Depth map calculation for a variable number of moving objects
using Markov sequential object processes
We advocate the use of Markov sequential object processes for tracking a variable number of moving objects through a video frame with a view towards depth map calculation. A regression model based on a sequential object process is related to the Hough transform; regularization terms are incorporated to control within and between frame object interactions. We construct a Markov chain Monte Carlo method for finding the optimal tracks and associated depth maps and illustrate the approach on a synthetic data set and a sport sequence.