The first steps in the design and construction of an autonomous vehicle for the physically and sensory disabled are described. The vehicle is basically a self-navigating wheelchair, which is designed to transport a person to a desired room within an office building given only the destination room number. The wheelchair has been equipped with an on-board microcomputer, a digital camera, and a scanning ultrasonic rangefinder. The goal of the project is to develop a vehicle that can operate without human intervention within a crowded environment with little or no impact on the building or its inhabitants. An overview of the project objectives and a detailed description of the components that are currently working are presented.

An important application of machine vision systems is the recognition of known three-dimensional objects. A major difficulty arises when two or more objects project the same or similar two-dimensional image, often resulting in misclassification and degradation of system performance. The changes in images which result from the motion of objects provide a source of three-dimensional information which can greatly aid the classification process, but this three-dimensional analysis is computationally complex and subject to many sources of error. This work develops a methodology which utilizes the information derived from the apparent changes in object features over time to facilitate the recognition task, without the need to actually recover the three-dimensional structure of the objects under view. The basic approach is to generate a ``feature signature'' by combining the feature measurements of the individual regions in a long sequence of images. The static information in the individual frames is analyzed along with the temporal information from the entire sequence. These techniques are particularly applicable in situations where static image processing methods cannot discriminate between ambiguous objects. Two example implementations are presented to illustrate the application of the techniques of object recognition using motion information.