The authors present a framework to guide development of evidential reasoning in object recognition systems. Principles of evidential reasoning processes for open-world object recognition are proposed and applied to build evidential reasoning capabilities. The principles summarize research and findings by the authors up through the mid-1990s, including seminal results in object-centered computer vision, figure-ground discrimination, and the application of hierarchical Bayesian inference, Bayesian networks, and decision graphs to evidential reasoning for object recognition.

Considers the applications of expert systems to complex military problems. A brief description of needs for expert systems in the military arena is given. An important aspect of expert systems concerns using uncertain information and ill-defined procedures. Many of the general techniques of dealing with uncertainty are described. The major portion of this work addresses specific expert system examples such as resource allocation, identification of radar images, maintenance and troubleshooting of electronic equipment, and the interpretation and understanding of radar images. Extensions of expert systems to incorporate learning are examined in the context of military intelligence to determine the disposition, location, and intentions of the adversary. The final application involves the use of distributed communicating cooperating expert systems for battle management.>

We present an architecture for terrain recognition for an autonomous land vehicle. Basic components of this are a set of data bases for generic object models, perceptual structures, temporary memory for the instantiation of object and relational hypothesis, and a long term memory for storing stable hypothesis which are affixed to the terrain representation. Different inference processes operate over these data bases. We describe components of this architecture: the perceptual structure data base, the grouping processes that operate over this, and schemas. We conclude with a processing example for matching predictions from the long term terrain model to imagery and extracting significant perceptual structures for consideration as potential landmarks.

This paper describes an inspection system designed to automatically detect and classify surface imperfections occurring on continuously cast hot steel slabs in a steel mill. The need to perform inspection at real-time throughput rates of 546 Kpixels/s using off-the-shelf components has led to the development of a unique architecture and algorithm set. The segmentation operations are done in a high-speed array processor front end. The imperfection classification is done in a mini-computer which uses statistical as well as syntactic/semantic classification techniques. The inspection system is currently undergoing evaluation in a steel mill.