14 June 1984 Contextual Analysis Of Tactical Scenes
Author Affiliations +
Proceedings Volume 0485, Applications of Artificial Intelligence I; (1984) https://doi.org/10.1117/12.943184
Event: 1984 Technical Symposium East, 1984, Arlington, United States
Abstract
Current automated approaches for recognizing spatially localized objects fall short of human recognition performance for two reasons. First, the classical statistical pattern recognizer uses only locally measured scene information in the recognition process. Contextual information can and should be extracted and exploited to enhance automated statistical approaches. Second, the human recognizer is able to learn from and adapt to new situations, while the automatic statistical pattern recognizer is confounded by any object that fails to match some subset of its training experience. Techniques from artificial intelligence can be employed to endow the machine with the ability to adapt to the scene at hand based on feedback of derived scene information. This paper describes an intelligent automated object recognition system that uses extracted scene context and feedback for improved recognition.
© (1984) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Arthur V. Forman, Arthur V. Forman, Patricia J. Rowland, Patricia J. Rowland, Wade G. Pemberton, Wade G. Pemberton, "Contextual Analysis Of Tactical Scenes", Proc. SPIE 0485, Applications of Artificial Intelligence I, (14 June 1984); doi: 10.1117/12.943184; https://doi.org/10.1117/12.943184
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

A General Approach To Knowledge-Based Vision
Proceedings of SPIE (March 28 1989)
Multisensorial Vision For Autonomous Vehicle Driving
Proceedings of SPIE (March 20 1989)
A Knowledge-Based Approach To Ship Identification
Proceedings of SPIE (March 25 1986)
Knowledge Based Sar Images Exploitation
Proceedings of SPIE (May 10 1987)
"Real-Time Computer Vision Using Intelligent Hardware"
Proceedings of SPIE (March 25 1986)

Back to Top