Backscattering Feature Analysis and Recognition of Civilian Aircraft in TerraSAR-X Images

This letter first analyzes the scattering features of civilian aircraft (CA) using high-resolution TerraSAR-X images of the Hong Kong International Airport based on the electromagnetic scattering theory. The main stable scattering features are found to be salient points. Then, a salient point vector (SPV) is proposed to describe the salient points. By adding two relaxation variables to the matching process, the SPV becomes both translationally and rotationally invariant over a certain orientation range. In addition, a recognition scheme is designed to validate the scattering analysis and the SPV descriptor. Finally, 43 test chips are collected from another TerraSAR-X image acquired in November 2013 in the same location with similar imaging parameters. The test chips are applied to validate the analysis, the SPV descriptor, and the recognition scheme. The results of the experiment indicate that the recognition rate of the Boeing 747 CA reaches 80% and that the scattering features of the aircraft are rotationally invariant to within at least 5°. This research verifies the potential application of CA monitoring using high-resolution synthetic aperture radar images.

[1]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[2]  Richard Bamler,et al.  Performance Analysis of the TerraSAR-X Traffic Monitoring Concept , 2006 .

[3]  Bir Bhanu,et al.  Recognizing articulated objects in SAR images , 2001, Pattern Recognit..

[4]  Bo Zhang,et al.  A Novel Hierarchical Ship Classifier for COSMO-SkyMed SAR Data , 2014, IEEE Geoscience and Remote Sensing Letters.

[5]  Naoki Suzuki,et al.  Benchmarking operational SAR ship detection , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[6]  Randolph L. Moses,et al.  Synthetic Aperture Radar 3D Feature Extraction for Arbitrary Flight Paths , 2012, IEEE Transactions on Aerospace and Electronic Systems.

[7]  Lee C. Potter,et al.  Civilian vehicle radar data domes , 2010, Defense + Commercial Sensing.

[8]  Gintautas Palubinskas,et al.  Radar Signatures of a Passenger Car , 2007, IEEE Geoscience and Remote Sensing Letters.

[9]  Jing Li,et al.  A comprehensive review of current local features for computer vision , 2008, Neurocomputing.

[10]  Nicu Sebe,et al.  Comparing salient point detectors , 2001, IEEE International Conference on Multimedia and Expo, 2001. ICME 2001..

[11]  Sang-Hong Park,et al.  New Discrimination Features for SAR Automatic Target Recognition , 2013, IEEE Geosci. Remote. Sens. Lett..

[12]  Carlos López-Martínez,et al.  Exploitation of Ship Scattering in Polarimetric SAR for an Improved Classification Under High Clutter Conditions , 2009, IEEE Transactions on Geoscience and Remote Sensing.