Classification of Crops using Multitemporal Hyperion Images

2015-07-24
Teke, Mustafa
Çetin, Yasemin
In this study, multi-temporal Hyperion and Landsat 8 images from Eastern Turkey are used to classify wheat, alfalfa and sainfoin (Onobrychis). 9 Hyperion and 9 Landsat 8 images acquired at similar dates from year 2013 are used for both same and cross date classification of crops. Ministry of Agriculture, Food and Live Stock's farmer registration system (CKS, Ciftci Kayit Sistemi) records are used as ground truth after a refinement process. Preprocessing steps used for Hyperion data are presented. 100 samples from each class are input to the SVM and KNN classifiers. SVM classifier performs better than KNN. Landsat 8-launched in 2013-has better same date classification accuracy compared to Hyperion: 91.86% vs 88.94%. Cross date classification of crops with Hyperion and Landsat 8 images yielded lower cross date classification accuracy for both multispectral and hyperspectral images and only in certain periods such as harvest acceptable classification accuracies may be obtained.

Suggestions

A multi-temporal masking classification method for field-based agricultural crop mapping
Arıkan, Mahmut; Türker, Mustafa; Department of Geodetic and Geographical Information Technologies (2003)
This study describes the field-based classification of agricultural crops using multi-date Landsat 7 ETM+ images acquired in May, July, and August 2000. The study area is located in north-west of Turkey with a size of about 1 5 km x 1 1.3 km and grows a variety of crops. The objective was to identify the summer (August) crops within the agricultural fields. The classification methodology is based on a multi- temporal masking of Landsat 7 ETM+ images. First, a supervised per-pixel classification of the three...
Characterization of taxonomically related some Turkish oak (quercus l.) species in an isolated stand : a morphometric analysis approach
Aktaş, Caner; Kaya, Zeki; Department of Biology (2010)
The genus Quercus L. is represented with more than 400 species in the world and 18 of these species are found naturally in Turkey. Although its taxonomical, phytogeographical and dendrological importance, the genus Quercus is still taxonomically one of the most problematical woody genus in Turkish flora. In this study, multivariate morphometric approach was used to analyze oak specimens collected from an isolated forest (Beynam Forest, Ankara) where Quercus pubescens Willd., Q. infectoria Olivier subsp. boi...
Classification of Turkish Iris L.(Iridaceae) by phenetic methods
Usta, Erdoğan; Kence, Aykut; Department of Biology (2002)
In this study the present taxonomy of Turkish Iris L. were revised by using phenetic clustering method based on external vegetative and floral morphological characters of herbarium and fresh specimens. For this, 79 morphological characters for each taxon within the genus Iris L. were extracted and the data were analyzed by the NTSYSpc 2. 1 computer package by UPGMA method. In addition to this, cytological and biogeographical data of the taxa were also integrated into the new classification. The results of t...
Genetic characterization of pear cultivars (Pyrus communis) in Çoruh river basin
Çoban, Abdulbaki; Kaya, Zeki; Department of Molecular Biology and Genetics (2019)
The genus Pyrus contains more than 20 different pear species which are used as food source, horticultural, and ornamental purposes. Overall, pear is the second most consumed pome fruit after apple. P. communis is the most cultivated pear species in Europe and Asia Minor. However, more than 10 species of genus Pyrus can be found naturally in Europe and Asia Minor. In this study, 8 P. communis populations (one wild and 7 cultivated) and 1 P. eleagnifolia population was used to reveal genetic structure of thos...
Revision of Vicia L. (Leguminosae) in the Central Anatolia, Turkey
Binzat, Okan Kaan; Doğan, Musa; Department of Biology (2012)
In this revisional study based on the the genus Vicia in Central Anatolia large quantities of data have been compilled from specimens representing the group of the taxa being studied. These data were then synthesized to make taxon descriptions, keys, geographical distributions and ecological preferences. Since 2009, about 700 specimens have been collected from Central Anatolia and examined as the research materials. In addition, a large number of specimens have also been studied in the following herbaria AN...
Citation Formats
M. Teke and Y. Çetin, “Classification of Crops using Multitemporal Hyperion Images,” 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/54627.