Exploring the Potential of Machine Learning for Automatic Slum Identification from VHR Imagery

Slum identification in urban settlements is a crucial step in the process of formulation of pro-poor policies. However, the use of conventional methods for slum detection such as field surveys can be time-consuming and costly. This paper explores the possibility of implementing a low-cost standardized method for slum detection. We use spectral, texture and structural features extracted from very high spatial resolution imagery as input data and evaluate the capability of three machine learning algorithms (Logistic Regression, Support Vector Machine and Random Forest) to classify urban areas as slum or no-slum. Using data from Buenos Aires (Argentina), Medellin (Colombia) and Recife (Brazil), we found that Support Vector Machine with radial basis kernel delivers the best performance (with F2-scores over 0.81). We also found that singularities within cities preclude the use of a unified classification model.

[1]  Qin Yu,et al.  Assessing the relationship between spatial features derived from high resolution satellite imagery and census variables in Accra, Ghana , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[2]  Juan Carlos Duque,et al.  Measuring intra-urban poverty using land cover and texture metrics derived from remote sensing data , 2015 .

[3]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[4]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[5]  Hannes Taubenböck,et al.  Urbanization in India - Spatiotemporal analysis using remote sensing data , 2009, Comput. Environ. Urban Syst..

[6]  Rainer Zah,et al.  Deriving fine-scale socioeconomic information of urban areas using very high-resolution satellite imagery , 2011 .

[7]  D. Tiede,et al.  Damage assessment in townships using VHSR data; The effect of Operation Murambatsvina / Restore Order in Harare, Zimbabwe , 2007, 2007 Urban Remote Sensing Joint Event.

[8]  Qian Song,et al.  Exploring the Use of Google Earth Imagery and Object-Based Methods in Land Use/Cover Mapping , 2013, Remote. Sens..

[9]  Juan Carlos Duque,et al.  A review of regional science applications of satellite remote sensing in urban settings , 2013, Comput. Environ. Urban Syst..

[10]  David W. S. Wong,et al.  An approach to differentiate informal settlements using spectral, texture, geomorphology and road accessibility metrics , 2013 .

[11]  Pablo Cabrera-Barona,et al.  Multiscale evaluation of an urban deprivation index: Implications for quality of life and healthcare accessibility planning , 2016 .

[12]  Geng-Ming Jiang,et al.  Preliminary mapping of high-resolution rural population distribution based on imagery from Google Earth: A case study in the Lake Tai basin, eastern China , 2012 .

[13]  Sadhana Jain,et al.  Remote sensing application for property tax evaluation , 2008, Int. J. Appl. Earth Obs. Geoinformation.

[14]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[15]  G. Marsaglia,et al.  Evaluating Kolmogorov's distribution , 2003 .

[16]  Oleksandr Kit,et al.  Automated detection of slum area change in Hyderabad, India using multitemporal satellite imagery , 2013 .

[17]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[18]  Luis Ángel Ruiz Fernández,et al.  Using semivariogram indices to analyse heterogeneity in spatial patterns in remotely sensed images , 2013, Comput. Geosci..

[19]  Monika Kuffer,et al.  Capturing the Diversity of Deprived Areas with Image-Based Features: The Case of Mumbai , 2017, Remote. Sens..

[20]  Luis Ángel Ruiz Fernández,et al.  Definition of a comprehensive set of texture semivariogram features and their evaluation for object-oriented image classification , 2010, Comput. Geosci..

[21]  Monika Kuffer,et al.  The utility of the co-occurrence matrix to extract slum areas from VHR imagery , 2015, 2015 Joint Urban Remote Sensing Event (JURSE).

[22]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[23]  Juan C. Duque,et al.  A Stepwise Procedure to Determinate a Suitable Scale for the Spatial Delimitation of Urban Slums , 2012 .

[24]  Txomin Hermosilla,et al.  Original papers: A feature extraction software tool for agricultural object-based image analysis , 2011 .

[25]  Ryan N. Engstrom,et al.  Determining the Relationship Between Census Data and Spatial Features Derived From High-Resolution Imagery in Accra, Ghana , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[26]  Matthias Rauterberg,et al.  Unsupervised understanding of location and illumination changes in egocentric videos , 2016, Pervasive Mob. Comput..

[27]  Jonathan Hersh,et al.  Evaluating the relationship between spatial and spectral features derived from high spatial resolution satellite data and urban poverty in Colombo, Sri Lanka , 2017, 2017 Joint Urban Remote Sensing Event (JURSE).

[28]  Hui Liu,et al.  The Use of Landscape Metrics and Transfer Learning to Explore Urban Villages in China , 2017, Remote. Sens..

[29]  Alfred Stein,et al.  Urban slum detection using texture and spatial metrics derived from satellite imagery , 2016 .

[30]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[31]  Mustapha Hakdaoui,et al.  Detecting Slums from SPOT Data in Casablanca Morocco Using an Object Based Approach , 2011, J. Geogr. Inf. Syst..

[32]  M. Kuffer,et al.  Urban morphology of unplanned settlements: the use of spatial metrics in VHR remotely sensed images , 2011 .

[33]  Monika Kuffer,et al.  Extraction of Slum Areas From VHR Imagery Using GLCM Variance , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[34]  Hannes Taubenböck,et al.  Exploitation of textural and morphological image features in Sentinel-2A data for slum mapping , 2017, 2017 Joint Urban Remote Sensing Event (JURSE).

[35]  Luis Carvalho,et al.  An Improved Evaluation of Kolmogorovs Distribution , 2015 .

[36]  Ryosuke Shibasaki,et al.  Identification of Village Building via Google Earth Images and Supervised Machine Learning Methods , 2016, Remote. Sens..

[37]  Alfred Stein,et al.  Uncertainty analysis for image interpretations of urban slums , 2016, Comput. Environ. Urban Syst..

[38]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[39]  Monika Kuffer,et al.  Slums from Space - 15 Years of Slum Mapping Using Remote Sensing , 2016, Remote. Sens..

[40]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[41]  S. Cessie,et al.  Ridge Estimators in Logistic Regression , 1992 .

[42]  H. Taubenböck,et al.  The physical face of slums: a structural comparison of slums in Mumbai, India, based on remotely sensed data , 2014 .