Abstract
This paper shows how the performance of feature trackers can be improved by building a view-based object representation consist- ing of qualitative relations between image structures at different scales. The idea is to track all image features individually, and to use the qual- itative feature relations for resolving ambiguous matches and for intro- ducing feature hypotheses whenever image features are mismatched or lost. Compared to more traditional work on view-based object tracking, this methodology has the ability to handle semi-rigid objects and par- tial occlusions. Compared to trackers based on three-dimensional object models, this approach is much simpler and of a more generic nature. A hands-on example is presented showing how an integrated application system can be constructed from conceptually very simple operations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Black, M. J. & Jepson A. (1998a), A probabilistic framework for matching temporal trajectories: Condensation-based recognition of gestures and expressions, in H. Burkhardt & B. Neumann, eds, ‘ECCV’98’, Vol. 1406 of Lecture Notes in Computer Science, Springer Verlag, Berlin, Freiburg, Germany, 909–924.
Black, M. J. & Jepson, A. (1998b), ‘Eigentracking: Robust matching and tracking of articulated objects using a view-based representation’, IJCV 26(1), 63–84.
Bretzner, L. & Lindeberg, T. (1998a), ‘Feature tracking with automatic selection of spatial scales’, Computer Vision and Image Understanding 71(3), 385–392.
Bretzner, L. & Lindeberg, T. (1998b), Use your hand as a 3-D mouse or relative orientation from extended sequences of sparse point and line correspondances using the affine trifocal tensor, in H. Burkhardt & B. Neumann, eds, ‘ECCV’98’, Vol. 1406 of Lecture Notes in Computer Science, Springer Verlag, Berlin, 141–157.
Burbeck, C. A. & Pizer, S. M. (1995), ‘Object representation by cores: Identifying and representing primitive spatial regions’, Vis. Res. 35(13), 1917–1930.
Crowley, J. L. & Parker, A. C. (1984), ‘A representation for shape based on peaks and ridges in the Difference of Low-Pass Transform’, IEEE-PAMI 6(2), 156–170.
Crowley, J. L. & Sanderson, A. C. (1987), ‘Multiple resolution representation and probabilistic matching of 2-D gray-scale shape’, IEEE-PAMI 9(1), 113–121.
Griffin, L. D., Colchester, A. C. F. & Robinson, G. P. (1992), ‘Scale and segmentation of images using maximum gradient paths’, IVC 10(6), 389–402.
Heap, T. & Hogg, D. (1996), Towards 3D hand tracking using a deformable model, in `Int. Conf. Automatic Face and Gesture Recognition’, Killington, Vermont, 140–145.
Isard, M. & Blake, A. (1998), A mixed-state condensation tracker with automatic model switching, in `6th ICCV’, Bombay, India, 107–112.
Koenderink, J. J. (1984), ‘The structure of images’, Biol. Cyb. 50, 363–370.
Koller, D., Daniilidis, K. & Nagel, H. (1993), ‘Model-based object tracking in monocular image sequences of road traffic scenes’, IJCV 257–281.
Kuch, J. J. & Huang, T. S. (1995), Vision based hand modelling and tracking for virtual teleconferencing and telecollaboration, in `5th ICCV’, Cambridge, MA, 666–671.
Lifshitz, L. & Pizer, S. (1990), ‘A multiresolution hierarchical approach to image segmentation based on intensity extrema’, IEEE-PAMI 12(6), 529–541.
Lindeberg, T. (1993), ‘Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention’, IJCV 11(3), 283–318.
Lindeberg, T. (1994), Scale-Space Theory in Computer Vision, Kluwer, Netherlands.
Lindeberg, T. (1998a), ‘Edge detection and ridge detection with automatic scale selection’, IJCV 30(2), 117–154.
Lindeberg, T. (1998b), ‘Feature detection with automatic scale selection’, IJCV 30(2), 77–116.
Lindeberg, T. & Bretzner, L. (1998), Förfarande och anordning för överföring av information genom rörelsedetektering, samt användning av anordningen. Patent pending.
Mauerer, T. & von der Malsburg, C. (1996), Tracking and learning graphs and pose on images of faces, in `Int. Conf. Automatic Face and Gesture Recognition’, Killington, Vermont, 176–181.
Olsen, O. F. (1997), Multi-scale watershed segmentation, in J. Sporring, M. Nielsen, L. Florack & P. Johansen, eds, `Gaussian Scale-Space Theory: Proc. PhD School on Scale-Space Theory’, Kluwer, Copenhagen, Denmark, 191–200.
Pizer, S. M., Burbeck, C. A., Coggins, J. M., Fritsch, D. S. & Morse, B. S. (1994), ‘Object shape before boundary shape: Scale-space medial axis’, J. Math. Im. Vis.4, 303–313.
Shokoufandeh, A., Marsic, I. & Dickinson, S. J. (1998), View-based object matching, in `6th ICCV’, Bombay, India, 588–595.
Smith, S. M. & Brady, J. M. (1995), ‘Asset-2: Real-time motion segmentation and shape tracking’, IEEE-PAMI 17(8), 814–820.
Triesch, J. & von der Malsburg, C. (1996), Robust classification of hand postures against complex background, in `Int. Conf. Automatic Face and Gesture Recognition’, Killington, Vermont, 170–175.
Vincken, K., Koster, A. & Viergever, M. (1997), ‘Probabilistic multiscale image segmentation’, IEEE-PAMI 19(2), 109–120.
Yasumuro, Y., Chen, Q. & Chihara, K. (1999), ‘Three-dimensional modelling of the human hand with motion constraints’, IVC 17(2), 149–156.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bretzner, L., Lindeberg, T. (1999). Qualitative Multi-scale Feature Hierarchies for Object Tracking. In: Nielsen, M., Johansen, P., Olsen, O.F., Weickert, J. (eds) Scale-Space Theories in Computer Vision. Scale-Space 1999. Lecture Notes in Computer Science, vol 1682. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48236-9_11
Download citation
DOI: https://doi.org/10.1007/3-540-48236-9_11
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66498-7
Online ISBN: 978-3-540-48236-9
eBook Packages: Springer Book Archive