Abstract
Recently the tensor voting framework (TVF), proposed by Medioni at al., has proved its effectiveness in perceptual grouping of arbitrary dimensional data. In the computer vision field, this algorithm has been applied to solve various problems as stereo-matching, boundary inference, and image inpainting. In the last decade the TVF was augmented with new saliency features, like curvature and first order tensors.
In this paper a new curvature estimation technique is described and its effectiveness, when used with the saliency functions proposed in [1], is demonstrated. Results are shown for synthetic datasets in spaces of different dimensionalities.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Campadelli, P., Lombardi, G.: Tensor voting fields: Direct votes computation and new saliency functions. In: Cucchiara, R. (ed.) ICIAP, pp. 677–684. IEEE Computer Society, Los Alamitos (2007)
Guy, G., Medioni, G.: Inferring global perceptual contours from local features. International journal of Computer Vision, 113–133 (1996)
Medioni, G., Kang, S.B.: Emerging topics in Computer Vision. Prentice-Hall, Englewood Cliffs (2004)
Mordohai, P., Medioni, G.: Tensor Voting: A Perceptual Organization Approach to Computer Vision and Machine Learning, 1st edn. Morgan and Claypool Publishers (2006)
Mordohai, P., Medioni, G.: Dense multiple view stereo with general camera placement using tensor voting. 3D Data Processing, Visualization and Transmission, pp. 725–732 (2004)
Mordohai, P., Medioni, G.: Stereo using monocular cues within the tensor voting framework. IEEE Trans. on PAMI 28(6), 968–982 (2006)
Jia, J., Tang, C.K.: Image repairing: Robust image synthesis by adaptive nd tensor voting. CVPR 01, 643 (2003)
Tong, W.S., et al.: First order augmentation to tensor voting for boundary inference and multiscale analysis in 3d. IEEE Trans. on PAMI 26(5), 858–863 (2004)
Nicolescu, M., Medioni, G.G.: Motion segmentation with accurate boundaries - a tensor voting approach. In: CVPR (1), pp. 382–389. IEEE Computer Society, Los Alamitos (2003)
Mordohai, P., Medioni, G.: Dimensionality estimation and manifold learning using tensor voting. Technical report, Institute for Robotics and Intelligent Systems, University of Southern California (2005)
Tang, C.K., Medioni, G.: Curvature-augmented tensor voting for shape inference from noisy 3d data. IEEE Trans. on PAMI 24(6), 858–863 (2002)
Fischer, S., et al.: Are iterations and curvature useful for tensor voting? In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 158–169. Springer, Heidelberg (2004)
Tang, C.K., Medioni, G.: Inference on integrated surface, curve, and junction descriptions from sparse 3d data. IEEE Trans. on PAMI 20(11), 1206–1223 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lombardi, G., Casiraghi, E., Campadelli, P. (2008). Curvature Estimation and Curve Inference with Tensor Voting: A New Approach. In: Blanc-Talon, J., Bourennane, S., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2008. Lecture Notes in Computer Science, vol 5259. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88458-3_55
Download citation
DOI: https://doi.org/10.1007/978-3-540-88458-3_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88457-6
Online ISBN: 978-3-540-88458-3
eBook Packages: Computer ScienceComputer Science (R0)