Wyniki wyszukiwania - Biblioteka Nauki

1

Semiautomatic land cover mapping according to the 2nd level of the CORINE Land Cover legend

100%

Golenia M. , Zagajewski B. , Ochtyra A. , Hościło A.

Polish Cartographical Review

|

2015

|

tom Vol. 47, No. 4

203--212

EN

Actual land cover maps are a very good source of information on present human activities. It increases value of actual spatial databases and it is a key element for decision makers. Therefore, it is important to develop fast and cheap algorithms and procedures of spatial data updating. Every day, satellite remote sensing deliver vast amount of new data, which can be semi-automatically classified. The paper presents a method of land cover classification based on a fuzzy artificial neural network simulator and Landsat TM satellite images. The latest CORINE Land Cover 2012 polygons were used as reference data. Three satellite images acquired 21 April 2011, 5 June 2010, 27 August 2011 over Warsaw and surrounding areas were processed. As an outcome of classification procedure, the maps, error matrices and a set of overall, producer and user accuracies and a kappa coefficient were achieved. The classification accuracy oscillates around 76% and confirms that artificial neural networks can be successfully used for forest, urban fabric, arable land, pastures, inland waters and permanent crops mapping. Low accuracies were obtained in case of heterogenic land cover units.

2

Zastosowanie sztucznych sieci neuronowych do aktualizacji map pokrycia terenu Corine

100%

Golenia M. , Zagajewski B. , Ochtyra A. , Hościło A.

|

tom T. 47, nr 3-4

257--266

PL

Aktualne mapy pokrycia terenu są podstawą wielu dyscyplin nauki oraz mają szerokie zastosowanie aplikacyjne. Jednym z problemów aktualizacji map jest proces aktualizacji danych. Teledetekcja dostarcza codziennie nowych zobrazowań satelitarnych, które mogą zaspokoić potrzeby aktualizacji baz danych. W niniejszym artykule autorzy przedstawiają metodę klasyfikacji pokrycia terenu sztucznymi sieciami neuronowymi fuzzy ARTMAP zgodnie z założeniami i legendą Corine Land Cover na podstawie danych satelitarnych Landsat, które wykorzystywane są do opracowania map pokrycia terenu. W artykule użyto jako danych referencyjnych i weryfikacyjnych najnowszą mapę Corine Land Cover (CLC) 2012. Do przeprowadzenia klasyfikacji symulatorem wykorzystano trzy zdjęcia satelitarne Landsat TM (21.04.2011, 05.06.2010, 27.08.2011). Obszarem badań były okolice Warszawy. Wynikami pracy symulatora są mapy klasyfikacji pokrycia terenu oraz macierze błędów klasyfikacji. Uzyskane wyniki potwierdzają, że sztuczne sieci neuronowe mogą z powodzeniem być wykorzystywane do aktualizacji map pokrycia terenu.

EN

Modern land cover maps are the basis of many scientific disciplines and they are widely applied. One of the problems connected with the revision of maps is the data updating procedure. Remote Sensing daily provides us with the new satellite images, that can meet the needs of database updates. In this article the method of classification for land cover with the artificial, neural, fuzzy ARTMAP networks is presented by the authors in accordance with the objectives and legend of the CORINE Land Cover Map on the basis of the Landsat satellite data, which are used to elaborate the land cover maps. The latest CORINE Land Cover map 2012 polygons are used as the reference and verification data. Three satellite Landsat TM images of 21.04.2011, 05.06.2010, 27.08.2011 are processed by a fuzzy, artificial, neural network classificatory simulator. The area of research was Warsaw and its surrounding area. The results of this research are the classificatory land cover maps and error matrices. Acquired results confirm that the artificial neural networks can be successfully used for land cover updating.

3

Mapa geomorfologiczna województw pomorskiego i warmińsko-mazurskiego z wykorzystaniem metod geoinformatycznych

88%

Marcinkowska A. , Ochtyra A. , Olędzki J. R. , Wołk-Musiał E. , Zagajewski B.

Teledetekcja Środowiska

|

2013

|

tom T. 49

43--79

EN

The aim of this study was to prepare geomorphological maps of pomorskie and warminsko-mazurskie voivodeships in scale 1:300 000. Analysis primarily were based on the General Geomorphological Map of Poland 1:500 000 and Landsat 5 TM satellite images in RGB 453 composition, and alternatively with Geological Map of Poland 1:200 000, Topographic Map of Poland 1:100 000 and Digital Terrain Model from Shuttle Radar Topography Mission. These materials were processed into digital form and imported them PUWG 1992 coordinate system. Based on them was lead interpretation and vectorization of geomorphological forms. It was detailing the boundaries in accordance with the content of the General Geomorphological Map of Poland 1:500 000. Then polygons were coded according to the numbering of J. Borzuchowski (2010). Very important was process to design a legend and then editing maps. The last stage of this study was to prepare a composition for printing maps. The effect of studies are geomorphological maps of pomorskie and warminsko-mazurskie voivodeships in scale 1:300 000, and an interactive databases in ESRI shapefile format (*.shp).

4

Ocena kondycji drzewostanów Tatrzańskiego Parku Narodowego za pomocą metody drzewa decyzyjnego oraz wielospektralnych obrazów satelitarnych Landsat 5 TM

88%

Ochtyra A. , Zagajewski B. , Kozlowska A. , Marcinkowska-Ochtyra A. , Jarocinska A.

|

tom 160

|

nr 03

EN

The paper presents a method of Landsat 5 Thematic Mapper satellite image processing to assess the condition of forests in the Tatra National Park (southern Poland). Selected images were acquired on 1987/09/01, 2005/09/02 and 2011/09/03 from the same sensor with maximum time interval for the first and last scene and from similar phenological period. Firstly, the data were radiometrically corrected using the ATCOR 2/3 software and Digital Terrain Model from the ASTER mission. Quality of the correction was assessed calculating RMSE for reflectance values from images and resampled spectral characteristics collected in terrain. RMSE was in range 3−10%. Next, basing on Landsat images, Normalized Difference Infrared Index (NDII) and a Maximum Likelihood supervised classificatory, following dominant land cover types were identified: forests (including dwarf pine), grasslands, rocks, lakes, shadows (additionally clouds were distinguished on data from 1987/09/01). It allowed to select forest areas with producer accuracy not worse than 97.69% and user accuracy not worse than 98.31%. On corrected Landsat images Normalized Difference Vegetation Index (NDVI, an overall vegetation state) and Moisture Stress Index (MSI, canopy water content) were calculated. Vegetation indices discriminated forest state using the decision tree method. The worst overall condition was observed for the 1987 (about 21% of forest stands were in the worst condition and 87% were in medium condition), while the best one in 2005 (75.51% forest stands were in good condition and 10.66% were in the best condition). In case of 2011, the overall condition was quite good, but there were large areas with poor condition caused by bark beetle outbreaks. Proposed method allows for a fast and objective assessment of forest condition. It is possible to detect damaged areas or stands in poor condition. It can be complement for traditional methods of monitoring and management in forestry and nature protection.

5

Określenie składu gatunkowego lasów Góry Chojnik (Karkonoski Park Narodowy) z wykorzystaniem lotniczych danych hiperspektralnych APEX

75%

Raczko E. , Zagajewski B. , Ochtyra A. , Jarocinska A. , Marcinkowska-Ochtyra A. , Dobrowolski M.

|

nr 07

EN

We used hyperspectral data from APEX scanner (288 spectral bands in 380−2500 nm spectral range; 3,5 m spatial resolution) to classify five tree species occurring in the area of Mt. Chojnik in the Karkonoski National Park (south−western Poland). Data used to delimit learning and veri− fication polygons were acquired during field research in August 2013, when ground truth polygons were acquired using device equipped with GPS receiver. Raw APEX data went through radio− metric and geometric correction at VITO office. To reduce processing time, 40 most informative bands were selected using information content analysis. The Support Vector Machines (SVM) algorithm was used for classification of the following tree species: Fagus sylvatica L., Betula pendula Roth, Pinus sylvestris L., Picea alba L. Karst and Larix decidua Mill. Final classification had 78.66% overall accuracy with Kappa coefficient equal to 0.71. The best classified species included beech (87.09%) and pine (83.96%), while the worst results were obtained for larch (60.29%). Low accuracy for larch could be caused by the fact that most of larch trees in the research area grow in small patches, which made it hard to specify large enough sample of training data. All classified tree species had producer's accuracy of at least 60%, with the highest value reaching 87%. User's accuracies were from 53% for pine to 85% for beech. It is possible to classify tree species using hyperspectral data with moderate to high accuracy even if the data used lacked atmospheric correction. Further work will focus on improving the classification accuracy and use of neural networks based classification methods. Results from this paper will serve as basis for tree species map of the Karkonoski National Park.