From Contextual Knowledge to Computational Constraints

In this work we address the issue of focused computation in computer vision for effectiveness and efficiencyIn particular, we propose a scheme that links scene-oriented contextual knowledge with the computational constraints required in visual motion segmentation and tracking. The approach uses Ra.yesia.ii belief revision techniques to map explicit scene knowledge onto implicit causal dependent constraints in controlling computational parameters. We discuss our experimental results from applying this method in improving existing techniques in traffic surveillance applications.