Image Understanding Research at Colorado State University

Colorado State University is initiating a new project on learning control strategies for object recognition. It is our belief that the current library of IU algorithms is su cient for solving many practical tasks if we can only learn to sequence them properly. We are investigating the use of open-loop and closed-loop control policies for sequencing IU algorithms, emphasizing the use of Markov decision models and reinforcement learning to derive closed-loop object recognition policies. This work is being conducted in the context of the Automatic Population of Geospatial Databases (APGD) project, where it will be used to learn object recognition strategies for nding buildings, roads and other objects of interest in aerial images.