Amerinex Artificial Intelligence, Inc. (AAI) is proposing the project (Toolkit for Recognition and Automatic Classification of Solar Features) for a Phase II SBIR award in Solar Image Processing.The TRACS project is designed to facilitate the automatic recognition, analysis, and tracking, of solar features in digital images. The developed algorithms will be able to extract, classify, and track solar features, such as filaments, sun spots, or coronal holes, from images that are taken from a variety of sensors, at a variety of spectral bands, and under varying atmospheric conditions. Given the success in the Phase I project in the development of appropriate tools for Image Processing, Feature Extraction, and Feature Analysis, five new classes of algorithms will be developed under the Phase II TRACS project. Feature Extraction modules will expand the set of known solar features, and Feature Grouping algorithms will be used to construct hierarchical descriptions of combinations of theses image events. Feature Models will relate these (composite) image events to specific solar phenomena, and Feature Tracking/Prediction algorithms will permit a description of the movement of the features over time. Finally, User Interface/Data Display algorithms will allow users to control processing, view data, and edit and/or annotate results.Commercial Applications:The software developed for the TRACS project will provide fast and reliable classification and tracking of solar features, thereby improving the prediction of solar-terrestrial disturbances. Similar technology can also be applied to computer-aided imaging applications such as terrestrial forecasting, aerial image interpretation, security, or any domain where automatic feature extraction, analysis, and tracking can aid the interpretation of remotely sensed data.
