Development of an Automatic Land Use Extraction System in Urban Areas using VHR Aerial Imagery and GIS Vector Data

Authors

1 Ph.D Candidate, Department of Civil Engineering, University of New Brunswick, Canada

2 Associate Professor, Department of Civil Engineering, University of New Brunswick, Canada

3 MSc Student, Department of Civil Engineering, University of New Brunswick, Canada

4 Professor, Department of Geomatics and Geodesy, University of New Brunswick, Canada

Abstract

Lack of detailed land use (LU) information and efficient data collection methods have made the modeling of urban systems difficult. This study aims to develop a novel hierarchical rule-based LU extraction framework using geographic vector and remotely sensed (RS) data, in order to extract detailed subzonal LU information, residential LU in this study. The LU extraction system is developed to extract residential LU at a fine spatial level  parcel through morphological analysis. First, a novel hybrid pixel- and object-based land cover (LC) classification system, coupled with a sophisticated GIS post-classification correction process, is developed to extract land cover, including vegetation, parking lot, and bare soil, required for LU classification. The land cover classification system developed results in an overall accuracy of 96.4%. Residential LUs are then extracted by examining the morphological properties of individual parcels (which are derived from RS and geographic vector data) using a binary logistic model, which results in an overall accuracy of 97.5%. The above results show that the LU classification expert system developed can classify and then divide large zones with mixed LUs into single-LU subzones with a high accuracy. Therefore, it has a significant value to address several persistent issues caused by using large zones in urban modeling, such as intrazonal travel and mixed-LU zones.

Keywords


- Agresti, A. (1996) “An introduction to categorical data analysis”, New York: Wiley.

- Barnsley, M. J., Steel, A. M. and Barr, S. L. (2003) “Determining urban land use through an analysis of the spatial composition of buildings identified in lidar and multispectral image data”, In V. Mesev (Ed.), Remotely sensed cities (pp. 47–82), London: Taylor & Francis.

- Beykaei, S. A., Zhong, M. and Zhang, Y. (2010) “Evaluating the accuracy of extracting urban land cover/use from remotely sensed imagery and its potential application in urban planning”, 8th International Transportation Specialty Conference, CSCE, Winnipeg, Manitoba.

- Chan, J. C., Bellens, R., Canters, F. and Gautama, S. (2009) “An assessment of geometric activity features for per-pixel classification of urban man-made object using very high resolution satellite imagery”, Photogrammetric Engineering & Remote Sensing, 75(4), pp.397-411.

- Deng, J.S., Wang, K., Li, J., Feng, X.L., and Huang, J.Q. (2005) “Integration of SPOT-5 and ETM+ images to detect land cover change in urban environment”, Proceedings of Geoscience and Remote Sensing Symposium, IGARSS '05, IEEE International, Vol 4, pp.2284- 2286.

- Gomarasca, M. A., Brivio, P. A., Pagnoni, F. and Galli, A. (1993) “One century of land use changes in the metropolitan area of Milan (Italy)”, International Journal of Remote Sensing, Vol. 14, pp.211– 223.

- Hill, J. and Hostert, P. (1996) “Monitoring the growth of a Mediterranean Metropolis based on the analysis of spectral mixtures – A case study on Athens (Greece)”, in Progress in Environmental Remote Sensing Research and Applications, edited by Parlow (Rotterdam: Balkema), pp.21–30.

- Liu, W. and Prinet, Y. (2005). “Building detection from high-resolution satellite image using Probability Model.” Proceedings of Geoscience and Remote Sensing Symposium. IGARSS '05. 2005 IEEE International, Vol. 6, pp.3888- 3891.

- McGibbon, G. S. and Eyton, J. R. (1996) “Frequencybased contextual landform classification.” The Canadian Surveyor, GEOMATICA, 50(3), pp. 287-299.

- Mesev, V. (2005) “Identification and characterization of urban building patterns using IKONOS imagery and point-based postal data.” Comput., Environ.Urban Syst., 29(5), pp.541-557.

- Mohaptra, R. P. and Wu, C. (2008) “Subpixel imperviousness: Estimation with IKONOS imagery: An artificial neural network approach.” Remote Sensing of Impervious Surfaces, pp.21-37.

- Mundia, C. N., and Aniya, M. (2005) “Analysis of land use/ cover changes and urban expansion of Nairobi City using remote sensing and GIS.” International Journal of Remote Sensing, 26 (13), pp.2831-2849.

- Pacifici, F., Fabio, D. F., Solimini, D. and Burini, A. (2007) “Urban land cover classification: potential of high and very-high resolution SAR imagery.” IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain, 1982-1985.

- Pesaresi, M. and Bianchin, A. (2001) “Recognizing Settlement Structure Using Mathematical Morphology and Image Texture.” In: Donnay, J.-P., Barnsley, M. and Longley, P., Editors, 2001. Remote sensing and urban analysis, Taylor & Francis, London, 55–67.

- Xiao, Y., Lim, S. K., Tan, S.T., and Tay, S. C. (2004) “Feature extraction using very high resolution satellite imagery”, IEEE International Geoscience and Remote Sensing Symposium, Anchorage, Alaska, pp.2004- 2007.

- Yoshida, H., and Omae, M (2005). “An approach for analysis of urban morphology: Methods to derive morphological properties of city blocks by using an urban landscape model and their interpretations”, Comput., Environ.Urban Syst., 29(2), pp. 223-247.

- Zhang, Y. (1999) “Optimization of building detection in satellite data by combining multispectral classification and texture filtering.” ISPRS Journal of Photogrammetry & Remote Sensing, 54(1), pp.50-60.

- Zhang, Y. (2001) “Detection of urban housing development by fusing multisensor satellite data and performing spatial feature post-classification”, International Journal of Remote Sensing, 22(17), pp.3339-3355.