Urban Slum Detection Approaches from High-Resolution Satellite Data Using Statistical and Spectral Based Approaches
- 30 Downloads
This paper proposes a new technique to detect the urban slums from urban buildings using very high resolution data. Many cities in the Global South are facing the development and growth of highly dynamic slum areas, but often lack detailed spatial information. Unlike buildings, vegetation and other features, urban slums lack in their unique spectral signatures. Thus, accurate detection of slums using remote sensing data poses real challenge to researchers and decision-makers. In this work, gray-level co-occurrence matrix, Tamura-based statistical feature extraction and wavelet frame transform-based spectral feature extraction techniques are proposed for detecting the urban slums from urban buildings. The very high resolution data of Madurai city, South India, acquired by Worldview-2 sensor (1.84 m) proved the ability of the proposed approaches to identify urban slums from urban buildings. Experimental results demonstrate that the proposed wavelet frame transform-based approach can generate higher classification accuracy than other approaches.
KeywordsWavelet frame transform GLCM Tamura Urban slums Urban buildings
We are very grateful to the provider DigitalGlobe, for providing imagery for research purpose under 8-band proposal scheme.
- Filho, M. N. B., & Sobreira, F. (2008). Accuracy of lacunarity algorithms in texture classification of high spatial resolution images from urban areas. The International Archives of the Photogrammetry, Remote Sensing, and Spatial Information Sciences, 36, 417–422.Google Scholar
- GOI. (2010). Rajiv Awas Yojana. In Government of India, Press Information Bureau, http://pibmumbai.gov.in/scripts/static.asp. Accessed 30 Mar 2011.
- Hofmann, P., Strobla, J., Blaschkea, T., & Kux, H. (2010). Detecting informal settlements from quickbird data in Rio De Janeiro using an object based approach. International Journal of Engineering Research and Applications (IJERA), 2(3), 221–225.Google Scholar
- Kohli, D., Kerle, N., Sliuzas, R. (2012). Local ontologies for object-based slum identification and classification. In Proceedings of the 4th GEOBIA (pp. 201–206).Google Scholar
- Unser, M., & Eden, M. (1989). Multiresolution feature extraction and selection for texture segmentation. IEEE Transactions on Image Processing, 11(7), 717–728.Google Scholar