Abstract
A new method is proposed for joint detection of roads in multifrequency synthetic aperture radar (SAR) images. First, a multisegmented polyline model was introduced to provide a more accurate description of a road curve. Then, the roads in the SAR images were extracted in a Bayesian tracking framework, and a particle filtering algorithm used to implement the tracking. Finally, a joint detection method based on the maximum likelihood (ML) criterion was proposed to determine the optimal weights of the particles. Using multifrequency SAR data from the National Aeronautics and Space Administration Jet Propulsion Laboratory (NASA/JPL) Airborne Synthetic Aperture Radar (AIRSAR), the effectiveness of the proposed method is demonstrated by experimental extraction results for a single road as well as for a road network, and it is validated that the joint detection method leads to a larger detection probability than the single detection method.
Published Version
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