Showing papers by "Jiri Matas published in 1996"
01 Jan 1996
TL;DR: A method that employs grammars to direct the inference process of a vision system that does interpretation of dynamic scenes is described, using a set of qualitative image descriptors to drive the interpretation and producing a 'natural language' description of scene activities.
Abstract: A method that employs grammars to direct the inference process of a vision system that does interpretation of dynamic scenes is described The system uses a set of qualitative image descriptors to drive the interpretation The result is a 'natural language' description of scene activities In addition the inference engine generates a set of predictions that can be used to control the interpretation strategy so as to make the processing of new images more efficient The system has been implemented in an expert system shell to demonstrate the viability of the approach Results on real images are reported
11 citations
16 Sep 1996
TL;DR: In this article, a method that employs grammars to direct the inference process of a vision system that does interpretation of dynamic scenes is described, which uses a set of qualitative image descriptors to drive the interpretation.
Abstract: A method that employs grammars to direct the inference process of a vision system that does interpretation of dynamic scenes is described. The system uses a set of qualitative image descriptors to drive the interpretation. The result is a 'natural language' description of scene activities. In addition the inference engine generates a set of predictions that can be used to control the interpretation strategy so as to make the processing of new images more efficient. The system has been implemented in an expert system shell to demonstrate the viability of the approach. Results on real images are reported.
9 citations