Recognizing multiple overlapping objects in image: an optimal formulation
S.Z. Li · IEEE Transactions on Image Processing · 2000
A statistically optimal formulation is presented for recognizing multiple, partially occluded objects. The optimality, in terms of the maximum a posteriori (MAP) principle, is with respect to all, rather than just individual modeled objects. Various constraints are incorporated into the posterior distribution. A two-stage MAP estimation approach is proposed to reduce the computational cost.