Control in a 3D reconstruction system using selective perception

• Main Authors: Marengoni, M., Hanson, A., Zilberstein, S., Riseman, E.
• Format: Conference Proceeding
• Language: English
• Subjects: Applied sciences; Artificial intelligence; Bayesian methods; Computational complexity; Computer networks; Computer science; control theory; systems; Computer vision; Control systems; Exact sciences and technology; High performance computing; Image reconstruction; Pattern recognition. Digital image processing. Computational geometry; Testing; Uncertainty; Utility theory
• DOI: 10.1109/ICCV.1999.790421

This paper presents a control structure for general purpose image understanding that addresses both the high level of uncertainty in local hypotheses and the computational complexity of image interpretation. The control of vision algorithms is performed by an independent subsystem that uses Bayesian networks and utility theory to compute the marginal value of information provided by alternative operators and selects the ones with the highest value. We have implemented and tested this control structure with several aerial image datasets. The results show that the knowledge base used by the system can be acquired using standard learning techniques and that the value-driven approach to the selection of vision algorithms leads to performance gains. Moreover, the modular system architecture simplifies the addition of both control knowledge and new vision algorithms.