University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Combining the hough transform and multiresolution MRF's for the robust motion estimation

Bober, M and Kittler, J (1996) Combining the hough transform and multiresolution MRF's for the robust motion estimation

Full text not available from this repository.


© Springer-Verlag Berlin Heidelberg 1996.The paper presents a novel approach to the Robust Analysis of Complex Motion. It employs a low-level robust motion estimator, conceptually based on the Hough Transform, and uses Multiresolution Markov Random Fields for the global interpretation of the local, low-level estimates. Motion segmentation is performed in the front-end estimator, in parallel with the motion parameter estimation process. This significantly improves the accuracy of estimates, particularly in the vicinity of motion boundaries, facilitates the detection of such boundaries, and allows the use of larger regions, thus improving robustness. The measurements extracted from the sequence in the front-end estimator include displacement, the spatial derivatives of the displacement, confidence measures, and the location of motion boundaries. The measurements are then combined within the MRF framework, employing the supercoupling approach for fast convergence. The excellent performance, in terms of estimate accuracy, boundary detection and robustness is demonstrated on synthetic and real-word sequences.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions : Surrey research (other units)
Authors :
Kittler, J
Date : 1 January 1996
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 13:47
Last Modified : 23 Jan 2020 18:50

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800