Search



Show Advanced search options Hide Advanced search options
Urban vegetation classification with high-resolution PlanetScope and SkySat multispectral imagery
Published July 14, 2021
66-75

In this study two high-resolution satellite imagery, the PlanetScope, and SkySat were compared based on their classification capabilities of urban vegetation. During the research, we applied Random Forest and Support Vector Machine classification methods at a study area, center of Rome, Italy. We performed the classifications based on the spect...ral bands, then we involved the NDVI index, too. We evaluated the classification performance of the classifiers using different sets of input data with ROC curves and AUC values. Additional statistical analyses were applied to reveal the correlation structure of the satellite bands and the NDVI and General Linear Modeling to evaluate the AUC of different models. Although different classification methods did not result in significantly differing outcomes (AUC values between 0.96 and 0.99), SVM’s performance was better. The contribution of NDVI resulted in significantly higher AUC values. SkySat’s bands provided slightly better input data related to PlanetScope but the difference was minimal (~3%); accordingly, both satellites ensured excellent classification results.

Show full abstract
149
90
Spatial distribution of vegetation cover in Erbil city districts using high-resolution Pléiades satellite image
Published June 30, 2018
10-22

Green spaces are playing an essential role for ecological balance and for human health in the city as well.
They play a fundamental role in providing opportunities for relaxation and enjoying the beauty of nature
for the urban population. Therefore, it is important to produce detailed vegetation maps to assist planners
in designing str...ategies for the optimisation of urban ecosystem services and to provide a suitable plan
for climate change adaptation in one fast growing city. Hence, this research is an investigation using 0.5
m high-resolution multispectral Pléiades data integrated with GIS data and techniques to detect and
evaluate the spatial distribution of vegetation cover in Erbil City. A supervised classification was used
to classify different land cover types, and a normalised difference vegetation index (NDVI) was used
to retrieve it for the city districts. Moreover, to evaluate the accessibility of green space based on their
distance and size, a buffer zone criterion was used. The results indicate that the built-up land coverage
is 69% and vegetation land cover is 14%. Regarding NDVI results, the spatial distribution of vegetation
cover was various and, in general, the lowest NDVI values were found in the districts located in the city
centre. On the other hand, the spatial distribution of vegetation land cover regarding the city districts was
non-equal and non-concentric. The newly built districts and the districts far from the Central Business
District (CBD) recorded the lowest vegetation cover compared with the older constructed districts.
Furthermore, most of the districts have a lack of access to green spaces based on their distance and size.
Distance and accessibility of green areas throughout the city are not equally distributed. The majority of
the city districts have access to green areas within radius buffer of two kilometres, whereas the lowest
accessibility observed for those districts located in the northeast of the city in particular (Xanzad,
Brayate, Setaqan and Raperin). Our study is one of the first investigations of decision-making support
of the spatial planning in a fast-growing city in Iraq and will have a utilitarian impact on development
processes and local and regional planning for Erbil City in the future.

Show full abstract
107
0
Land cover analysis based on descriptive statistics of Sentinel-2 time series data
Published December 20, 2018
1-9

In our paper we examined the opportunities of a classification based on descriptive statistics of NDVI
throughout a year’s time series dataset. We used NDVI layers derived from cloud-free Sentinel-2 images
in 2018. The NDVI layers were processed by object-based image analysis and classified into 5 classes, in
accordance with Co...rine Land Cover (CLC) nomenclature. The result of classification had a 76.2% overall
accuracy. We described the reasons for the disagreement in case of the most remarkable errors. 

Show full abstract
270
32
Studying floodplain roughness in an Upper Tisza study area
Published July 14, 2021
85-90

Floods slowing down due to the significant decrease of the gradient have considerable sediment accumulation capacity in the floodplain. The grade of accumulation is further increased if the width of the floodplain is not uniform as water flowing out of the narrow sections diverge and its speed is decreased. Surface roughness in a study area of ...492 hectares in the Upper Tisza region was analysed based on CIR (color-infrared) orthophotos from 2007. An NDVI index layer was created first on which object-based image segmentation and threshold-based image classification were performed. The study area is dominated by land cover / land use types (grassland-shrubs, forest) with high roughness values. It was concluded that vegetation activity based analyses on their own are not enough for determining floodplain roughness.

Show full abstract
81
54
Specific features of NDVI, NDWI and MNDWI as reflected in land cover categories
Published September 15, 2016
194-202

The remote sensing techniques provide a great possibility to analyze the environmental processes in
local or global scale. Landsat images with their 30 m resolution are suitable among others for land
cover mapping and change monitoring. In this study three spectral indices (NDVI, NDWI, MNDWI) were
investigated from the aspect of land c...over types: water body (W); plough land (PL); forest (F); vineyard
(V); grassland (GL) and built-up areas (BU) using Landsat-7 ETM+ data. The range, the dissimilarities
and the correlation of spectral indices were examined. In BU – GL – F categories similar NDVI values
were calculated, but the other land cover types differed significantly. The water related indices (NDWI,
MNDWI) were more effective (especially the MNDWI) to enhance water features, but the values of other
categories ranged from narrower interval. Weak correlation were found among the indices due to the
differences caused by the water land cover class. Statistically, most land cover types differed from each
other, but in several cases similarities can be found when delineating vegetation with various water
content. MNDWI was found as the most effective in highlighting water bodies.

Show full abstract
483
0
1 - 5 of 5 items