Paper review: Okada96Object

"Object tracking based on optical flow and depth"
[Abstract] This paper describes a method of tracking an object by fusing optical flow and depth. We calculate a probability of a pixel belonging to the target based on the prediction of the target region, estimation of target velocity and that of target depth. The pixels which have high probability are determined to be the target rigion. Because the target region is extracted by fusing optical flow and depth, our method is not noly able to extract the target region robustly, but also works even if tracking with either optical flow or depth alone may fail. Occlusion of the target can also be detected from the abrupt change of depth of the target region. Our method successfully tracked a moving person using a real image sequence.

@article{Okada96Object,
Journal = {IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems},
Year = {Dec. 1996},
Title = {Object Tracking Based on Optical Flow and Depth},
Number = {},
Pages = {565 - 571},
Author = {R. Okada and Y. Shirai and J. Miura },
Volume = {}}