Depth map calculation for a variable number of moving objects using Markov sequential object processes
IEEE Transactions on Pattern Analysis and Machine Intelligence , Volume 30 p. 1308- 1312
We advocate the use of Markov sequential object processes for tracking a variable number of moving objects through video frames with a view towards depth calculation. A regression model based on a sequential object process quantifies goodness of fit; 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 depths and illustrate the approach on a synthetic data set as well as a sport sequence.
|, , , , ,|
|I.E.E.E. Computer Society Press|
|IEEE Transactions on Pattern Analysis and Machine Intelligence|
|Markov sequential point processes for image analysis and statistical physics|
van Lieshout, M.N.M. (2008). Depth map calculation for a variable number of moving objects using Markov sequential object processes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 1308–1312.