A robust head pose estimation system for uncalibrated monocular videos
Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
A probabilistic framework for learning kinematic models of articulated objects
Journal of Artificial Intelligence Research
Scale Invariant Feature Transform on the Sphere: Theory and Applications
International Journal of Computer Vision
PWP3D: Real-Time Segmentation and Tracking of 3D Objects
International Journal of Computer Vision
Motion capture of hands in action using discriminative salient points
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Parallel generalized thresholding scheme for live dense geometry from a handheld camera
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
On-set performance capture of multiple actors with a stereo camera
ACM Transactions on Graphics (TOG)
Hi-index | 0.14 |
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.