Airport Runway Area Detection Based on Multi-Feature Optimization in PolSAR Images

In this paper, a novel method of airport runway area detection in Polarimetric Synthetic Aperture Radar (PolSAR) image is proposed based on multi-feature optimization. Firstly, training samples are manually selected and a variety of features are extracted from the samples. Secondly, some features which are weakly relevant and redundant are removed by analyzing the relevance and redundancy among the target features. Then, the region of interest (ROI) is extracted by Random Forest (RF) classifier which is designed to divide the image contents into two parts. Finally, image morphology processing and some prior information of the runway like its parallel line property, length and width range and topological property are used to identify the real runway area. Experiments are carried out with real full-polarimetric Synthetic Aperture Radar (SAR) image data collected by the US UAVSAR system. The detected runway areas have a complete structure and clear outline, which demonstrate that the proposed method is effective and robust.