LADAR Range Image Segmentation using Curve Evolution and Maximum Likelihood Estimation

In this paper, we develop a new maximum likelihood-based, curve evolution approach for laser radar range image segmentation. This approach combines a hybrid scene model for representing the range distribution of the field and a statistical mixture model for the range data measurement noise. The image segmentation problem is formulated as an energy minimization problem which jointly estimates the target boundary together with the target region intensity and background texture directly from the noisy range data. Curve evolution techniques and an expectation-maximization algorithm are jointly employed as an efficient solver for minimizing the objective energy