Abstract
Mapping and monitoring of urban land cover are becoming increasingly important in the face of ongoing climate change. The recently launched pair of Sentinel-2 satellites regularly delivers images with the highest spectral and spatial resolution among the freely available images. Based on these data, we proposed an object-based classification method for urban land-cover mapping at two basic scale levels. The proposed set of classification rules is transferable to different urban areas without the need to collect training samples. The inevitable problem of different spectral characteristics of vegetation in individual areas is solved by computing the area-specific thresholds using the central values of forest stands and grasslands read out of the histogram. Special features summarising the normalised difference vegetation index (NDVI) time-series using the Google Earth Engine platform were designed to distinguish cropland from other classes. The transferability of the rule sets was verified in six Central European cities with different climatic conditions—Bratislava, Nitra, and Žilina (Slovakia), Zakopane (Poland), and Kaposvár and Orosháza (Hungary). The overall classification accuracy reached 78–90% in each tested area at the first hierarchical level, and 76–89% on the second level, respectively. The performance of the methodology was compared with the random forest (RF) machine learning method with training samples collected in Bratislava. The results confirmed that without area-specific training samples, the accuracy of the RF method is 5–35 percentage point (p.p.) lower than the accuracy of the proposed rule-based method. In addition, without the NDVI summary indices, the accuracy of the RF classifier decreased by another 10–30 p.p.
Zusammenfassung
Hierarchische objektbasierte Kartierung städtischer Bodenbedeckungen mit Sentinel-2 Data: Eine Fallstudie anhand von sechs Städten Mitteleuropas. Die Kartierung und Überwachung der städtischen Bodenbedeckung wird in Hinblick auf den Klimawandel immer wichtiger. Das vor einiger Zeit gestartete Sentinel-2-Satellitenpaar liefert regelmäßig Bilder, die unter den frei verfügbaren die höchste spektrale und räumliche Auflösung bieten. Basierend auf diesen Daten schlagen wir eine objektorientierte Klassifizierungsmethode für städtische Bodenbedeckungen vor und orientieren uns dabei an zwei Maßstäben. Die vorgeschlagenen Klassifizierungsregeln lassen sich auf unterschiedliche Stadtgebiete ohne neue Trainingsdaten übertragen. Das unvermeidliche Problem der unterschiedlichen spektralen Merkmale der Vegetation auf unterschiedlichen Flächen wird durch Umwandlung der aus dem Histogramm abgelesenen Zentralwerte in flächenspezifische Schwellenwerte bei der Entscheidungsfindung gelöst. Spezielle Algorithmen wurden zur Auswertung der NDVI (Normalised Differenence Vegetation Index)- Zeitreihe auf Basis von Google Earth entwickelt, um Ackerland von anderen Klassen zu unterscheiden. Die Anwendbarkeit der Regeln wurde an sechs mitteleuropäischen Städten mit unterschiedlichen klimatischen Bedingungen verifiziert, und zwar in Bratislava, Nitra und Žilina (alle Slowakei) und Zakopane (Polen) sowie Kaposvár und Orosháza (beide Ungarn). Die Gesamtklassifizierungsgenauigkeit erreichte überall 78% – 90% auf der ersten Hierarchieebene und 76% – 89% auf der zweiten. Die Leistungsfähigkeit unserer Methode wurde mit der Random Forest Methode (RF) und Trainingsgebieten in Bratislava verglichen. Die Ergebnisse zeigten, dass ohne flächenspezifische Trainingsgebiete die Genauigkeit der RF-Methode 5 bis 35 Prozentpunkte geringer als die Genauigkeit unserer vorgeschlagenen regelbasierten Methode ist. Ohne die Zusammenfassung der NDVI-Indizes ist die Genauigkeit der RF-Klassifikation noch einmal um 10 bis 30 Prozentpunkte geringer.
Similar content being viewed by others
References
Baatz M, Schäpe A (2000) Multiresolution Segmentation: an optimization approach for high quality multi-scale image segmentation. Angewandte Geographische Informationsverarbeitung XII Beiträge zum AGIT-Symposium Salzburg 2000, Karlsruhe, Herbert Wichmann Verlag pp 12–23, DOI Export Date 6 May 2013
Baker F, Smith CL, Cavan G (2018) A combined approach to classifying land surface cover of urban domestic gardens using citizen science data and high resolution image analysis. Remote Sens 10:4. https://doi.org/10.3390/rs10040537
Bangira T, Alfieri SM, Menenti M, van Niekerk A (2019) Comparing thresholding with machine learning classifiers for mapping complex water. Remote Sens 11:11. https://doi.org/10.3390/rs11111351
Blaschke T, Lang S, Hay J (eds) (2008) Object-based image analysis: spatial concepts for knowledge-driven remote sensing applications. Springer, Berlin
Chatziantoniou A, Petropoulos GP, Psomiadis E (2017) Co-Orbital Sentinel 1 and 2 for LULC mapping with emphasis on wetlands in a mediterranean setting based on machine learning. Remote Sens 9:12. https://doi.org/10.3390/rs9121259
Dennis M, Barlow D, Cavan G, Cook P, Gilchrist A, Handley J, James P, Thompson J, Tzoulas K, Wheater CP, Lindley S (2018) Mapping urban green infrastructure: a novel landscape-based approach to incorporating land use and land cover in the mapping of human-dominated systems. Land 7(1):17. https://doi.org/10.3390/land7010017
Drǎguţ L, Tiede D, Levick SR (2010) ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. Int J Geogr Inf Sci 24(6):859–871. https://doi.org/10.1080/13658810903174803
Formaggio A, Vieira M, Rennó C, Aguiar D, Mello M (2010) Object-Based Image Analysis and Data Mining for mapping sugarcane with Landsat imagery in Brazil. Int Arch Photogram Rem Sens Spatial Inf Sci SPRS Arch 38:4C7
Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R (2017) Google earth engine: planetary-scale geospatial analysis for everyone. Remote Sens Env 202:18–27. https://doi.org/10.1016/j.rse.2017.06.031
Gupta K, Kumar P, Pathan SK, Sharma KP (2012) Urban neighborhood green index—a measure of green spaces in urban areas. Landsc Urban Plan 105(3):325–335. https://doi.org/10.1016/j.landurbplan.2012.01.003
Hao PY, Tang HJ, Chen ZX, Yu L, Wu MQ (2019) High resolution crop intensity mapping using harmonized Landsat-8 and Sentinel-2 data. J Integr Agric 18(12):2883–2897. https://doi.org/10.1016/S2095-3119(19)62599-2
Haralick R, Shanmugan K, Dinstein I (1973) Textural features for image classification. https://doi.org/10.1109/TSMC.1973.4309314
Heupel K, Spengler D, Itzerott S (2018) A progressive crop-type classification using multitemporal remote sensing data and phenological information. PFG J Photogram Remote Sens Geoinf Sci 86(2):53–69. https://doi.org/10.1007/s41064-018-0050-7
Immitzer M, Vuolo F, Atzberger C (2016) First experience with Sentinel-2 data for crop and tree species classifications in central Europe. Remote Sens 8:3. https://doi.org/10.3390/rs8030166
Jebur MN, Mohd Shafri HZ, Pradhan B, Tehrany MS (2014) Per-pixel and object-oriented classification methods for mapping urban land cover extraction using SPOT 5 imagery. Geocarto Int 29(7):792–806. https://doi.org/10.1080/10106049.2013.848944
Kalantar B, Mansor SB, Sameen MI, Pradhan B, Shafri HZ (2017) Drone-based land-cover mapping using a fuzzy unordered rule induction algorithm integrated into object-based image analysis. Int J Remote Sens 38(8–10):2535–2556. https://doi.org/10.1080/01431161.2016.1277043
Khatami R, Mountrakis G, Stehman SV (2016) A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: general guidelines for practitioners and future research. Remote Sens Env 177(March):89–100. https://doi.org/10.1016/j.rse.2016.02.028
Labib SM, Harris A (2018) The potentials of Sentinel-2 and LandSat-8 data in green infrastructure extraction, using object based image analysis (OBIA) method. Eur J Remote Sens 51(1):231–240. https://doi.org/10.1080/22797254.2017.1419441
Labib SM, Lindley S, Huck JJ (2020) Spatial dimensions of the influence of urban green-blue spaces on human health: a systematic review. Environ Res 180(2019):108869. https://doi.org/10.1016/j.envres.2019.108869
Lauriola P (2016) Introduction. In: Musco F (ed) Counteracting urban heat Island effects in a global climate change scenario. Springer, eBook, pp xlvii–liii
Lawrence RL, Moran CJ (2015) The AmericaView classification methods accuracy comparison project: a rigorous approach for model selection. Remote Sens Env 170:115–120. https://doi.org/10.1016/j.rse.2015.09.008
Lefebvre A, Sannier C, Corpetti T (2016) Monitoring urban areas with sentinel-2A data: application to the update of the copernicus high resolution Layer Imperviousness Degree. Remote Sens 8(7):606. https://doi.org/10.3390/rs8070606
Ma L, Li M, Ma X, Cheng L, Du P, Liu Y (2017) A review of supervised object-based land-cover image classification. ISPRS J Photogram Rem Sens 130:277–293. https://doi.org/10.1016/j.isprsjprs.2017.06.001
Malinowski R, Lewiński S, Rybicki M, Jenerowics M, Gromny E, Krupiński M, Wojtkowski C, Krupiński M, Günther S, Krätzschmar E (2019) S2GLC Final Report. Tech. Rep. 1, Centrum Badań Kosmicznych PAN. https://doi.org/10.1017/CBO9781107415324.004
Markevych I, Schoierer J, Hartig T, Chudnovsky A, Hystad P, Dzhambov AM, de Vries S, Triguero-Mas M, Brauer M, Nieuwenhuijsen MJ, Lupp G, Richardson EA, Astell-Burt T, Dimitrova D, Feng X, Sadeh M, Standl M, Heinrich J, Fuertes E (2017) Exploring pathways linking greenspace to health: theoretical and methodological guidance. Environ Res 158(June):301–317. https://doi.org/10.1016/j.envres.2017.06.028
Mathieu R, Freeman C, Aryal J (2007) Mapping private gardens in urban areas using object-oriented techniques and very high-resolution satellite imagery. Landsc Urban Plan 81(3):179–192. https://doi.org/10.1016/j.landurbplan.2006.11.009
Maxwell AE, Warner TA, Fang F (2018) Implementation of machine-learning classification in remote sensing: an applied review. Int J Remote Sens 39(9):2784–2817. https://doi.org/10.1080/01431161.2018.1433343
Maxwell AE, Strager MP, Warner TA, Ramezan CA, Morgan AN, Pauley CE (2019) Large-area, high spatial resolution land cover mapping using random forests, GEOBIA, and NAIP orthophotography: findings and recommendations. Remote Sens 11:12. https://doi.org/10.3390/rs11121409
Miettinen J, Shi C, Liew SC (2019) Towards automated 10–30 m resolution land cover mapping in insular South-East Asia. Geocarto Int 34(4):443–457. https://doi.org/10.1080/10106049.2017.1408700
Millard K, Richardson M (2015) On the importance of training data sample selection in Random Forest image classification: a case study in peatland ecosystem mapping. Remote Sens 7(7):8489–8515. https://doi.org/10.3390/rs70708489
Mngadi M, Odindi J, Peerbhay K, Mutanga O (2019) Examining the effectiveness of Sentinel-1 and 2 imagery for commercial forest species mapping. Geocarto Int 2019:1–12. https://doi.org/10.1080/10106049.2019.1585483
Momeni R, Aplin P, Boyd DS (2016) Mapping complex urban land cover from spaceborne imagery: the influence of spatial resolution, spectral band set and classification approach. Remote Sens 8:2. https://doi.org/10.3390/rs8020088
Moskal LM, Styers DM, Halabisky M (2011) Monitoring urban tree cover using object-based image analysis and public domain remotely sensed data. Remote Sens 3(10):2243–2262. https://doi.org/10.3390/rs3102243
Myint SW, Gober P, Brazel A, Grossman-Clarke S, Weng Q (2011) Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sens Env 115(5):1145–1161. https://doi.org/10.1016/j.rse.2010.12.017
Nichol J, Wong MS (2007) Remote sensing of urban vegetation life form by spectral mixture analysis of high-resolution IKONOS satellite images. Int J Remote Sens 28(5):985–1000. https://doi.org/10.1080/01431160600784176
Olofsson P, Foody GM, Herold M, Stehman SV, Woodcock CE, Wulder MA (2014) Good practices for estimating area and assessing accuracy of land change. Remote Sens Env 148:42–57. https://doi.org/10.1016/j.rse.2014.02.015
Pan Z, Huang J, Zhou Q, Wang L, Cheng Y, Zhang H, Blackburn GA, Yan J, Liu J (2015) Mapping crop phenology using NDVI time-series derived from HJ-1 A/B data. Int J Appl Earth Observ Geoinf 34:188–197. https://doi.org/10.1016/j.jag.2014.08.011
Pauleit S, Ennos R, Golding Y (2005) Modeling the environmental impacts of urban land use and land cover change—A study in Merseyside, UK. Landsc Urban Plan 71(2–4):295–310. https://doi.org/10.1016/j.landurbplan.2004.03.009
Pesaresi M (2000) Texture analysis for urban pattern recognition using fine-resolution panchromatic satellite imagery. Geogr Environ Modell 4(1):43–63. https://doi.org/10.1080/136159300111360
Pesaresi M, Gerhardinger A, Kayitakire F (2008) A robust built-up area presence index by anisotropic rotation-invariant textural measure. IEEE J Sel Top Appl Earth Observ Remote Sens 1(3):180–192. https://doi.org/10.1109/JSTARS.2008.2002869
Pesaresi M, Corbane C, Julea A, Florczyk AJ, Syrris V, Soille P (2016) Assessment of the added-value of sentinel-2 for detecting built-up areas. Remote Sens 8:4. https://doi.org/10.3390/rs8040299
Phiri D, Morgenroth J (2017) Developments in Landsat land cover classification methods: a review. Remote Sens 9:9. https://doi.org/10.3390/rs9090967
Puissant A, Rougier S, Stumpf A (2014) Object-oriented mapping of urban trees using Random Forest classifiers. Int J Appl Earth Observ Geoinf 26:235–245. https://doi.org/10.1016/j.jag.2013.07.002
Qiu C, Mou L, Schmitt M, Zhu XX (2019) Local climate zone-based urban land cover classification from multi-seasonal Sentinel-2 images with a recurrent residual network. ISPRS J Photogram Remote Sens 154:151–162. https://doi.org/10.1016/j.isprsjprs.2019.05.004
Radoux J, Bogaert P, Fasbender D, Defourny P (2011) Thematic accuracy assessment of geographic object-based image classification. Int J Geogr Inf Sci 25(6):895–911. https://doi.org/10.1080/13658816.2010.498378
Robinson C, Hou L, Malkin K, Soobitsky R, Czawlytko J, Dilkina B, Jojic N (2019) Large scale high-resolution land cover mapping with multi-resolution data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12726–12735
Rosina K, Kopecká M (2016) Mapping of urban green spaces using sentinel-2a Data: methodical aspects. In: Proceedings of 6th international conference on cartography and GIS, Albena, Bulgaria
Rouse J, Haas R, Scheel J, Deering D (1974) Monitoring Vegetation Systems in the Great Plains with ERTS. In: Proceedings, 3rd earth resource technology satellite (ERTS) symposium, Vol 1, pp 48–62
Salehi B, Zhang Y, Zhong M, Dey V (2012) Object-based classification of urban areas using VHR imagery and height points ancillary data. Remote Sens 4(8):2256–2276. https://doi.org/10.3390/rs4082256
Schipperijn J, Stigsdotter UK, Randrup TB, Troelsen J (2010) Influences on the use of urban green space—a case study in Odense, Denmark. Urban Forestry Urban Green 9(1):25–32. https://doi.org/10.1016/j.ufug.2009.09.002
Shackelford AK, Davis CH (2003) A combined fuzzy pixel-based and object-based approach for classification of high-resolution multispectral data over urban areas. IEEE Trans Geosci Remote Sens 41(10 Part I):2354–2363. https://doi.org/10.1109/TGRS.2003.815972
Sothe C, de Almeida CM, Liesenberg V, Schimalski MB (2017) Evaluating Sentinel-2 and Landsat-8 data to map sucessional forest stages in a subtropical forest in Southern Brazil. Remote Sens 9:8. https://doi.org/10.3390/rs9080838
Stanková H, Matula D (2017) Analýza štruktúry mestskej zelene a jej zmien v centre Bratislavy. Geografický časopis 69(2):145–165
Sun Z, Xu R, Du W, Wang L, Lu D (2019) High-resolution urban land mapping in China from sentinel 1A/2 imagery based on Google Earth Engine. Remote Sens 11(7):1–22. https://doi.org/10.3390/rs11070752
Tavares PA, Beltrão NES, Guimarães US, Teodoro AC (2019) Integration of Sentinel-1 and Sentinel-2 for classification and LULC mapping in the urban area of Belém, Eastern Brazilian Amazon. Sensors (Basel, Switz) 19(5):1140. https://doi.org/10.3390/s19051140
Thanh Noi P, Kappas M (2017) Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors (Basel, Switz) 18:1. https://doi.org/10.3390/s18010018
Tian H, Huang N, Niu Z, Qin Y, Pei J, Wang J (2019) Mapping winter crops in China with multi-source satellite imagery and phenology-based algorithm. Remote Sens 11(7):1–23. https://doi.org/10.3390/rs11070820
Trimble (2011) eCognition ® Developer 8.7 Reference Book p 416. https://doi.org/10.1525/hlq.2011.74.1.43
Trimble (2019) eCognition Suite. https://geospatial.trimble.com/products-and-solutions/ecognition
Wardlow BD, Egbert SL (2008) Large-area crop mapping using time-series MODIS 250 m NDVI data: an assessment for the U.S. Central Great Plains. Remote Sens Env 112(3):1096–1116. https://doi.org/10.1016/j.rse.2007.07.019
Acknowledgements
This work was supported by the Research and Development Operational Programme funded by the ERDF under Grant ITMS 26240220086 (Comenius University in Bratislava Science Park) and the Slovak Research and Development Agency under Grant APVV-15-0136. The authors would like to thank the anonymous reviewers for their valuable feedback and comments on the manuscript that improved it significantly.
Author information
Authors and Affiliations
Corresponding author
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Bobáľová, H., Benová, A. & Kožuch, M. Hierarchical Object-Based Mapping of Urban Land Cover Using Sentinel-2 Data: A Case Study of Six Cities in Central Europe. PFG 89, 15–31 (2021). https://doi.org/10.1007/s41064-020-00135-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41064-020-00135-8