevision.org.pk
The study area has an undulating topography, with terraced land for agriculture and slopy and dissected patches under natural vegetation. The objective of the study is to valuate the capability of LANDSAT-TM data for identification of various land-uses and to differentiate the vegetation covers, like forest, crop, shrubs and grasses. The image classification was carried out through supervised and unsupervised classification techniques. In general, the trend of coverage of classes identified by both the techniques is the same. The contingency table indicates the accuracy of trainingsamples within range of 94 to 98 percent, used for the classification of image. The NVI technique was used to separate the spectral reflectance of vegetation from background reflectance. It has improved the segregation of bare ground and vegetative areas. The coverage of water-bodies can be estimated by using any technique, since the reflectance of water is quite different from other landcovers except some shadow-areas. The effect of shadow-areas in the hilly terrain can be eliminated on micro-level considering their association with the surrounding landcover. Considering the spectral resolution of the RS data used, the technique has high potential for identification of various landcovers and land use. A combination of image analysis techniques with field survey of sample-sites will allow refining the boundaries of defined classes.
Study Of Remote Sensing And Satellite Images Ability In Preparing Agricultural Land Use Map (Alum)
2010
In this research the Preparation of Land use map of scanner LISS III satellite data, belonging to the IRS in the Aghche region in Isfahan province, is studied carefully. For this purpose, the IRS satellite images of August 2008 and various land preparation uses in region including rangelands, irrigation farming, dry farming, gardens and urban areas were separated and identified. Therefore, the GPS and Erdas Imaging software were used and three methods of Maximum Likelihood, Mahalanobis Distance and Minimum Distance were analyzed. In each of these methods, matrix error and Kappa index were calculated and accuracy of each method, based on percentages: 53.13, 56.64 and 48.44, were obtained respectively. Considering the low accuracy of these methods in separation of land preparation use, the visual interpretation of the map was used. Finally, regional visits of 150 points were noted at random and no error was observed. It shows that the map prepared by visual interpretation is in high a...
The aim of the study was to examine the potential maximum likelihood classification in the mapping of basic land cover/land use classes by using ALOS AVNIR-2 imagery. The two specific objectives were; (a) to develop a maximum likelihood classification scheme for mapping land cover/land use classes using ALOS AVNIR-2 imagery, (b) to estimate the accuracy of the used method. Land cover nomenclature is classified according to the Coordination of Information on the Environment (CORINE) Level 2 and 3 classifications. Ten urban land cover classes were used in this study: river, wetland vegetation, forest, mining area, shadow, mountain forest, cemetery, agriculture, built up area, industrial area. The classification accuracy was assessed using 218 pixels were stratified randomly distributed throughout the study area and independent of training sites used by the supervised classification algorithm. The results show that overall classification accuracies is 81.19% and overall kappa statistics is 0.7845.
2018
Land use and land cover classification system has been used widely in many applications such as for baseline mapping for Geographic Information System (GIS) input and also target identification for identification of roads, clearings and also land and water interface. The research was conducted in Kuala Tiga, Tanah Merah, Kelantan and the study area covers for about 25 km2. The main purpose of this research is to access the possibilities of using remote sensing for the detection of regional land use change by developing land cover classification system. Another goal is to compare the accuracy of supervised and unsupervised classification system by using remote sensing. In this research, both supervised and unsupervised classifications were tested on satellite images of Landsat 7 and 8 in the year 2001 and 2016. As for supervised classification, the satellite images are combined and classified. Information and data from the field and land cover classification is utilized to identify t...
Analysis of land use in the Banyuasin district using the image Landsat 8 by NDVI method
2017
Land use is one important factor in the planning of infrastructure development. The development that does not consider land use may cause an impact to environmental degradation. In minimizing the time and costs, the introduction of land use in an area could be done with remote sensing technology, one of the methods that could be used is the Normalized Different Vegetation Index (NDVI). NDVI is a combination of a multi-spectral band by using a wavelength Red and Near Infra-Red (NIR) on image Landsat 8 to estimate the vegetation cover. Than each classification of vegetation density will provide the reflectance value. In this study, the land cover classification result based on vegetation density by NDVI method, namely 0.5120-0.3706 for the low-density vegetation area; 0.3706-0.6149 for the moderate density vegetation area; and 0.6149-0.8677 for the high-density vegetation area. While the overall accuracy percentage of land use classification was 80%.
AUTOCARTO-CONFERENCE-, 1995
Most fundamental per-pixel classification techniques group pixels into clusters based on their spectral characteristics. Since various terrestrial objects may exhibit similar spectral responses, the classification accuracies of remote sensing derived image-maps is often reduced. This study focuses on using the shape index of detected ground objects to resolve some of the spectral confusions which occur when pure per-pixel classification algorithms are applied. First, homogeneous areas were identified by using an edge detection algorithm. Second, a stratification procedure divided the image into two strata based on the shape index of patches. One stratum was composed of patches with regular shapes and large sizes, such as agricultural fields and some wet meadows. The other stratum was composed of highly fragmented patches, including urban areas, roads, and riparian vegetation. By stratifying the image, the classes which frequently caused mixed clusters, such as grassy surfaces in urban areas and crop fields, wet fields and riparian forests, were assigned to different strata, thus reducing the possibility of spectral confusion. Third, a spectral classification algorithm was applied to the two strata separately to derive the land cover information for each layer. Finally, the two classifications were merged to produce the final land use/land cover map of the study area.
Landuse Pattern Analysis Using Remote Sensing: A Case Study of Mau District, India
Land use mapping is fundamental for assessment, managing and protection of natural resources of a region and the information on the existing land use is one of the prime pre-requisites for suggesting better use of terrain. Advances in satellite sensor and their analysis techniques are making remote sensing systems realistic and attractive for use in research and management of natural resources. Land use maps are valuable tools for agricultural and natural resources studies. Due to strength of natural resources, updating these maps is essential. Employing traditional methods through aerial photos interpretation to produce such maps are costly and time consuming. With the growth of population and socio-economic activities, natural land cover is being modified for various development purposes. This has increased the rate of changes on land-use pattern over time and thus, affecting the overall ecosystem health. Land use mapping is an important tool for land management and monitoring. Th...