Abstract: An automated system is provided for classifying materials in remotely-sensed imagery based on automated construction of a dynamic classifier—namely, a classifier that is automatically trained on the same image to which it is then subsequently applied. A first automated process identifies high confidence exemplars of each class using tailored classification techniques. This data is then used to train a supervised classification model (e.g., discriminant analysis), and the resultant classifier is applied to other pixels in the image that are unclassified or uncertain. Dynamic classification is automatically customized to the current image and can yield a more accurate and efficient material classification versus a static (image-independent) or manually trained classifier.

Abstract: Techniques are described for pooling data originating from different entities into a data pool managed by a data pool management system for performing accurate and resource-efficient statistical and other data operations by entities. Techniques further include maintaining rule sets that govern access to the data sets of the data pool. The DPMS uses the rule sets to determine whether a particular data set, on which a particular operation is requested to be performed, qualifies as authorized data for the requesting entity. In an embodiment, the DPMS determines, based on one rule set, that the particular data set does not qualify as authorized data for the particular operation. The DPMS further determines that based on another rule set the particular data set does qualify as authorized data for the particular operation. Based on determining that authorizing rule set overrides the non-authorizing rule set, DPMS proceeds to performing the particular operation using the particular data set.

Abstract: Techniques are described for pooling data originating from different entities into a data pool managed by a data pool management system for performing accurate and resource-efficient statistical and other data operations by entities. Techniques further include maintaining rule sets that govern access to the data sets of the data pool. The DPMS uses the rule sets to determine whether a particular data set, on which a particular operation is requested to be performed, qualifies as authorized data for the requesting entity. In an embodiment, the DPMS determines, based on one rule set, that the particular data set does not qualify as authorized data for the particular operation. The DPMS further determines that based on another rule set the particular data set does qualify as authorized data for the particular operation. Based on determining that authorizing rule set overrides the non-authorizing rule set, DPMS proceeds to performing the particular operation using the particular data set.

Abstract: An automated system is provided for classifying materials in remotely-sensed imagery based on automated construction of a dynamic classifier—namely, a classifier that is automatically trained on the same image to which it is then subsequently applied. A first automated process identifies high confidence exemplars of each class using tailored classification techniques. This data is then used to train a supervised classification model (e.g., discriminant analysis), and the resultant classifier is applied to other pixels in the image that are unclassified or uncertain. Dynamic classification is automatically customized to the current image and can yield a more accurate and efficient material classification versus a static (image-independent) or manually trained classifier.

Abstract: Techniques are described for pooling data originating from different entities into a data pool managed by a data pool management system for performing accurate and resource-efficient statistical and other data operations by entities. Techniques further include maintaining rule sets that govern access to the data sets of the data pool. The DPMS uses the rule sets to determine whether a particular data set, on which a particular operation is requested to be performed, qualifies as authorized data for the requesting entity. In an embodiment, the DPMS determines, based on one rule set, that the particular data set does not qualify as authorized data for the particular operation. The DPMS further determines that based on another rule set the particular data set does qualify as authorized data for the particular operation. Based on determining that authorizing rule set overrides the non-authorizing rule set, DPMS proceeds to performing the particular operation using the particular data set.