Multi-model fitting based on minimum spanning tree

Fathalla, Radwa and Vogiatzis, George (2014). Multi-model fitting based on minimum spanning tree. IN: BMVC 2014 : proceedings of the British Machine Vision Conference 2014. Valstar, Michel; French, Andrew and Pridmore, Tony (eds) British Machine Vision Association, BMVA.


This paper presents a novel approach to the computation of primitive geometrical structures, where no prior knowledge about the visual scene is available and a high level of noise is expected. We based our work on the grouping principles of proximity and similarity, of points and preliminary models. The former was realized using Minimum Spanning Trees (MST), on which we apply a stable alignment and goodness of fit criteria. As for the latter, we used spectral clustering of preliminary models. The algorithm can be generalized to various model fitting settings, without tuning of run parameters. Experiments demonstrate the significant improvement in the localization accuracy of models in plane, homography and motion segmentation examples. The efficiency of the algorithm is not dependent on fine tuning of run parameters like most others in the field.

Divisions: Engineering & Applied Sciences > Computer science
Engineering & Applied Sciences > Computer science research group
Engineering & Applied Sciences > Systems analytics research institute (SARI)
Event Title: 25th British Machine Vision Conference
Event Type: Other
Event Dates: 2014-09-01 - 2014-09-05
Uncontrolled Keywords: Computer Vision and Pattern Recognition
Full Text Link: http://www.bmva ... es/paper122.pdf
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
Published Date: 2014-09-30
Authors: Fathalla, Radwa
Vogiatzis, George



Version: Published Version

| Preview

Export / Share Citation


Additional statistics for this record