Synthetic aperture radar (SAR) is a remote sensing technology that can truly operate 24/7. It's an all-weather system that can operate at any time except in the most extreme conditions. Coherent change detection (CCD) in SAR can identify minute changes such as vehicle tracks that occur between images taken at different times. From polarimetric SAR capabilities, researchers have developed decompositions that allow one to automatically classify the scattering type in a single polarimetric SAR (PolSAR) image set. We extend that work to CCD in PolSAR images to identify the type change. Such as change caused by no return regions, trees, or ground. This work could then be used as a preprocessor for algorithms to automatically detect tracks.
Sandia National Laboratories (SNL) flew its Facility for Advanced RF and Algorithm Development (FARAD) X-Band (9.6 GHz center frequency), fully-polarimetric synthetic aperture radar (PolSAR) in VideoSAR-mode to collect complex-valued SAR imagery before, during, and after the fifth and sixth Source Physics Experiment's (SPE-5 and SPE-6) underground explosion. The results from the fifth Source Physics Experiment (SPE-5) used single-polarimetric VideoSAR data while SPE-6 used single and fully-polarimetric VideoSAR data. We show that SAR can provide surface change products indicative of disturbances caused by the underground chemical explosions. These are surface coherence measures, Po1SAR change signatures, and differential interferometric SAR (InSAR) height change.
A new method is introduced for combining information from multiple sources to support one-class classification. The contributing sources may represent measurements taken by different sensors of the same physical entity, repeated measurements by a single sensor, or numerous features computed from a single measured image or signal. The approach utilizes the theory of statistical hypothesis testing, and applies Fisher's technique for combining p-values, modified to handle nonindependent sources. Classifier outputs take the form of fused p-values, which may be used to gauge the consistency of unknown entities with one or more class hypotheses. The approach enables rigorous assessment of classification uncertainties, and allows for traceability of classifier decisions back to the constituent sources, both of which are important for high-consequence decision support. Application of the technique is illustrated in two challenge problems, one for skin segmentation and the other for terrain labeling. The method is seen to be particularly effective for relatively small training samples.
The goal of this SAND report is to provide guidance for other groups hosting workshops and peerto-peer learning events at Sandia. Thus this SAND report provides detail about our team structure, how we brainstormed workshop topics and developed the workshop structure. A Workshop “Nuts and Bolts” section provides our timeline and check-list for workshop activities. The survey section provides examples of the questions we asked and how we adapted the workshop in response to the feedback.
In an effort to enhance image classification of terrain features in fully polarimetric SAR images, this paper explores the utility of combining the results of two state-of-the-art decompositions along with a semi-supervised classification algorithm to classify each pixel in an image. Each pixel is labeled either with a pre-determined classification label, or labeled as unknown.