Visual Interpretation and Understanding
Dept Cognitive and Computing Sciences
University of Sussex
Brighton BN1 9QH
Dept Computer Science
In this review, we first define the subfield of visual interpretation and understanding and then address three major issues in using knowledge to increase the functionality and performance of vision systems. These selected issues are the role of context, control and learning. In section 2, we outline four approaches and key papers on 1) constraint-based vision, 2) model-based vision, 3) formal logic, and 4) probabilistic frameworks for visual interpretation and control. In section 3, we discuss the exploitation of these techniques in automating linguistic descriptions of scenes, enhancing human computer interaction in multimodal and multimedia systems, in behavioural control for robotics, advanced surveillance systems and biomedical image analysis systems. Finally, we conclude with new directions using deformable models, dynamic learning, and situated approaches to visual understanding.