Abstract
Main road features extracted from remotely sensed imagery play an important role in many civilian and military applications, such as updating Geographic Information System (GIS) databases, urban structure analysis, spatial data matching and road navigation. Current methods for road feature extraction from high-resolution imagery are typically based on threshold value segmentation. It is difficult however, to completely separate road features from the background. We present a new method for extracting main roads from high-resolution grayscale imagery based on directional mathematical morphology and prior knowledge obtained from the Volunteered Geographic Information found in the OpenStreetMap. The two salient steps in this strategy are: (1) using directional mathematical morphology to enhance the contrast between roads and non-roads; (2) using OpenStreetMap roads as prior knowledge to segment the remotely sensed imagery. Experiments were conducted on two ZiYuan-3 images and one QuickBird high-resolution grayscale image to compare our proposed method to other commonly used techniques for road feature extraction. The results demonstrated the validity and better performance of the proposed method for urban main road feature extraction.
Highlights
In recent years, earth observation technologies have led to a rapid development of satellite imagery at very high spatial resolution
Road Extraction Based on Directional Mathematical morphology (MM) and Volunteered Geographic Information (VGI) in Urban Areas
Our method integrates directional mathematical morphology, VGI prior knowledge captured in the OSM, and shape features to extract main road from ZY-3 images
Summary
Earth observation technologies have led to a rapid development of satellite imagery at very high spatial resolution (such as ZiYuan-3, Geo-eye, QuickBird and Worldview et al.). Many approaches have been developed to extract main roads from high resolution imagery in urban areas in order to keep the GIS road network databases updated in a timely way. Zhu et al [19] extracted road networks from high-resolution satellite images by using classical MM; their classical MM method depends on the shape of a Structuring Element (SE) and MM is not sufficient for detecting curved and rectilinear structures at the same time. Valero et al [24] used path closings to detect road networks in very high resolution remote sensing images In their method, a binary mask was used to extract the median gray value (M(x, y)) of roads in the image that was processed by path closings, and set M(x, y) as threshold to determine which pixels belonged to roads. Our method integrates directional mathematical morphology, VGI prior knowledge captured in the OSM, and shape features to extract main road from ZY-3 images.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call