From image sequences towards conceptual descriptions

摘要

Four approaches towards the extraction of conceptual descriptions from image sequences which all evolved from the same 1977 proposal are surveyed. After a critical evaluation of the insights gained from these experimental approaches, the necessity to strive for a complete conceptual model of a (necessarily limited) discourse world is emphasized. It is suggested to introduce a ‘generically describable situation’ as a new conceptual unit for the computer-internal representation of more complex discourse worlds. References to other approaches for the extraction of descriptions from images and image sequences are pointed out for comparison.