bject-oriented mapping of urban trees using Random Forest lassifiers

Abstract Since vegetation in urban areas delivers crucial ecological services as a support to human well-being and to the urban population in general, its monitoring is a major issue for urban planners. Mapping and monitoring the changes in urban green spaces are important tasks because of their functions such as the management of air, climate and water quality, the reduction of noise, the protection of species and the development of recreational activities. In this context, the objective of this work is to propose a methodology to inventory and map the urban tree spaces from a mono-temporal very high resolution (VHR) optical image using a Random Forest classifier in combination with object-oriented approaches. The methodology is developed and its performance is evaluated on a dataset of the city of Strasbourg (France) for different categories of built-up areas. The results indicate a good accuracy and a high robustness for the classification of the green elements in terms of user and producer accuracies.

[1]  Alfred Stein,et al.  Context-sensitive extraction of tree crown objects in urban areas using VHR satellite images , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[2]  Dong-Chen He,et al.  How do People Perceive the City's Green Space? A View from Satellite Imagery (In Hanoi, Vietnam) , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[3]  Xuezhi Feng,et al.  Object-oriented method for urban vegetation mapping using IKONOS imagery , 2010 .

[4]  André Stumpf,et al.  Object-oriented mapping of landslides using Random Forests , 2011 .

[5]  N. Coops,et al.  Extracting urban vegetation characteristics using spectral mixture analysis and decision tree classifications. , 2009 .

[6]  Steven E. Franklin,et al.  Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests , 2012 .

[7]  Rick L. Lawrence,et al.  Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest) , 2006 .

[8]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[9]  Chengfan Li,et al.  Extraction of urban vegetation from high resolution remote sensing image , 2010, 2010 International Conference On Computer Design and Applications.

[10]  Frieke Van Coillie,et al.  Synergy of very high resolution optical and radar data for object-based olive grove mapping , 2011, Int. J. Geogr. Inf. Sci..

[11]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[12]  Simon Dufour,et al.  Green and blue belt networks: Mapping connectivity areas at a regional scale using medium and high spatial resolution satellite images , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[13]  A. Smith,et al.  Image segmentation scale parameter optimization and land cover classification using the Random Forest algorithm , 2010 .

[14]  Valentyn Tolpekin,et al.  Markov random field based super-resolution mapping for identification of urban trees in VHR images , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[15]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[16]  P. Sivakumar,et al.  A REVIEW ON IMAGE SEGMENTATION TECHNIQUES , 2016 .

[17]  M. Mcdonnell,et al.  The use of gradient analysis studies in advancing our understanding of the ecology of urbanizing landscapes: current status and future directions , 2008, Landscape Ecology.

[18]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[19]  Bertrand Thirion,et al.  Random Forests based feature selection for decoding fMRI data , 2010 .

[20]  Josef Strobl,et al.  What’s wrong with pixels? Some recent developments interfacing remote sensing and GIS , 2001 .

[21]  Y. Zhang,et al.  A REVIEW ON IMAGE SEGMENTATION TECHNIQUES WITH REMOTE SENSING PERSPECTIVE , 2010 .

[22]  Tapas Ranjan Martha,et al.  Segment Optimization and Data-Driven Thresholding for Knowledge-Based Landslide Detection by Object-Based Image Analysis , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[23]  David Sheeren,et al.  Discriminating small wooded elements in rural landscape from aerial photography: a hybrid pixel/object-based analysis approach , 2009 .

[24]  R. Jongman,et al.  European ecological networks and greenways , 2004 .

[25]  J. D. Wattsa,et al.  MERGING RANDOM FOREST CLASSIFICATION WITH AN OBJECT-ORIENTED APPROACH FOR ANALYSIS OF AGRICULTURAL LANDS , 2008 .

[26]  Lu Xia,et al.  Detecting Urban Vegetation Using a Object-oriented Method with QuickBird Imagery , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[27]  Sakari Tuominen,et al.  Performance of different spectral and textural aerial photograph features in multi-source forest inventory , 2005 .

[28]  Matthieu Cord,et al.  Detection, Characterization, and Modeling Vegetation in Urban Areas From High-Resolution Aerial Imagery , 2008, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[29]  André Stumpf,et al.  Active Learning in the Spatial Domain for Remote Sensing Image Classification , 2014, IEEE Transactions on Geoscience and Remote Sensing.

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

[31]  L. Bottou,et al.  1 Support Vector Machine Solvers , 2007 .

[32]  Laurence Hubert-Moy,et al.  Wooded hedgerows characterization in rural landscape using very high spatial resolution satellite images , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[33]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[34]  M. Pal,et al.  Random forests for land cover classification , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[35]  Antônio Miguel Vieira Monteiro,et al.  Parameter selection for region‐growing image segmentation algorithms using spatial autocorrelation , 2006 .

[36]  Mary Ann Fajvan,et al.  A Comparison of Multispectral and Multitemporal Information in High Spatial Resolution Imagery for Classification of Individual Tree Species in a Temperate Hardwood Forest , 2001 .

[37]  Dirk Tiede,et al.  ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data , 2010, Int. J. Geogr. Inf. Sci..

[38]  Samia Boukir,et al.  Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests , 2011 .

[39]  Mikhail F. Kanevski,et al.  A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification , 2011, IEEE Journal of Selected Topics in Signal Processing.

[40]  J. Nichol,et al.  Remote sensing of urban vegetation life form by spectral mixture analysis of high‐resolution IKONOS satellite images , 2007 .

[41]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[42]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

[43]  Brian Johnson,et al.  Unsupervised image segmentation evaluation and refinement using a multi-scale approach , 2011 .

[44]  Zhang Youjing,et al.  Identification scales for urban vegetation classification using high spatial resolution satellite data , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[45]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[46]  Steven E. Franklin,et al.  A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery , 2012 .

[47]  Xuezhi Feng,et al.  Detecting urban vegetation from IKONOS data using an object-oriented approach , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..

[48]  Qulin Tan,et al.  Mapping urban tree coverage using object-oriented image analysis method: A case study , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[49]  Jianglin Ma,et al.  Natura 2000 habitat identification and conservation status assessment with superresolution enhanced hyperspectral (CHRIS/PROBA) imagery , 2010 .

[50]  Ting Wang,et al.  Application of Breiman's Random Forest to Modeling Structure-Activity Relationships of Pharmaceutical Molecules , 2004, Multiple Classifier Systems.

[51]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[52]  Hubert Gulinck,et al.  Classification and quantification of green in the expanding urban and semi-urban complex: Application of detailed field data and IKONOS-imagery , 2008 .

[53]  J. Liira,et al.  Issues related to delineation of forest boundaries on Landsat Thematic Mapper winter images , 2004 .

[54]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..

[55]  Thomas Blaschke,et al.  A “ Green Index ” Incorporating Remote Sensing and Citizen ’ S Perception of Green Space , 2005 .

[56]  José Martínez Sotoca,et al.  When Overlapping Unexpectedly Alters the Class Imbalance Effects , 2007, IbPRIA.

[57]  Arko Lucieer,et al.  apping invasive Fallopia japonica by combined spectral , spatial , and temporal nalysis of digital orthophotos , 2012 .

[58]  Aggelos K. Katsaggelos,et al.  A survey of classical methods and new trends in pansharpening of multispectral images , 2011, EURASIP J. Adv. Signal Process..

[59]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[60]  A. Huete,et al.  A Modified Soil Adjusted Vegetation Index , 1994 .

[61]  R. Mathieu,et al.  Mapping private gardens in urban areas using object-oriented techniques and very high-resolution satellite imagery , 2007 .

[62]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[63]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[64]  Anne-Marie Séguin,et al.  Mapping the Greenscape and Environmental Equity in Montreal: An Application of Remote Sensing and GIS , 2011 .