Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 55

Liczba wyników na stronie
first rewind previous Strona / 3 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  pokrycie terenu
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 3 next fast forward last
PL
Wpływ sposobu użytkowania w obrębie obszarów otaczających miasta jest szczególnie silny w przypadku małych ośrodków, gdyż tereny leśne i rolnicze graniczą tam częstokroć bezpośrednio ze strefami mieszkalnymi. Coraz liczniej pojawiają się publikacje, które dokumentują oddziaływanie tych dwóch sposobów użytkowania, wskazując m.in. na znaczenie uwarunkowań przestrzennych, które determinują wielkość wpływu otoczenia na jakość życia mieszkańców miast. Celem pracy było oszacowanie udziału sposobów użytkowania w otoczeniu 738 małych miast Polski (<20 tys. mieszkańców), z uwzględnieniem potencjału rekreacyjnego lasów i ewentualnych zagrożeń wyni¬kających z bliskiego sąsiedztwa z intensywnie użytkowanymi gruntami rolnymi. Podstawą uzyskanych wyników była baza Corine Land Cover z 2018 roku, z której pozyskano informację o usytuowaniu zabudowy miejskiej, lasach oraz terenach rolnych (grunty orne i sady). Uzyskane wyniki wskazują, że w przypadku 35,6% małych miast Polski teren zabudowany nie sąsiadował z lasami, a 7,3% miast nie posiadało lasów w promieniu 1,5 km. Natomiast tylko w 5,6% miastach teren zabudowany nie graniczył z jakimkolwiek terenem rolnym, a w 4,9% teren ten otoczony był w ponad 80% polami. Należy sądzić, że w grupie miast otoczonych polami, przy planowaniu struktury przestrzennej, szczególną uwagę należałoby poświęcić projektowaniu nowych terenów zielonych i rewaloryzacji już istniejących.
EN
The impact of land use within the areas surrounding cities is particularly strong in the case of small towns, as forest and agri¬cultural areas often directly border residential areas. There are more and more publications that document the impact of these two forms of land use, highlighting, among other things, the importance of spatial conditions that determine the impact of the environment on the quality of life of city inhabitants. The aim of the study was to estimate the share of different land use methods in the vicinity of 738 small Polish towns (<20,000 inhabitants), taking into account the recreational potential of forests and possible threats resulting from close proximity to intensively used agricultural land. The study was based on the Corine Land Cover database from 2018. Information on the location of urban development, forests and agricultural land (arable land and orchards) was obtained from this database. The results indicate that in the case of 35.6% of small Polish towns, built-up areas were not adjacent to forests, and 7.3% of towns did not have forests within a radius of 1.5 km. On the other hand, only in 5.6% of cities did no built-up areas border agricultural areas, and in 4.9% of cities more than 80% of built-up areas were surrounded by fields. In cities surrounded by fields, special attention should be paid to the design of new green areas and the redevolopment of existing ones when planning the spatial structure.
EN
The aim of the study was to diagnose the main trends of changes in land cover in selected communes of Polish metropolitan areas. Detailed studies were conducted in deliberately selected housing estates located in the core of metropolitan area (at least one housing estate) and communes located directly at the border of cities and located on the outskirts of metropolitan areas. The examined communes also differed in the quality of natural conditions of agricultural production. The study used LANDSAT 5 TM and RapidEye satellite images from three limited-time registrations (1996/1999, 2011, 2016/2017). On the basis of remote sensing data, changes in land use were specified by presenting them in a graphic form as compilation of numerical maps. The analyses were performed on processed images (colour compositions), which were subjected to supervised classification using the maximum-likelihood technique. The quality control of supervised classification showed accuracy of 89.3% for LANDSAT 5 TM scene analyses and 91.8% for RapidEye images. Kappa coefficient for the discussed classification was: 0.84 (LANDSAT TM) and 0.89 (Rapid Eye). The results obtained for individual metropolitan areas allow to identify the directions of changes (Land Use Change Cover) taking place in them, with consideration to specificity of each of them.
EN
Population growth and urbanization lead to urban heat island (UHI) phenomenon. Urbanization is occurring at a very high rate in the Surat city. Thus, the study of the urbanization impact on the UHI effect for the Surat city is performed in the present study through studying the impact of land use land cover on the land surface temperature of urban and sub-urban areas of the Surat city over the period May 1998 to May 2018. Also, these effects are compared with that of a nearby sub urban taluka Kamrej, which showed that temperature in urban areas is more than that of the sub-urban areas. Aforesaid facts clearly showing the existence of the UHI effect in the Surat city. As urbanization contributes to climate change, its effects on rainfall are studied by comparing rainfall trends of urban and sub-urban areas of the Surat city and nearby sub-urban area Kamrej. Trend analysis showed that trend magnitude values are higher for the urban areas than sub-urban areas, indicating that UHI effect increases rainfall in urban areas. Hotspot analysis is also performed for the Surat city corresponding to May 2018 to recognize hot spots and cold spots. As the Surat city is highly urbanized, thus, hotspots are more than cold spots.
EN
Unmanned Aerial Vehicles (UAVs), commonly known as drones are increasingly being used for three dimensional (3D) mapping of the environment. This study utilised UAV technology to produce a revised 3D map of the University of Lagos as well as land cover change detection analysis. A DJI Phantom 4 UAV was used to collect digital images at a flying height of 90 m, and 75% fore and 65% side overlaps. Ground control points (GCPs) for orthophoto rectification were coordinated with a Trimble R8 Global Navigation Satellite System. Pix4D Mapper was used to produce a digital terrain model and an orthophoto at a ground sampling distance of 4.36 cm. The change detection analysis, using the 2015 base map as reference, revealed a significant change in the land cover such as an increase of 16,306.7 m2 in buildings between 2015 and 2019. The root mean square error analysis performed using 7 GCPs showed a horizontal and vertical accuracy of 0.183 m and 0.157 m respectively. This suggests a high level of accuracy, which is adequate for 3D mapping and change detection analysis at a sustainable cost.
EN
Timely and accurate detection of land use/land cover (LULC) change is important for the macro and micro level sustainable development of any region. For this purpose, geospatial techniques are the best tool for change analysis as they supply timely, cheaper, precise and up to date information. This paper examines the spatial temporal change trend in LULC in the case of Central Haryana. Landsat 2, 3, 5, 7 and 8 images for the years 1975–2020 for pre and post monsoon periods were analyzed for the study. Radiometric correction was performed to derive better information. ArcGIS 10.2 and ENVI 5.3 are used for thematic layout and thematic change preparation. An unsupervised classification using ERDAS IMAGINE 2015 has also been done to classify study area in eight classes. The year 1975 is considered as the base year for change detection analysis. Results showed an increasing trend for the land use classes of built up, water body, and agricultural land without waterlogging in the pre and post monsoon periods between 1975 and 2020. Remaining land use classes of agriculture with waterlogging, open waterlogged area, vegetation and fallow land/sand dunes decreased during the same period. Increased human activities have changed the LULC in the region and have had a great impact on its sustainable regional development.
EN
The real estate cadastre is the primary source of information on land use. It re cords information related to the division of land into types based on the actual way of land use or development. The distinguished types of land use depend on many geographical factors, as well as historical and economic conditions. The study presents a comparison of the detail of land use classification registered in the real estate cadastre in areas functionally related to the urban areas of 9 European countries: Austria, Bulgaria, the Czech Republic, Estonia, Spain, Lithuania, Luxembourg, Germany and Poland. The research concerned the determination of the degree to which the classification of land use in urbanized areas is detailed, whether the studied European countries are characterized by the same number of distinguished classes of ob jects at different levels of detail, and what percentage are the distinguished classes of land use objects in urbanized areas in relation to all of the distinguished classes of objects land use at different levels of detail of classification. The study used legal acts regulating land use issues which have been made available in national languages by government institutions.
EN
The present study aimed to analyse changes in the land cover of Vilnius city and its surrounding areas and propose a scenario for their future changes using an Artificial Neural Network. The land cover dynamics modelling was based on a multilayer perceptron neural network. Landscape metrics at a class and landscape level were evaluated to determine the amount of changes in the land uses. As the results showed, the Built-up area class increased, while the forest (Semi forest and Dense forest) classes decreased during the period from 1999 to 2019. The predicted scenario showed a considerable increase of about 60 % in the Built-up area until 2039. The vegetation plant areas consist about 47 % of all the area in 2019, but it will be 36 % in 2039, if this trend (urban expansion) continues in the further. The findings further indicated the major urban expansion in the vegetation areas. However, Built-up area would expand over Semi forest land and Dense forest land, with a large part of them changed into built- up areas.
PL
Celem badań jest ocena możliwości realizacji klasyfikacji nadzorowanej z wykorzystaniem obrazów (komponentów) uzyskiwanych w wyniku przetworzenia oryginalnych obrazów Sentinel-2A za pomocą metody głównych składowych (PCA). Klasyfikację wykonano w ośmiu wariantach, z wykorzystaniem algorytmów najmniejszej odległości (MD, Minimum Distance) oraz największego prawdopodobieństwa (ML, Maximum Likelihood), przy czym zastosowano oryginalne kanały 2, 3, 4, 8 Sentinel-2A oraz różną liczbę komponentów. Wyniki klasyfikacji oceniono poprzez porównanie z danymi o pokryciu terenu według Ewidencji Gruntów i Budynków (EGiB). Przeprowadzenie klasyfikacji na ograniczonej do dwóch liczbie komponentów uzyskanych w procedurze PCA tylko nieznacznie zmieniło wyniki w porównaniu do klasyfikacji na oryginalnych, nieprzetworzonych kanałach Sentinel-2A. Najbardziej zbliżone do danych EGiB rezultaty uzyskano stosując klasyfikację ML kanałów oryginalnych, nieprzetworzonych lub używając wszystkich komponentów PCA. Podjęta próba porównania pokrycia terenu ustalonego za pomocą klasyfikacji obrazów satelitarnych z klasami pokrycia, które zostały wyodrębnione z mapy EGiB wykazała, że przetworzenie mapy z postaci wektorowej na rastrową wpływa istotnie na uzyskiwane wyniki.
EN
The aim of the research is to assess the feasibility of supervised classification using images (components) obtained through processing the original Sentinel-2A images by means of the principal component method (PCA). The classification was performed in eight variants, using the algorithms of the minimum distance (MD) and the maximum likelihood (ML), with the original channels 2, 3, 4, 8 of Sentinel-2A and a various number of components. The results of the classification were assessed by comparing them to the land coverage data of Land and Buildings Register (Ewidencja Gruntów i Budynków – EGiB). Performing the classification on a number of PCA components limited to two only slightly altered the results compared to the classification on the original, raw Sentinel-2A channels. The results most similar to the EGiB data were obtained using the ML classification of the original channels, i.e. raw channels or using all PCA components. The attempt to compare the land coverage established by the classification of satellite images to the coverage classes that were extracted from the EGiB map revealed that processing the map from vector to raster form significantly influences the obtained results.
PL
Ostatnie 25 lat w Polsce cechują duże zmiany społeczno-gospodarcze, wyraźnie widoczne także w pokryciu i użytkowaniu terenu. W artykule przedstawiono charakterystykę ilościową, jakościową oraz przestrzenną zmian w pokryciu terenu, jakie zaszły w Polsce w latach 1990-2012, ze szczególnym zwróceniem uwagi na okresy: 1990-2000, 2000-2006 oraz 2006-2012. Analizy zostały wykonane na podstawie danych zgromadzonych w bazach CORINE Land Cover. Podstawowym celem badań była ocena zmian pokrycia terenu, które są następstwem zmian sposobu użytkowania ziemi w Polsce w okresie transformacji systemowej na przełomie XX i XXI wieku. Szczegółowo przeanalizowano przejmowanie gruntów rolnych i leśnych na budowę dróg oraz powiększanie terenów zabudowanych. Otrzymane wyniki pokazują, że powierzchnia zmian była stosunkowo niewielka i w żadnym z analizowanych okresów nie przekroczyła 1% powierzchni kraju. Zaobserwowano, że od 1990 roku następuje systematyczne zwiększanie terenów antropogenicznych głównie kosztem terenów rolniczych (gruntów ornych, sadów i plantacji oraz łąk i pastwisk) i zalesionych.
EN
The last 25 years in Poland are characterized by large socio-economic changes, clearly visible in the land cover. The article presents quantitative, qualitative and spatial characteristics of land cover changes in Poland in the years 1990-2012, with special attention paid to the periods 1990-2000, 2000-2006 and 2006-2012. The analyses base on CORINE land Cover data. The main objective of the study was to analyze the urbanization and accompanying land take of agricultural lands and forest for the construction of roads and the spread of built-up areas. The results show that the area of land cover changes was relatively small and it does not exceeded 1% of the country's territory. Since 1990 a systematic increase in anthropogenic areas is observed which is accompanying with afforestation, and decrease of arable lands.
EN
The objective of this paper is the assessment of the share of individual land cover categories in centric and ring-shaped evaluation polygons. In the analyses the data from the Corine Land Cover project for 2006 and 2012 were used. These data are available through the Urban Atlas. The basic spatial statistics concerning the land cover categories were determined. As a result of the analyses, information about land cover changes that took place over a period of 6 years was obtained, observed with increasing distance from the assumed reference point. An inference was also made regarding the possibility of determining the changes taking place in selected units in the period of 2006–2012.
PL
W ramach badań przeprowadzona została ocena stopnia udziału poszczególnych kategorii pokrycia w centrycznych poligonach oceny o kształcie pierścieni. Określono podstawowe statystyki przestrzenne dotyczące kategorii pokrycia terenu. Wykorzystano dane opracowane w ramach projektu Corine Land Cover dla roku 2006 i 2012, udostępnione poprzez Urban Atlas. W wyniku przeprowadzonych analizy otrzymano informacje o zmianach w pokryciu terenu, jakie zaszły w okresie 6 lat, w raz z oddalaniem się od przyjętego punktu odniesienia. Przeprowadzono także wnioskowanie dotyczące badania możliwości określenia zmian zachodzących w wybranych jednostkach w okresie od 2006 do 2012 roku.
EN
The aim of the study was to diagnose the main trends of the changes in land cover around the urban agglomerations, as illustrated with the example of Lublin, over the last twenty years (1998–2016), as well as their statistical and graphical presentation in the form of digital maps compilation. The project was conducted on the basis of the remote sensing data: RapidEye and LANDSAT 5 TM satellite imagery from three temporal records (1998, 2009–11, 2016–17). Detailed research was carried out in purposefully selected municipalities. The performed analyses showed that in the studied municipalities some changes in the use of arable land and grassland occurred. The largest loss in terms of area share was recorded mainly in the arable land. At the core of the metropolitan area, i.e. in the city of Lublin, over the last 20 years the share of arable land in the total area decreased by almost 11 percentage points (p.p.). In the municipalities located directly at the border with Lublin, this loss was much lower, and was equal 4–5 p.p. Slightly larger changes occurred in municipalities located further from the core, where both in the category of very good and slightly weaker natural conditions, losses of arable land were greater than in municipalities located directly at the core’s border of the metropolitan area (MA).
EN
The study discusses the changes in the land cover in the western part of the Zduńska Wola city. The study was based on the analysis of land cover data obtained from aerial photographs taken in years 1933 and 2015. For 82 years, significant changes took place in the city and they were reflected in land cover changes. The study area was covering 3.7 km2 and in the analysed period, the land cover changes took an area of 2.8 km², that is 75,7% of its surface. Changes mainly occurred on the grassy and agricultural areas, which were changed in to artificial surfaces, mainly into builtup areas.
PL
Celem artykułu jest analiz zmian pokrycia terenu wokół wybranych miast pofortecznych Śląska, na podstawie historycznych oraz współczesnych materiałów kartograficznych z użyciem oprogramowania GIS. Obszar badań obejmuje Nysę i Świdnicę, miasta na terenie których znajdują się nowożytne fortyfikacje oraz Oleśnicę, miasto nieposiadające w którym nigdy takich obwarowań nie było. Przeprowadzone badania pozwoliły określić wpływ fortyfikacji nowożytnych na rodzaj pokrycia otaczającego je terenu w okresie ponad 250 lat. Badania wykazały, że największe zmiany w formach pokrycia terenu wokół miasta związane były z likwidacją twierdzy i polegały głównie na wzroście powierzchni zabudowy miejskiej, rozwoju przemysłu i infrastruktury komunikacyjnej. Wyraźnie zmalała wówczas powierzchnia zieleni wysokiej i użytków zielonych. Wokół Oleśnicy nie zaobserwowano gwałtownych zmian w żadnym z badanych przedziałów czasowych, poza znacznym wzrostem powierzchni zabudowy miejskiej w pierwszej połowie XX w. We wszystkich badanych miastach na przełomie XX i XXI w. nastąpił duży wzrost powierzchni zabudowy miejskiej, infrastruktury i przemysłu, głównie kosztem powierzchni zieleni wysokiej oraz użytków zielonych.
EN
The aim of this study is the presentation of land cover changes around selected post-fortress cities located in Lower Silesia. The study is based on the historical and contemporary areas with the use of GIS. The area of the study includes the cities of Nysa and Świdnica, which have modern fortifications, and Oleśnica, a city which HAS never had this type of fortification.The study allowed the impact of modern fortifications on the type of land cover of surrounding areas and their changes, during over 250 years, to be determined. The study shows that the biggest changes in land use in all of the cities selected were connected with the liquidation of fortresses, and these were concerned mainly with the increase of urban areas, industrial areas, and transport areas. We can observe a decrease in forestry and grasslands. Around Oleśnica, we did not notice many changes, besides the increase of urban areas in the first half of the twentieth century. All cities at the turn of the 20th and 21st centuries saw a large increase in urban development, infrastructure, and industry, mainly at the expense of forestry and grasslands.
EN
The city of Lagos, Nigeria has undergone rapid increase in population due to economic and commercial activities. As a result of this, there has been a persistent change in Land use/Land cover (LULC) of the city and shoreline through the years. This observation necessitated the use of multi-temporal satellite data to characterize shoreline changes between 1984 and 2016. Therefore, the study attempts to determine the shoreline change during the study period and the coastal land use and land cover (LULC) of the study area. Satellite data was acquired and subjected to some image processing techniques such as image enhancement, supervised classification, and shoreline extraction. The digital shoreline analysis system (DSAS) in ArcGIS environment was utilized to cast transects and calculate statistical parameters for the shoreline and spatial data used was Landsat TM, ETM and OLI for the years 1984, 1990, 2000, 2004 and 2016 respectively. The results indicate that LULC changes in built-up areas increases rapidly during the years (1984-2015) from 12.2 -36.2%, water bodies increased from (1984-1990-2000) from 52%, 54%, 52% and reduces to 47.4% in the year 2015 while vegetation cover reduces drastically through the year range from 36%, 33%, 29%, 24% and 16%. A total of 1034 transects were generated with 100m spacing and the average rate of change was calculated for the 32 year period (1984-2016). The linear regression rate (LRR) shoreline result shows a mean of -0.59m/year where 73.1% of transect fall under erosion and 61.8% accretion respectively. The end point rate (EPR) and net shoreline movement (NSM) analysis revealed mean shoreline change of -0.57m/year and -18.1m/period respectively from 1984-2016. The EPR and NSM results both revealed that 231 transect or 22.3% experienced erosion, and 805 transect or 77.9% with accretion. It was observed that significant accretion rate recorded along most sections of the shorelines is attributed to beach nourishment activities.
PL
W pracy przedstawiono wpływ zmian w pokryciu terenu na stosunki wodne w zlewni cieku Bogdanki o powierzchni 51,9 km2. Przeprowadzone badania i analizy dostępnych materiałów kartograficznych wykazały, że w latach 1940–2012 na wskutek procesów urbanizacyjnych nastąpił znaczny wzrost terenów przekształconych antropogenicznie (z prawie 8% w roku 1940 do ponad 42% w 2012). Obszary zurbanizowane (zabudowa i szlaki komunikacyjne) przyczyniły się do uszczelnienia terenu a co za tym idzie do obniżenia zdolności retencyjnych zlewni o 0,25 mln m3. Zmniejszenie zdolności retencyjnych zlewni przyczyniło się do wzrostu wielkości opadu efektywnego P10% o 0,4 mm i P1% o 0,8 mm, co skutkowało wzrostem przepływów maksymalnych o prawdopodobieństwie przewyższenia 10% i 1% w cieku o ponad 20%.
EN
This work presents the impact of land cover on water relations in the catchment of the Bogdanka watercourse which is 51.9 km2. The research and analysis of available cartographic materials have shown a significant increase in the anthropogenically transformed areas due to urbanization from almost 8% in 1940 to over 42% in 2012. Urbanized areas (buildings and communication routes) have contributed to sealing the area and thus reduced retention capacity by 0.25 million m3. Therefore, the effective rainfall P10% and P1% have increased respectively by 0.4 mm and 0.8 mm. As a result the maximum flow of exceedance probability of 10% and 1% have reached over 20% in the Bogdanka watercourse.
EN
The aim of the study was to characterise and analyse the changes in the structure of the natural environment in the municipality of Pelplin, located in the Pomeranian province in northern Poland, in the years 1972-2014. The study is based on the analysis aerial photographs and cartographic materials. The specific objectives of the work was to re-create the land cover status in 1972 and 2014 and provide a graphical representation of changes in the land cover at the beginning and end of the analysed period. In effect, a differential map was produced. To sum up, the range of surface changes in the various categories of land use / land cover in relation to the space they occupied in 1972 should be ranked in the following order: grassland, areas with a transport function and roads, watercourses and reservoirs, built-up areas, plantings and bushes , forests , arable land. The only category which reduced its surface area included arable land, whereas other categories recorded an increase. Overall, the changes included 11.5 km2, i.e. 8.3 % of the municipality.
EN
Land development and consumption have spun out of control in major cities in Ghana. Kumasi as the second main and fastest growing city with an annual population growth rate of 5.4% in Ghana is experiencing this phenomenon. Land use/cover change in rural–urban peripheral is foremost to these dynamic changes. This study is premised on remote sensing and GIS methods to explore urbanization in Kumasi rural–urban fringe. Satellite data (Landsat multi-temporal images and Disaster Monitoring Constellation-DMC) and GIS techniques were used to analyze and compute the land cover changes (amount, trend and location) that had transpired for the period of 1986 to 2011. This study assesses the nature, extent and impact of urban growth (compact and sprawl) on Kumasi and surrounding districts. The study showed that, forest loss is massive, agricultural activities in Kumasi is receding as the years go but intensifying in the fringe districts. Settlements are expanding in all directions at the expense of farmland but firstly along the roads.
EN
One of the elements of the mineral deposit prospectivity analysis is the evaluation of land surface in terms of the conditions and possible restrictions on the potential exploitation of ores, which are connected with diverse forms of land use and protecting valuable nature areas. In the article the quantitative method of cartographic environmental analysis of the accessibility of mineral deposit areas is presented, based on the evaluation of land cover (CORINE Land Cover) and legal protected areas by the GIS system application. The core of the method is the point bonitation made in the specially calculated grid of elementary fields. The method was used to show and evaluate both the spatial planning and nature protection conditions for the potential exploitation in prospective areas of selected raw materials, such as: metal ores and gypsum, rock salt, K–Mg salts and native sulphur in Poland. The prospective areas with estimated resources were presented on maps at scale 1 : 200 000. The results are presented in the cartographic form, allowing appointing locations for mine investments.
19
Content available remote Próba budowy katastru słonecznego na obszarze miasta Zielona Góra
PL
W artykule przedstawiono możliwości wykorzystania danych pozyskanych metodą skaningu laserowego do budowy katastru słonecznego, umożliwiającego dostarczenie szczegółowych informacji na temat przydatności dachów budynków do montażu ogniw fotowoltaicznych. W artykule przybliżono funkcjonowanie wybranych, istniejących w Europie i na świecie, portali geoinformacyjnych zawierających dane dotyczące katastru słonecznego oraz podjęto próbę budowy katastru (mapy nasłonecznienia) dla fragmentu obszaru miasta Zielona Góra. W tym celu został wykorzystany numeryczny model pokrycia terenu zapisany w postaci rastrowej, uzupełniony o dane metrologiczne pozyskane dla omawianego obszaru oraz obrysy przyziemia budynków stanowiące element bazy danych obiektów topograficznych.
EN
The article presents possibilities of using data obtained by aerial laser scanning to make a portal containing detailed geographical information about building roofs on which photovoltaic cells could be installed. The article explains how selected geoportals containing data about solar cadastres work in Europe and in the other parts of the world. It also presents an attempt to prepare a solar cadastre (an insolation map) for a part of the town of Zielona Góra. For this purpose a numerical land cover model was used, presented in raster graphics, complemented with meteorological data obtained for the area under analysis as well as outlines of the ground levels of buildings as a component of the database of topographical objects.
20
Content available remote Remote Sensing Data Binary Classification Using Boosting with Simple Classifiers
EN
Boosting is a classification method which has been proven useful in non-satellite image processing while it is still new to satellite remote sensing. It is a meta-algorithm, which builds a strong classifier from many weak ones in iterative way. We adapt the AdaBoost.M1 boosting algorithm in a new land cover classification scenario based on utilization of very simple threshold classifiers employing spectral and contextual information. Thresholds for the classifiers are automatically calculated adaptively to data statistics. The proposed method is employed for the exemplary problem of artificial area identification. Classification of IKONOS multispectral data results in short computational time and overall accuracy of 94.4% comparing to 94.0% obtained by using AdaBoost.M1 with trees and 93.8% achieved using Random Forest. The influence of a manipulation of the final threshold of the strong classifier on classification results is reported.
first rewind previous Strona / 3 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.