PROJECT TITLE :

Road Network Extraction via Aperiodic Directional Structure Measurement

ABSTRACT:

In this paper, we tend to present a novel aperiodic directional structure measurement (ADSM) toward road network extraction. Based mostly on the observations from Cognitive Psychology concerning the aperiodicity and native directionality, ADSM will well characterize roadlike structures independent of the spectral character and contrast. By exploiting such measurement as guidance, we have a tendency to construct a mask to denote potential road regions. Then, by combining with some common morphology operators, our approach is ready to provide sturdy road centerlines efficiently. We evaluate our approach with information from varied satellite sensors and create comprehensive comparisons with previous state-of-the-art ways. Experimental results demonstrate the merit using our ADSM as a metric to identify potential road structures, similarly because the effectiveness and efficiency of our road network extraction system.