A new method for road detection in urban areas using high-resolution satellite images and Lidar data based on fuzzy nearest-neighbor classification and optimal features

Detection of roads in urban areas is of greater importance and is a persistent research focus in the remote sensing community. The spectral and geometrical varieties of road pixels; their spectral similarity to other features such as buildings, parking lots, and sidewalks; and the occasional obstruction by vehicles and trees are obstacles to the precise identification of urban roads through satellite images. Lidar data, however, provide height information that can facilitate the identification of roads from other spectrally similar elements. Therefore, Lidar has been widely used alongside satellite images to identify features such as roads. In this paper, high-resolution QuickBird satellite imagery and Lidar data processed through nearest-neighbor classification based on optimal features have been used together to extract various types of urban roads. This work designed and implemented a rule-oriented strategy based on a masking approach. A supplementary strategy based on optimal design features was also used. The overall precision of class identification is 91 % with a kappa coefficient of 0.87, which shows a satisfactory precision according to different conditions and considerable interclass noise. The final results demonstrate the high capability of object-oriented methods in simultaneous identification of a wide variety of road elements in complex urban areas using both high-resolution satellite imagery and Lidar data.

[1]  Ashok Samal,et al.  Semi-Automated Road Detection From High Resolution Satellite Images by Directional Morphological Enhancement and Segmentation Techniques , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[2]  John Trinder,et al.  Building Detection Using LIDAR Data and Multispectral Images , 2003, DICTA.

[3]  G. Vosselman.  ON THE ESTIMATION OF PLANIMETRIC OFFSETS IN LASER ALTIMETRY DATA , 2002 .

[4]  Rohit Maurya,et al.  Road extraction using K-Means clustering and morphological operations , 2011, 2011 International Conference on Image Information Processing.

[5]  John A. Gamon,et al.  Assessing leaf pigment content and activity with a reflectometer , 1999 .

[6]  A. Mohammadzadeh,et al.  Automatic main road extraction from high resolution satellite imageries by means of particle swarm optimization applied to a fuzzy-based mean calculation approach , 2009 .

[7]  C. Steger,et al.  AUTOMATIC ROAD EXTRACTION BASED ON MULTI-SCALE, GROUPING, AND CONTEXT , 1999 .

[8]  T Rajani Mangala,et al.  A New Automatic Road Extraction Technique using Gradient Operation and Skeletal Ray Formation , 2011 .

[9]  Mohsen Gholoobi,et al.  Using object-based hierarchical classification to extract land use land cover classes from high-resolution satellite imagery in a complex urban area , 2015 .

[10]  Jinliang Wang,et al.  Urban road information extraction from high resolution remotely sensed image based on semantic model , 2013, 2013 21st International Conference on Geoinformatics.

[11]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[12]  Peng Jiangui,et al.  A method for main road extraction from airborne LiDAR data in urban area , 2011, 2011 International Conference on Electronics, Communications and Control (ICECC).

[13]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[14]  A. Gruen,et al.  Semi-Automatic Linear Feature Extraction by Dynamic Programming and LSB-Snakes , 1997 .

[15]  Yi-Hsing Tseng,et al.  Automatic Segmentation of Lidar Data into Coplanar Point Clusters Using an Octree-Based Split-and-Merge Algorithm , 2010 .

[16]  K. Pakzad,et al.  SCALE-DEPENDENT ADAPTATION OF OBJECT MODELS FOR ROAD EXTRACTION , 2005 .

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

[18]  Qiang Du,et al.  Constrained boundary recovery for three dimensional Delaunay triangulations , 2004 .

[19]  Emmanuel P. Baltsavias,et al.  Object extraction and revision by image analysis using existing geodata and knowledge: current status and steps towards operational systems☆ , 2004 .

[20]  Sudhir Gupta,et al.  Automatic road network extraction using high resolution multi-temporal satellite images , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[21]  Juan B. Mena,et al.  State of the art on automatic road extraction for GIS update: a novel classification , 2003, Pattern Recognit. Lett..

[22]  Jon Atli Benediktsson,et al.  Advanced directional mathematical morphology for the detection of the road network in very high resolution remote sensing images , 2010, Pattern Recognit. Lett..

[23]  C. Jordan.  Derivation of leaf-area index from quality of light on the forest floor , 1969 .

[24]  F. Baret,et al.  Potentials and limits of vegetation indices for LAI and APAR assessment , 1991 .

[25]  Ruisheng Wang,et al.  EXTRACTION OF ROAD NETWORKS USING PAN-SHARPENED MULTISPECTRAL AND PANCHROMATIC QUICKBIRD IMAGES , 2005 .

[26]  L. Alparone,et al.  Enhanced Gram-Schmidt Spectral Sharpening Based on Multivariate Regression of MS and Pan Data , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[27]  Ming Zhong,et al.  Object-Based Classification of Urban Areas Using VHR Imagery and Height Points Ancillary Data , 2012, Remote. Sens..

[28]  Yong Hu,et al.  Automated extraction of digital terrain models, roads and buildings using airborne lidar data , 2003 .

[29]  Jing Li,et al.  Hierarchical object oriented classification using very high resolution imagery and LIDAR data over urban areas , 2009 .