Community Research and Development Information Service - CORDIS


This paper addresses the problem of recovering 3-D motion parameters from optical flow fields calculated from two or more consecutive pairs of perspective images. The proposed approach is based on the ideas of Randomised Hough Transform (RHT), i.e., the principles of random sampling of velocity vectors and accumulation of motion parameters. The experiments with simulated and real image data in translational and general motion cases demonstrate that a robust interpretation of 3-D motion parameters can be obtained even in the presence of significant levels of noise.

Additional information

Authors: HEIKKONEN J, JRC Ispra (IT)
Bibliographic Reference: Article: Pattern Recognition Letters (1995)
Record Number: 199511152 / Last updated on: 1995-08-23
Original language: en
Available languages: en