From nobody@cs.Buffalo.EDU Thu Jun 26 16:12 EDT 1997 From: nobody@cs.Buffalo.EDU Date: Thu, 26 Jun 1997 16:11:58 -0400 (EDT) To: techreps@cs.Buffalo.EDU Subject: techrep: POST request Content-Type: text Content-Length: 1906 Comments: File is a gzip'ed Postscript document. ContactPerson: rchopra@cs.buffalo.edu Remote host: hassaleh.cedar.buffalo.edu Remote ident: unknown ### Begin Citation ### Do not delete this line ### %R 97-09 %U diss.ps %A Rajiv Chopra %T An Architecture for Exploiting Qualitative Scene-specific Context in High-Level Computer Vision %D June 1, 1997 %I Department of Computer Science, SUNY Buffalo %K constraint satisfaction; computer vision; interval arithmetic; context based vision; image understanding %X In this dissertation we present an architecture to incorporate collateral information in the high level computer vision task of object location. The declarative specification of the scene hypothesis and the domain independent control algorithm that exploits spatial information to drive the vision process, are two major contributions of this dissertation. This work has been theoretically grounded in constraint satisfaction algorithms. Apart from the application of standard CSP algorithms, several new techniques in constraint satisfaction have been developed. We provide an algorithm that performs consistency filtering for certain types of non-binary constraints. We also present an innovative application of interval arithmetic in constraint satisfaction. Though interval constraint satisfaction is an extensive research area, we believe this to be the first attempt at using interval arithmetic to reduce the domain generation cost of finite domain CSPs. A new algorithm has been proposed here for the above. Illustration with a simple example, analysis and implementation of the algorithm have also been detailed here. We have demonstrated the architecture in three implemented vision systems and have shown that it is simple yet powerful for application in several domains.