Similarity ratio based algorithms to generate SAR superpixels

Download
2017
Akyılmaz, Emre
Synthetic Aperture Radar (SAR) has the capability of working in all weather conditions during day and night that makes it attractive to be used for automatic target detection and recognition purposes. However, it has the problem of high amount of multiplicative speckle noise. Superpixel segmentation as a preprocessing step is an oversegmentation technique that groups similar neighboring pixels into regularly organized segments with approximately the same size. As boundaries of the objects are important elements to be traced, superpixels should adhere well to the edges. This can only be achieved by an algorithm robust to speckle noise. In this thesis, similarity ratio is first developed as a new metric that is robust to speckle noise. Secondly, Mahalanobis distance is used instead of Euclidian so that the superpixel can fit better to shapes in the real world. Thirdly, the constant determining the relative importance of radiometric and geometric terms is replaced with an adaptive function. The performance of combinations of similarity ratio with Euclidean distance (SREP), Mahalanobis distance (SRMP) and Mahalanobis distance with adaptive scheme (SRAMP) are evaluated by conducting experiments on real and synthetic images. The experimental results showed that similarity ratio and adaptive Mahalanobis proximity (SRAMP) outperforms the other approaches in terms of uniformity, compactness and visual appearance.

Suggestions

Spectral and statistical analyses of experimental radar clutter data
Kahyaoğlu, Nazlı Deniz; Yılmaz, Ali Özgür; Department of Electrical and Electronics Engineering (2010)
The performance of radar detection and imaging systems strongly depends on the characteristics of radar clutter. In order to improve the radar signal processing algorithms, successful analysis and modeling of radar clutter are required. For a successful model of radar clutter, both the spectral and statistical characteristics of the clutter should be revealed. Within the scope of this study, an experimental radar data acquisition system is established to analyze radar clutter. The hardware and the data proc...
Comparative evaluation of SAR image formation algorithms
Şahin, Halil İbrahim; Dural Ünver, Mevlüde Gülbin; Koç, Seyit Sencer; Department of Electrical and Electronics Engineering (2010)
In the scope of this thesis, simulation-based analyses and comparative evaluation of Synthetic Aperture Radar (SAR) image formation techniques, namely Time Domain Correlation, Range Stacking, Range Doppler and Chirp Scaling algorithms, are presented. For this purpose, first, the fundamental concepts of SAR such as SAR geometry, resolution and signal properties are explained. A broadside SAR simulator that provides artificial raw data as an input to the algorithms is designed and implemented. Then, the mathe...
Jammer cancelation by using space-time adaptive processing
Uysal, Halil; Severcan, Mete; Department of Electrical and Electronics Engineering (2011)
Space-Time Adaptive Processing (STAP) has been widely used in spaceborne and airborne radar platforms in order to track ground moving targets. Jammer is an hostile electronic countermeasure that is being used to degrade radar detection and tracking performance. STAP adapts radar’s antenna radiating pattern in order to reduce jamming effectiveness. Jamming power that enters the system is decreased with respect to the adapted radiation pattern. In this thesis, a generic STAP radar model is developed and imple...
Spectral graph based approach for analysis of 3D lidar point clouds
Bayram, Eda; Alatan, Abdullah Aydın; Vural, Elif; Department of Electrical and Electronics Engineering (2017)
Airborne Laser Scanning is a well-known remote sensing technology, which provides quite dense and highly accurate, yet unorganized, point cloud descriptions of the earth surface. However, processing of such a 3D point cloud is quite challenging due to its irregular structure and 3D geometry. In this thesis,two novel approaches for the analysis of unorganized 3D point cloud data are proposed, specifically the ones that are generated by the airborne mounted LIDAR sensor. These methods rely on the spectral grap...
Multi-disciplinary design and optimization of air to surface missiles with respect to flight performance and radar cross section
Karakoç, Ali; Aksel, Mehmet Haluk; Department of Mechanical Engineering (2011)
This study focuses on the external configuration design of a tactical missile based on maximizing flight range while minimizing the radar signature which is a crucial performance parameter for survivability. It is known that shaping of a missile according to aerodynamic performance may have significant negative effects on the radar cross section. Thus, the impact of the geometry changes on the aerodynamic performance and the radar cross section is investigated. Suggorage models for the flight range, control...
Citation Formats
E. Akyılmaz, “Similarity ratio based algorithms to generate SAR superpixels,” Ph.D. - Doctoral Program, Middle East Technical University, 2017.