This review paper takes a user-orientated view of knowledge-based computer vision systems - a viewpoint biased towards the practical applications of the technology as a component in a real-time control system. It inve...
详细信息
This paper describes the methodological and implementational aspects of an intelligent system which is being developed for the planning of plant-side process operations such as start-up, response to faults, optimizati...
详细信息
This paper describes the methodological and implementational aspects of an intelligent system which is being developed for the planning of plant-side process operations such as start-up, response to faults, optimization, etc. In particular, it shows how knowledge is modeled, how the planning methodology is structured, and how current developments in artificialintelligence and LISP computers are being used to provide the implementational framework.
This review paper takes a user-orientated view of knowledge-based computer vision systems – a viewpoint biased towards the practical applications of the technology as a component in a real-time control system. It inv...
详细信息
This review paper takes a user-orientated view of knowledge-based computer vision systems – a viewpoint biased towards the practical applications of the technology as a component in a real-time control system. It investigates the characteristics of this area of application and defines the potential role of vision-based systems. On the basis of this, it reviews current progress in fulfilling these roles. It highlights critical areas – especially the need to recognise that the industrial environment requires solutions which can co-exist in those environments, and can react at speeds which are acceptable in the closed-loop control situation of which they form a part. It is argued that simply bringing together well-understood low-level processing systems and currently-available expert systems-based high-level processing, is bound to fail and indeed partially accounts for the many unsuccessful installations. In practice, a total systems-approach must be taken, recognising the realities of the application – including the still-unresolved problems relating to knowledge-acquisition. The paper concludes that low- and high-level processing must be integrated into highly flexible, explicit knowledge-based solutions to produce systems which are capable of fast, deterministic performance, but have inherent learning capabilities to cope with changing applications.
暂无评论