Paper Info
Title
Automatic road extraction from satellite imagery using LEGION networks
Abstract
We present an automatic method for road extraction from satellite imagery. The core of the proposed method is Locally Excitatory Globally Inhibitory Oscillator Networks (LEGION). We decompose the road extraction task into three stages. The first stage is image segmentation by LEGION. In the second stage, we compute the medial axis of each segment and select the segments with narrow widths. The third is the road grouping stage. With the medial axes, alignment-dependent connections between medial axis points are established and LEGION is utilized to group the well-aligned medial axes, which represent extracted road segments. Due to the selective gating mechanism of LEGION, different roads in an image are grouped separately. Experimental results on synthetic and real images show the effectiveness of this method.
Year
DOI
Venue
2009
10.1109/IJCNN.2009.5178605
IJCNN
Keywords
Field
DocType
automatic road extraction,medial axis point,automatic method,road extraction,legion network,medial axis,road extraction task,satellite imagery,different road,road segment,well-aligned medial axis,image segmentation,assembly,data mining,application software,synchronization,pixel,neural networks,remote sensing,layout,satellites,feature extraction,oscillators
Computer science,Medial axis,Image segmentation,Artificial intelligence,Geophysical signal processing,Computer vision,Synchronization,Satellite imagery,Pattern recognition,Feature extraction,Pixel,Real image,Machine learning
Conference
ISSN
Citations 
PageRank 
2161-4393
2
0.44
References 
Authors
11
5
Name
Order
Citations
PageRank
Jiangye Yuan121513.96
DeLiang Wang23933362.87
Bo Wu36920.31
Lin Yan4334.24
Rongxing Li514114.56