Disparity Estimation Based on Bayesian Maximum A Posteriori (MAP) Algorithm

摘要

In this paper, a general formula of disparity es- timation based on Bayesian Maximum A Posteriori (MAP) al- gorithm is derived and implemented with simplified probabilis- tic models. The formula is the generalized probabilistic diffu- sion equation based on Bayesian model, and can be implemented into some different forms corresponding to the probabilistic mod- els in the disparity neighborhood system or configuration. The probabilistic models are independence and similarity among the neighboring disparities in the configuration. The independence probabilistic model guarantees the discontinuity at the object boundary region, and the similarity model does the continuity or the high correlation of the disparity distribution. According to the experimental results, the proposed algorithm had good esti- mation performance. This result showes that the derived formula generalizes the probabilistic diffusion based on Bayesian MAP al- gorithm for disparity estimation. Also, the proposed prohabilistic models are reasonable and approximate the pure joint probabil- ity distribution very well with decreasing the computations to O(n(D)) from O(n(D)~4) of the generalized formula.