A new method for road detection in urban areas using high-resolution satellite images and Lidar data based on fuzzy near
- PDF / 4,050,426 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 34 Downloads / 171 Views
ORIGINAL PAPER
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 Asghar Milan Lak 1 & Mohammad Javad Valadan Zoej 1 & Mehdi Mokhtarzade 1
Received: 14 February 2015 / Accepted: 8 February 2016 # Saudi Society for Geosciences 2016
Abstract 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, highresolution 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 ruleoriented 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
* Asghar Milan Lak [email protected] Mohammad Javad Valadan Zoej [email protected] Mehdi Mokhtarzade [email protected]
1
Geomantic Faculty, Remote Sensing and Photogrammetry Department, Khaje Nasiredin Toosi University, ValiAsr Street, Tehran, Iran
wide variety of road elements in complex urban areas using both high-resolution satellite imagery and Lidar data. Keywords Road detection . Optimal features . High-resolution satellite imagery . Lidar data
Introduction Roads are one of the most important classes of topographic features and have attracted much research into their automatic detection to keep databases updated. Roads have numerous usages in geospatial information systems. Roads are used in urban planning, vehicle navigation, traffic management, disaster management, etc. The advent of high-resolution satellite images empowered remote sensing with many capabilities for producing land coverage information and resolving myriad features, including roads and buildings in urban areas. During the last three decades, much prominent research into automatic road detection has been performed which led to various strategies and algorithms (Mena 2003; Baltsavias 2004). Methods based on image segmentation and classification (Maurya et al. 2011; Chaudhuri et al. 2012), image filtering (Disha et al. 2012; Wang et al. 2005), multi-temporal analyses (
Data Loading...
