But cognitive vision is multifaceted, complicating this domain for computers. It can encode social and cultural knowledge, says the coordinator, using, for example, the location of knives and forks to identify plates. The team in Sweden is building robot that can clear dinner tables. Recent work on vision has broken down into research guided by artificial intelligence and geometry but with little integration of the two approaches. The process resembles computeraided design. No single technique, using basic clues, would recognise all the chairs here, admits Christensen. Today we lack techniques that allow us to correctly classify all objects in this image.

They could completely on their own in unfriendly or inaccessible environments. No single technique, using basic clues, would recognise all the chairs here, admits Christensen. One of this projects results integration of interpretation and modelling of human interaction could be used in video streaming. For example, during televised sports programmes, video recorders could be told to find and display specific goal or action.

And there will be per cent increase in the number of people of retirement age. The Information Society Technologies programmefunded project COGVIS has spent two years advancing computer vision. But cognitive vision is multifaceted, complicating this domain for computers. These machines be just decade away, believes the leader of European project studying the nuts and bolts of computer vision. The robot, developed in Italy, is studying armhand movement and grasping skills.

Vision has also typically been considered in isolation. For example, in this illustration, computer vision would find it difficult to distinguish between pictures and real objects. For example, during televised sports programmes, video recorders could be told to find and display specific goal or action. Next, the system could try to locate and grasp cup or only search for the cup that it wants to pick up. The robot, developed in Italy, is studying armhand movement and grasping skills. Yet it needs to be considered in the context of an embodied agent.

But cognitive vision is multifaceted, complicating this domain for computers. Although COGVIS focuses on basic research, it has been building robots to test out ideas. At the projects meeting, held in Leeds, England, various teams presented the results of their work. Such systems will perform taskoriented categorisation and recognition of objects and events, in the context of an embodied agent.