Title :
Fused multi-sensor image mining for feature foundation data
Author :
Streilein, William ; Waxman, Allen ; Ross, William ; Liu, Fang ; Braun, Michael ; Fay, David ; Harmon, Paul ; Read, Chung Hye
Author_Institution :
Lincoln Lab., MIT, Lexington, MA, USA
Abstract :
Presents work on methods and user interfaces developed for interactive mining for feature foundation data (e.g. roads, rivers, orchards, forests) in fused multi-sensor imagery. A suite of client/server-based tools, including the Site Mining Tool and Image Map Interface, enable image analysts (IAs) to mine multi-sensor imagery for feature foundation data and to share trainable search agents, search results and image annotations with other IAs connected via a computer network. We discuss extensions to the fuzzy ARTMAP neural network which enable the Site Mining Tool to report confidence measures for detected search targets and to automatically select the critical features in the input vector which are most relevant for particular searches. Examples of the use of the Site Mining Tool and Image Map Interface are shown for an electo-optical (EO), IR and SAR data set derived from Landsat and Radarsat imagery, as well as multispectral (4-band) and hyperspectral (224-band) data sets. In addition, we present an architecture for the enhancement of hyperspectral fused imagery that utilizes internal category activity maps of a trained fuzzy ARTMAP network to enhance the visualization of targets in the color-fused imagery.
Keywords :
ART neural nets; client-server systems; data mining; data visualisation; feature extraction; fuzzy neural nets; image recognition; remote sensing; sensor fusion; user interfaces; 3D target visualization; IR data; Image Map Interface; Landsat imagery; Radarsat imagery; SAR data; Site Mining Tool; client/server-based tools; collaborative exploitation; color-fused imagery; computer network; confidence measures; detected search targets; electrooptical data; feature foundation data; fused multi-sensor image mining; fuzzy ARTMAP neural network; hyperspectral data sets; image analysis; image annotations; image enhancement architecture; input vector critical feature selection; interactive data mining; internal category activity maps; multispectral data sets; pattern recognition; search results; sensor fusion; synthetic aperture radar; target recognition; trainable search agents; user interfaces; Computer networks; Fuzzy neural networks; Hyperspectral imaging; Image analysis; Neural networks; Particle measurements; Radar detection; Rivers; Roads; User interfaces;
Conference_Titel :
Information Fusion, 2000. FUSION 2000. Proceedings of the Third International Conference on
Conference_Location :
Paris, France
Print_ISBN :
2-7257-0000-0
DOI :
10.1109/IFIC.2000.862686
