Distributed Control of Attention

Detection of objects is in general a computationally demanding task. To simplify the problem it is of interest to focus the attention to a set of regions of interest. Indoor environments often have large homogeneous textured objects, such as walls and furniture. In this paper we present a model which detects large homogeneous regions and uses this information to search for targets that are smaller in size. Homogeneity is detected by a number of different descriptors and a coalition technique is used to achieve robustness. Expectations about size allow for constraint object search. The presented model is evaluated in the context of a table top scenario.