Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 1

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  training samples
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
It is the most beneficial to apply geomatics to research projects for which the spatial aspect of data is important. Tools offered by GIS improve collection of spatial data, their modifications and analysis. Moreover, when large spatial data sets of various types are considered, it becomes even more important to refer to geomatics. Simultaneous analysis of digital maps, satellite images, aerial photos, feature data base and multimedia, requires special tools which are offered by GIS software. The aim of this paper is to present an example of the application of geomatics to a research project. The project is aimed at an investigation of crop recognition on microwave satellite images. In this project, GIS software on desktop and mobile platforms were applied to spatial data collection and analysis. One of the most important tasks of the project is to classify the content of satellite images. This task is related to the collection of appropriate ground data. The classification method used in the project belongs to supervised methods. In supervised approach it is necessary to collect samples representing each class on the image. These samples allow to train the classifier and help to determine the decision boundaries in the feature space defined by satellite images. The quality of final classification results depends on how adequately these training samples are selected. In the case of crop recognition on satellite images, training samples for various crops are initially specified in the study area. Next, pixels representing selected sample areas are identified on satellite images. More than 30 training samples are needed for each crop class in order to satisfy statistical requirements. Moreover, the validation of classifier requires a set of independent validation samples. On the whole, 700 fields covered by unique crops were selected in the study area. It has been assumed that only fields with an area larger than 5 hectares can form training and validation sets. The record of crop type and several parameters characterizing crop condition or its phenological phase for each of these fields were taken during the visits to the test site. Data collection was correlated with satellite overpasses and repeated during the consecutive acquisitions of images within the whole crop growth season. The project started in 2003 and was continued in 2004 and 2005. Each year the set of sample fields was slightly different. Due to crop rotation and other farming practices, the selection of crop representation varied from one year to another. Moreover, the boundaries of some of the fields had to be modified and a full record of these modifications was kept in the project database. The initial version of field geometry was obtained by digitization of crop boundaries on a LANDSAT ETM image. This initial layer was updated during the field campaign using a palmtop with GPS receiver and ARCPad software. GIS tools helped to define the boundaries of sample fields and to register all estimated or measured parameters which characterized crops in the fields. GIS tools were used during the initial phase of the project, as well as at the subsequent steps of spatial data handling. The following tasks were completed using GIS ARCMap software: collection of spatially oriented microwave satellite images which were acquired during the crop growth season; collection of thematic maps for the study area . DTM, soil map etc.; processing of thematic maps aimed on derivation of some useful products like for example maps of slope and aspect based on DTM; management of images showing various phases of crop development in the study area; creation of the relational database which contains descriptive data referring to the fields. Crop recognition on microwave images is based on the assumption that different types of crops backscatter microwave uniquely, giving a "spectral signature". Average values of microwave response registered in satellite image within the boundaries of the training fields were used as crop signatures in the project. These signatures were calculated using zonal functions available in GIS software. Afterwards, crop signatures were assembled in the relational database and classified using other software. GIS tools were also used for the assessment of classification results. Geostatistical analysis made it possible to look for any spatial bias of crop recognition results. Geostatistical tools also help to investigate the influence of spatially distributed factors on crop classification.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.