Fully Automatic Road Network Extraction from Satellite Images

Abstract

corresponding FIR (finite impulse response) filter. Resulting Abstract-In this paper a fully automatic road detection two images are fused together using Karhounen-Louve algorithm is introduced. It comprises of pre-processing the image transform (KLT) which is based on principal component via a series of wavelet based filter banks and reducing the analysis (PCA). This process underlines the prominent yielding data into a single image which is of the same size as the features of the original image as well as de-noising it, since original optical grayscale satellite image, then utilizing a fuzzy the prominent features appear in both of the wavelet inference algorithm to carry out the road detection which can then be used as an input to a geographical information system for twan image whienoiseades not correla ew cartographic or for other purposes that are in need. We use a between high and low resolutlon scales as it lacks coherence. trous algorithm twice with two different wavelet bases in order to Principal component analysis is a powerful statistical tool filter and de-noise the satellite image. Each wavelet function commonly used for pattern recognition or data compression.resolves features at a different resolution level associated with the This approach takes contextual spatial information into frequency response of the corresponding FIR filter. Resulting account and exploits the complementary characteristics of the two images are fused together using Karhounen-Louve transform passive optical and/or SAR data. Furthermore it is also (KLT) which is based on principal component analysis (PCA). possible to use more than two images to begin with and fuse This process underlines the prominent features of the original them into a single one in this step without any loss of image as well as de-noising it, since the prominent features appear in both of the wavelet transformed images while noise geralit if don sop were justified tomshOw tter does not strongly correlate between scales. Next a fuzzy logic performance at the expense of computational time. On this inference algorithm which is based on statistical information and image obtained thorough wavelet filtering and KLT, road on geometry is used to extract the road pixels. detection is carried out using a fuzzy-logic inference algorithm. Linguistic variables used for this task are mean, Index Terms-road extraction, satellite imagery, fuzzy logic standard deviation which are computed within a 5x5 pixel size image window and also another linguistic variable based on I. INTRODUCTION geometry. The inference algorithm then classifies each pixel rVHTS paper deals with a fully automatic road detection as road or non-road with regard to the fuzzy inference rules 1 algorithm. Road detection algorithms can be classified yielding in a binary image. into two major groups; semi-automatic and automatic.Satellite images used in this paper are passive opticalThe first approach necessitates that the user specify some images which are converted to gray-scale representation prior ini...

An Integrated Multistage Framework for Automatic Road Extraction from High Resolution Satellite Imagery

“…The performance of the proposed method is verified on satellite images of size 512×512 each. The performance of the proposed technique is compared with two state of the art techniques: Tuncer (2007) and Mokhtarzade et al (2007), as well as a free commercial tool for feature extraction (Geospace 2008), termed as FeatureObjeX.…”

“…This drove us to formulate and design a hierarchical pipelined framework, consisting of the classification (supervised), information integration, filtering and local neighborhood analysis to obtain descent results with acceptable quality. Results will be compared with two state-of-the-art methods (Tuncer 2007;Mokhtarzade and Zoej 2007) published in literature and one GIS-based software (Geospace 2008) used for raster image analysis.…”

“…The initial probabilistic values and segmented maps are obtained using the method discussed in Section "Segmentation Using Probabilistic SVM". In order to directly compare our approach with the recently published results in (Tuncer 2007;Mokhtarzade and Zoej 2007), we use a pair of images published by them for evaluation. We will show the results first on the images used in (Tuncer 2007) and (Mokhtarzade and Zoej 2007), and then with a few examples from the testing dataset acquired from wikimapia (Koriakine and Saveliev 2006) in Figs.…”

“…15, 16, 17 and 18. Figure 14a shows two sample images used in (Tuncer 2007) and (Mokhtarzade and Zoej 2007). Output of human operator to detect roads from the two images are presented in Fig.…”

“…These primitives are defined, measured, extracted and linked using different methods for dissimilar road scenes. Tuncer (2007) proposed a method which comprises of preprocessing the image via a series of wavelet based filter banks and reducing the data into a single image which is of the same size as the original satellite image. Then a fuzzy inference algorithm is utilized to perform road detection.…”