Road condition assessment by OBIA and feature selection techniques using very high-resolution WorldView-2 imagery

Abstract Accurate information on the conditions of road asphalt is necessary for economic development and transportation management. In this study, object-based image analysis (OBIA) rule-sets are proposed based on feature selection technique to extract road asphalt conditions (good and poor) using WorldView-2 (WV-2) satellite data. Different feature selection techniques, including support vector machine (SVM), random forest (RF) and chi-square (CHI) are evaluated to indicate the most effective algorithm to identify the best set of OBIA attributes (spatial, spectral, textural and colour). The chi-square algorithm outperformed SVM and RF techniques. The classification result based on CHI algorithm achieved an overall accuracy of 83.19% for the training image (first site). Furthermore, the proposed model was used to examine its performance in different areas; and it achieved accuracy levels of 83.44, 87.80 and 80.26% for the different selected areas. Therefore, the selected method can be potentially useful for detecting road conditions based on WV-2 images.

[1]  Taskin Kavzoglu,et al.  Mapping urban road infrastructure using remotely sensed images , 2009 .

[2]  Eyal Ben-Dor,et al.  A spectral based recognition of the urban environment using the visible and near-infrared spectral region (0.4-1.1 µm). A case study over Tel-Aviv, Israel , 2001 .

[3]  Yuan Tian,et al.  Chi-square Statistics Feature Selection Based on Term Frequency and Distribution for Text Categorization , 2015 .

[4]  Mahesh Pal,et al.  Support vector machine‐based feature selection for land cover classification: a case study with DAIS hyperspectral data , 2006 .

[5]  Xiaole Ji,et al.  The Attribute Accuracy Assessment of Land Cover Data in the National Geographic Conditions Survey , 2014 .

[6]  S. Cornell,et al.  Random Forest characterization of upland vegetation and management burning from aerial imagery , 2009 .

[7]  Amrita.  Fusion of Statistic, Data Mining and Genetic Algorithm for feature selection in Intrusion Detection , 2013 .

[8]  Dar A. Roberts,et al.  Imaging spectrometry of urban materials , 2004 .

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

[10]  Yuri Zhang,et al.  A new automatic approach for effectively fusing Landsat 7 as well as IKONOS images , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[11]  Fadi A. Thabtah,et al.  Phishing detection based Associative Classification data mining , 2014, Expert Syst. Appl..

[12]  T. Esch,et al.  Object-based feature extraction using high spatial resolution satellite data of urban areas , 2010 .

[13]  T. Minor,et al.  Detecting and discriminating impervious cover with high-resolution IKONOS data using principal component analysis and morphological operators , 2003 .

[14]  Sanjiv K. Bhatia,et al.  Rule-based classification of high-resolution imagery over urban areas in New York City , 2013 .

[15]  Jasmina Novakovic,et al.  Using Information Gain Attribute Evaluation to Classify Sonar Targets , 2009 .

[16]  Jay B. Simha,et al.  Evaluation of Feature Selection Methods for Predictive Modeling Using Neural Networks in Credits Scoring , 2010 .

[17]  Wuming Zhang,et al.  AUTOMATIC ROAD EXTRACTION OF URBAN AREA FROM HIGH SPATIAL RESOLUTION REMOTELY SENSED IMAGERY , 2008 .

[18]  Nigel Waters,et al.  Review of remote sensing methodologies for pavement management and assessment , 2015 .

[19]  G. Foody.  Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy , 2004 .

[20]  Fernando De la Torre,et al.  Optimal feature selection for support vector machines , 2010, Pattern Recognit..

[21]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

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

[23]  A. Mookambiga,et al.  Automated road network extraction using artificial neural network , 2011, 2011 International Conference on Recent Trends in Information Technology (ICRTIT).

[24]  Qihao Weng,et al.  Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends , 2012 .

[25]  John F. Schalles,et al.  Application of hyperspectral remotely sensed data for water quality monitoring: Accuracy and limitation , 2010 .

[26]  Helmi Zulhaidi Mohd Shafri,et al.  Combining data mining algorithm and object-based image analysis for detailed urban mapping of hyperspectral images , 2014 .

[27]  Fan Xia,et al.  Assessing object-based classification: advantages and limitations , 2009 .

[28]  Cheng Wang,et al.  Spectral characteristics and feature selection of hyperspectral remote sensing data , 2004 .

[29]  Margaret E. Gardner,et al.  Spectrometry for urban area remote sensing—Development and analysis of a spectral library from 350 to 2400 nm , 2004 .

[30]  Lalit Kumar,et al.  Investigating the Use of Remote Sensing and GIS Techniques to Detect Land Use and Land Cover Change: A Review , 2013 .

[31]  José Alberto Quintanilha,et al.  Use of Hyperspectral and High Spatial Resolution Image Data in an Asphalted Urban Road Extraction , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[32]  D. Lu,et al.  Extraction of urban impervious surfaces from an IKONOS image , 2009 .

[33]  Mohd Rosli Hainin,et al.  Road Surface Assessment of Pothole Severity by Close Range Digital Photogrammetry Method , 2012 .

[34]  Xun Wang,et al.  Road Extraction in Remote Sensing Images Using a New Algorithm , 2008, 2008 International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[35]  Vassilia Karathanassi,et al.  Investigation of hyperspectral remote sensing for mapping asphalt road conditions , 2011 .

[36]  M. Mohammadi,et al.  ROAD CLASSIFICATION AND CONDITION DETERMINATION USING HYPERSPECTRAL IMAGERY , 2012 .

[37]  Kurt Prospere,et al.  Plant Species Discrimination in a Tropical Wetland Using In Situ Hyperspectral Data , 2014, Remote. Sens..

[38]  Tunga Güngör,et al.  Comparison of text feature selection policies and using an adaptive framework , 2013, Expert Syst. Appl..

[39]  Lian Lian,et al.  Research on Segmentation Scale of Multi-Resources Remote Sensing Data Based on Object-Oriented , 2011 .

[40]  Taşkin Kavzoĝlu,et al.  An investigation of the design and use of feed-forward artificial neural networks in the classification of remotely sensed images , 2001 .

[41]  Helmi Zulhaidi Mohd Shafri,et al.  Development of a Generic Model for the Detection of Roof Materials Based on an Object-Based Approach Using WorldView-2 Satellite Imagery , 2013 .

[42]  Subir Kumar Sarkar,et al.  Implementation Aspects of Logic Functions using Single Electron Threshold Logic Gates and Hybrid SET-MOS Circuits , 2016 .

[43]  Jennifer A. Miller,et al.  Contextual land-cover classification: incorporating spatial dependence in land-cover classification models using random forests and the Getis statistic , 2010 .

[44]  H. Mayer,et al.  AUTOMATIC ROAD EXTRACTION FROM MULTISPECTRAL HIGH RESOLUTION SATELLITE IMAGES , 2005 .

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

[46]  Pengpeng Lin,et al.  A Framework for Consistency Based Feature Selection , 2009 .

[47]  Helmi Zulhaidi Mohd Shafri,et al.  Integrated approach using data mining-based decision tree and object-based image analysis for high-resolution urban mapping of WorldView-2 satellite sensor data , 2016 .

[48]  Mahroo Eftekhari,et al.  Feature-based detection using Bayesian data fusion , 2013 .

[49]  Xiaoying Jin,et al.  A fuzzy rule base system for object-based feature extraction and classification , 2007, SPIE Defense + Commercial Sensing.

[50]  Helmi Zulhaidi Mohd Shafri,et al.  Detailed intra-urban mapping through transferable OBIA rule sets using WorldView-2 very-high-resolution satellite images , 2015 .

[51]  M. Herold,et al.  Spectral characteristics of asphalt road aging and deterioration: implications for remote-sensing applications. , 2005, Applied optics.

[52]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[53]  Xuan Li,et al.  The research of road extraction for high resolution satellite image , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[54]  Silan Zhang,et al.  On the System of Diophantine Equations x 2 − 6y 2 = −5 and x = az 2 − b , 2014, TheScientificWorldJournal.

[55]  Gang Fu,et al.  Road extraction in remote sensing images based on PCNN and mathematical morphology , 2009, Optical Engineering + Applications.

[56]  Xuefei Hu,et al.  Impervious surface area extraction from IKONOS imagery using an object-based fuzzy method , 2011 .

[57]  Changshan Wu,et al.  Quantifying high‐resolution impervious surfaces using spectral mixture analysis , 2009 .

[58]  Norbert Haala,et al.  Building parameters extraction from remote-sensing data and GIS analysis for the derivation of a building taxonomy of settlements – a contribution to flood building susceptibility assessment , 2015 .

[59]  Shattri Mansor,et al.  Hyperspectral Remote Sensing of Urban Areas: An Overview of Techniques and Applications , 2012 .

[60]  Helmi Zulhaidi Mohd Shafri,et al.  Improving detailed rule-based feature extraction of urban areas from WorldView-2 image and lidar data , 2014 .

[61]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[62]  Sergio A. Alvarez,et al.  Chi-squared computation for association rules: preliminary results , 2003 .

[63]  Jie Tian,et al.  Optimization in multi‐scale segmentation of high‐resolution satellite images for artificial feature recognition , 2007 .

[64]  Helmi Zulhaidi Mohd Shafri,et al.  Mapping of Intra-Urban Land Covers Using Pixel-Based and Object-Based Classifications from Airborne Hyperspectral Imagery , 2015, 2015 2nd International Conference on Information Science and Security (ICISS).

[65]  Aixia Guo,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2014 .

[66]  Patricia Gober,et al.  Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery , 2011, Remote Sensing of Environment.

[67]  Yung-Hsiang Hung,et al.  SVM-RFE Based Feature Selection and Taguchi Parameters Optimization for Multiclass SVM Classifier , 2014, TheScientificWorldJournal.

[68]  Helmi Zulhaidi Mohd Shafri,et al.  Spectral feature selection and classification of roofing materials using field spectroscopy data , 2015 .

[69]  Qiaoping Zhang,et al.  A FRAMEWORK FOR ROAD CHANGE DETECTION AND MAP UPDATING , 2004 .

[70]  N. El-Sheimy,et al.  NEW COMBINED PIXEL/OBJECT-BASED TECHNIQUE FOR EFFICIENT URBAN CLASSSIFICATION USING WORLDVIEW-2 DATA , 2012 .

[71]  Helmi Zulhaidi Mohd Shafri,et al.  Development of fuzzy rule-based parameters for urban object-oriented classification using very high resolution imagery , 2014 .

[72]  S. Bhaskaran,et al.  Per-pixel and object-oriented classification methods for mapping urban features using Ikonos satellite data , 2010 .

[73]  Margaret E. Gardner,et al.  SPECTROMETRY AND HYPERSPECTRAL REMOTE SENSING FOR ROAD CENTERLINE EXTRACTION AND EVALUATION OF PAVEMENT CONDITION , 2002 .

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

[75]  A. Araújo,et al.  Feature Selection for Classification of Remote Sensed Hyperspectral Images : A Filter approach using Genetic Algorithm and Cluster Validity , 2012 .

[76]  Helmi Zulhaidi Mohd Shafri,et al.  Object-based classification of QuickBird image and low point density LIDAR for tropical trees and shrubs mapping , 2015 .

[77]  Yang Hu,et al.  Road Extraction from Remote Sensing Imagery Based on Road Tracking and Ribbon Snake , 2009, 2009 Pacific-Asia Conference on Knowledge Engineering and Software Engineering.