Have a personal or library account? Click to login
Analysis of Built-Up Classes in Urbanised Zones Using Radar Images Cover

Analysis of Built-Up Classes in Urbanised Zones Using Radar Images

Quaestiones Geographicae
Volume 42 (2023): Issue 3 (September 2023)
By: Joanna Pluto-Kossakowska and  Joanna Giczan  
Open Access
|Sep 2023

Figures & Tables

Fig. 1.

The extent of Gdynia’s boundary (purple lines) on the VV ICEYE image (right) and the visualisation of the UA database in the study area according to the UA legend (left). UA, Urban Atlas.
The extent of Gdynia’s boundary (purple lines) on the VV ICEYE image (right) and the visualisation of the UA database in the study area according to the UA legend (left). UA, Urban Atlas.

Fig. 2.

Sentinel-1 variables selected for classification. The same representative example for the Continuous urban fabric CUF class shown on orthophotomap in Fig. 5.
Sentinel-1 variables selected for classification. The same representative example for the Continuous urban fabric CUF class shown on orthophotomap in Fig. 5.

Fig. 3.

Results of supervised classification by RF (upper) and MD (lower) for Sentinel-1 with UA class outlines. The fragment shows the representation and variety of different classes in the area. The same legend is applicable as was mentioned in Table 2.
Results of supervised classification by RF (upper) and MD (lower) for Sentinel-1 with UA class outlines. The fragment shows the representation and variety of different classes in the area. The same legend is applicable as was mentioned in Table 2.

Fig. 4.

RF (100 trees) classification result on Sentinel-1 before (upper) and after aggregation to four classes (lower). Example of Port area (PA) class differentiation. The same legend is applicable as was mentioned in Table 2.
RF (100 trees) classification result on Sentinel-1 before (upper) and after aggregation to four classes (lower). Example of Port area (PA) class differentiation. The same legend is applicable as was mentioned in Table 2.

Fig. 5.

ICEYE variables selected for classification and contours of the Continuous urban fabric CUF class (as a representative example). The right-bottom orthophoto shows the scale and shape of features.
ICEYE variables selected for classification and contours of the Continuous urban fabric CUF class (as a representative example). The right-bottom orthophoto shows the scale and shape of features.

Fig. 6.

Results of classification using RF (upper) and MD (lower) on ICEYE image with UA class borders. The same legend is applicable as was mentioned in Table 2. This representative example shows the diversity of classes.
Results of classification using RF (upper) and MD (lower) on ICEYE image with UA class borders. The same legend is applicable as was mentioned in Table 2. This representative example shows the diversity of classes.

Fig. 8.

Comparison of Sentinel-1 (upper) and ICEYE (lower) results based on MD classifier, after class aggregation. The same legend is applicable as was mentioned in Table 2. This representative example shows the diversity of classes.
Comparison of Sentinel-1 (upper) and ICEYE (lower) results based on MD classifier, after class aggregation. The same legend is applicable as was mentioned in Table 2. This representative example shows the diversity of classes.

Fig. 7.

Overall classification accuracy (total and kappa) based on RF and MD classifiers for Sentinel-1 (S1, in green colours) and ICEYE (brown-orange colours).
Overall classification accuracy (total and kappa) based on RF and MD classifiers for Sentinel-1 (S1, in green colours) and ICEYE (brown-orange colours).

Urban Atlas classes selected for the study_ These code names and colours have been used in the forth-coming presentation of results_

Class nameSealed Level (SL)Codename and colour on imagesName and colour of aggregated classes
Continuous urban fabric>80%CUFDense urban area
Discontinuous dense urban fabric50–80%DDUF
Discontinuous medium density urban fabric30–50%DMDUF
Discontinuous low density urban fabric10–30%DLDUFLow density urban area
Discontinuous very low density urban fabric<10%DVLDUF
Isolated structures IS
Port areas PAIndustrial area
Industrial, commercial, public, military and private units ICPMAPU
Arable land (annual crops) ALVegetation
Forests F
Pastures P
UA class borders

Specification of the SAR data used in the study_

SensorDateBandPolarisationOrbitModeSpatial resolution after corrections and resampling
ICEYE19.04.2019X (3 cm)VVAscendingSM2 m
Sentinel-127.12.2018C (5 cm)VH + VVDescendingIW10 m

Comparison of classification results in different images and different algorithms for discontinuous low and very low density urban fabric, both in low density urban area class; these representative examples visualise a general pattern_

Discontinuous low density urban fabric
orthophotomapDense urban areaLow density urban areaIndustrial areaVegetationUrban Atlas feature
Sentinel-1ICEYE
Random Forests
Minimum Distance
Discontinuous very low density urban fabric
orthophotomap
Sentinel-1ICEYE
Random Forests
Minimum Distance

Sentinel-1 image classification accuracy by RF (top) and MD (bottom) algorithms – both results after aggregation_

Class valueVegetationDense urbanLow dens. urbanIndustrialTotalU_AccuracyKappa
RF classification
Vegetation6855821708340.8210
Dense urban2914051623360.4170
Low dens. urban1966617983770.0450
Industrial2810323214540.7070
Total93836745651200100
P_Accuracy0.7300.3810.3780.49300.5810
Kappa0000000.398
MD classification
Vegetation7476321578880.8410
Dense urban3214431182970.4850
Low dens. urban14156211143320.0630
Industrial1810403624840.7480
Total93836745651200100
P_Accuracy0.7960.3920.4670.55600.6370
Kappa0000000.468

Comparison of classification results in different images and different algorithms for Continuous urban fabric class and discontinuous dense urban fabric, both in one dense urban area class; these representative examples visualise a general pattern_

Continuous urban fabric
orthophotomapDense urban areaLow density urban areaIndustrial areaVegetationUrban Atlas feature
Sentinel-1ICEYE
Random Forests
Minimum Distance
Discontinuous dense urban fabric
orthophotomap
Sentinel-1ICEYE
Random Forests
Minimum Distance
DOI: https://doi.org/10.14746/quageo-2023-0032 | Journal eISSN: 2081-6383 | Journal ISSN: 2082-2103
Journal RSS Feed
Language: English
Page range: 195 - 211
Submitted on: Jan 3, 2023
Published on: Sep 7, 2023
Published by: Adam Mickiewicz University
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year
Keywords:
urban area,
texture analysis,
GLCM,
supervised classification,
Urban Atlas
Related subjects:
Geosciences,
Geography

© 2023 Joanna Pluto-Kossakowska, Joanna Giczan, published by Adam Mickiewicz University
This work is licensed under the Creative Commons Attribution 4.0 License.

Previous articleVolume 42 (2023): Issue 3 (September 2023)Next article