TY - CONF T1 - Integration of visual and inertial information for egomotion: a stochastic approach T2 - Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006 Y1 - 2006 A1 - Domke, J. A1 - Aloimonos, J. KW - Computer vision KW - data mining KW - Distributed computing KW - egomotion estimation KW - Gabor filters KW - Gravity KW - inertial information KW - inertial sensor KW - Laboratories KW - Motion estimation KW - Noise measurement KW - Probability distribution KW - probability distributions KW - Rotation measurement KW - stochastic approach KW - Stochastic processes KW - visual information AB - We present a probabilistic framework for visual correspondence, inertial measurements and egomotion. First, we describe a simple method based on Gabor filters to produce correspondence probability distributions. Next, we generate a noise model for inertial measurements. Probability distributions over the motions are then computed directly from the correspondence distributions and the inertial measurements. We investigate combining the inertial and visual information for a single distribution over the motions. We find that with smaller amounts of correspondence information, fusion of the visual data with the inertial sensor results in much better egomotion estimation. This is essentially because inertial measurements decrease the "translation-rotation" ambiguity. However, when more correspondence information is used, this ambiguity is reduced to such a degree that the inertial measurements provide negligible improvement in accuracy. This suggests that inertial and visual information are more closely integrated in a compositional sense JA - Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006 PB - IEEE SN - 0-7803-9505-0 M3 - 10.1109/ROBOT.2006.1642007 ER -