Title :
Combined Region and Motion-Based 3D Tracking of Rigid and Articulated Objects
Author :
Brox, Thomas ; Rosenhahn, Bodo ; Gall, Juergen ; Cremers, Daniel
Author_Institution :
Dept. of Comput. Sci., Univ. of California, Berkeley, CA, USA
fDate :
3/1/2010 12:00:00 AM
Abstract :
In this paper, we propose the combined use of complementary concepts for 3D tracking: region fitting on one side and dense optical flow as well as tracked SIFT features on the other. Both concepts are chosen such that they can compensate for the shortcomings of each other. While tracking by the object region can prevent the accumulation of errors, optical flow and SIFT can handle larger transformations. Whereas segmentation works best in case of homogeneous objects, optical flow computation and SIFT tracking rely on sufficiently structured objects. We show that a sensible combination yields a general tracking system that can be applied in a large variety of scenarios without the need to manually adjust weighting parameters.
Keywords :
image motion analysis; image segmentation; image sequences; object detection; optical tracking; SIFT feature; SIFT tracking; articulated object; motion-based 3D tracking; object region tracking; object segmentation; optical flow; region fitting; rigid object; Biological system modeling; Cameras; Humans; Image edge detection; Image motion analysis; Image segmentation; Optical computing; Optical sensors; Robot vision systems; Tracking; Tracking; motion.; segmentation; Algorithms; Humans; Image Processing, Computer-Assisted; Models, Statistical; Movement;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2009.32