Effective feature extraction is the basis of every approach to automated image analysis. An important class of extraction operators, point and region of interest detectors, has not yet been developed for SAR Polarimetry. This paper describes a region of interest operator designed to identify distinctive regions in a scale invariant fashion. The work presented includes a novel definition of image entropy, in the information theoretical sense, for polarimetric SAR image content, as well as a rigorous statistical analysis of the operators scale selection mechanism. This analysis establishes the ability to identify a region irrespec- tive of its size. The results presented include the application of the operator to real data and demonstrations of the operators scale invariance. I. INTRODUCTION Feature extractors, for instance edge detectors, act as con- centrators of information that emphasise certain relevant prop- erties of an image and suppress noise and other types of irrele- vant information. This process is essential to algorithms which aim to provide high level, semantic interpretations of image content. This is partly due to the fact that such algorithms are easier to formulate if certain types of information are available, but also because images contain such a wealth of information that an exhaustive analysis is usually infeasible. A number of feature extraction operators have been proposed in the context of polarimetric SAR data. Ideally, these operators are designed to take the statistical properties of SAR images into account. Examples include polarimetric edge detectors (1) and texture descriptors (2). An important class of operators, point of interest and region of interest (ROI) detectors, has not yet been developed for SAR remote sensing data. ROI operators identify distinctive, prominent or highly informative patches in an image, and are employed to achieve sparse but succinct representations of complex image data. A wide range of problems in the automated analysis of image data can be formulated as search problems, where there is a need to identify certain objects or segments of a scene. In these types of problem, an operator which reduces an entire image to a comparatively small collection of patches, which are localised and have a known size, can greatly reduce the size of the search space to be considered.
[1]
Knut Conradsen,et al.
CFAR edge detector for polarimetric SAR images
,
2003,
IEEE Trans. Geosci. Remote. Sens..
[2]
Volker Rodehorst.
Photogrammetrische 3D-Rekonstruktion im Nahbereich durch Auto-Kalibrierung mit projektiver Geometrie
,
2004
.
[3]
Knut Conradsen,et al.
A test statistic in the complex Wishart distribution and its application to change detection in polarimetric SAR data
,
2003,
IEEE Trans. Geosci. Remote. Sens..
[4]
G LoweDavid,et al.
Distinctive Image Features from Scale-Invariant Keypoints
,
2004
.
[5]
Michael Brady,et al.
Saliency, Scale and Image Description
,
2001,
International Journal of Computer Vision.
[6]
Pietro Perona,et al.
A Bayesian approach to unsupervised one-shot learning of object categories
,
2003,
Proceedings Ninth IEEE International Conference on Computer Vision.
[7]
Thomas L. Ainsworth,et al.
A wavelet multiresolution technique for polarimetric texture analysis and segmentation of SAR images
,
2004,
IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.