This paper introduces a novel class of descriptors constructed solely from the extraction of a feature set's qualities of location, magnitude and orientation. Oriented Feature Constellations (OFC) descriptors are unlike typical feature descriptors that separate feature extraction from definition, where local underlying pixel information is used to form a unique high-dimensional vector for matching. We use other extracted features within the local neighborhood, or local constellation, to define unique descriptors for matching. This idea is demonstrated by creating a corner orientation extension to Features from Accelerated Segment Test (FAST) corners and use these features to create descriptors, called OFC-FAST. Using a standard two stage matcher to generate dense matches across test image sets, we compare our results with those obtained using Scale Invariant Feature Transform (SIFT) features. OFC-FAST descriptors were able to generate disparity maps of higher densities while using less computational time than the comparison method was able to achieve. We believe that the capability of OFC descriptors to quickly generate higher density disparity maps will be useful for applications in semi-dense 3D reconstruction.

In SAR applications, the size of data can be quite large, and many data compression algorithms have been developed to reduce the storage requirements for SAR data. Previous research has been done on the compression of both amplitude and raw SAR data. However, the performance metrics used in these compression schemes are often visual-related metrics such as peak-signal-to-noise ratio (PSNR) or signal-to-quantization-noise ratio (SQNR). These metrics have been shown to provide misleading results for data with large dynamic range such as raw SAR data. The present research evaluates the performance of popular compression algorithms for raw SAR data in both SQNR and coherent change detection (CCD), which is superior in detecting subtle, man-made changes in the scene [1]. The results shows that higher SQNR does not lead to better CCD. This finding determines that the popular compression methods currently being used are not optimized for SAR data with respect to CCD.