PROGRESS ON VISION THROUGH LEARNING: A Collaborative Effort of George Mason University and University of Maryland

This report briefly reviews research progress on vision through learning conducted as a collaborative effort of the GMU Machine Learning and Inference Laboratory and the UMD Computer Vision Laboratory. The report covers work done on the following projects: (1)The Multi-level Image Sampling and Transformation (MIST) methodology for learning image descriptions and transformations (2) Applying the MIST methodology to semantic analysis of outdoor scenes (3) Recognizing objects in a cluttered environment (4) Learning in navigation (5) Intelligent interfaces: Learning in the RADIUS environment (6) Learning space configuration and homing (7) Learning object functionality Our work aims at ultimately developing vision systems that apply a range of symbolic and parametric machine learning methods to solving vision problems. __________________________ † This research was supported by the Advanced Research Projects Agency under grants F49620-92-J-0549 and F49620-95-1-0462, administered by the Air Force Office of Scientific Research. The development of machine learning systems used in this research was supported in part by the Advanced Research Projects Agency under grant No. N00014-91-J-1854, administered by the Office of Naval Research, in part by the Office of Naval Research under grant N00014-91-J-1351, and in part by the National Science Foundation under grants IRI9020266, CDA-9310297 and CDA-9309725.