We present a new method using the Bayesian approach and a Markov random field (MRF) model of integrating several low level visual modules. Using this approach, we have shown how results from an edge based stereo module can be integrated with an intensity based stereo algorithm. In another example, results from a shape from shading module are combined with intensity based stereo. We first derive the intensity based stereo algorithm using the MRF model. The integration is then performed by coupling the results from other modules to the energy functional of the MRF associated with the intensity based stereo. The maximum a prosteriori (MAP) estimate of the resulting MRF is obtained using the mean field annealing algorithm. Results from real and artificial images show a consistent improvement in the accuracy after integration.
Richard W. Prager,
"Integrating visual modules: a Bayesian approach", Proc. SPIE 1956, Sensor Fusion and Aerospace Applications, (3 September 1993); doi: 10.1117/12.155077; https://doi.org/10.1117/12.155077