Motion Estimation Using Physical Simulation

Research output: Contribution to conference (unpublished)Paperpeer-review

10 Citations (Scopus)
142 Downloads (Pure)

Abstract

We consider the task of monocular visual motion estimation from video image sequences. We hypothesise that performance on the task can be improved by incorporating an understanding of physically likely and feasible object dynamics. We test this hypothesis by incorporating a physical simulator into a least-squares estimation procedure. We initialise a full trajectory estimate using RANSAC followed by gradient descent refinement. We present results for 2D image sequences consisting of single ambiguous, visible or occluded balls, as well as results for 3D computer-generated sequences of objects in free-flight with added noise. Results suggest that restricting the estimation to allow only motions that are feasible according to the physics simulator can produce marked improvement when the observed object motion is within the limits of the physics simulator and its world model. Conversely, merely penalising deviations from feasible physical dynamics produces a consistent but incremental improvement over more common dynamics models.
Original languageEnglish
Pages1511-1517
Number of pages7
DOIs
Publication statusPublished - 7 May 2010
EventProceedings of the 2010 IEEE International Conference on Robotics and Automation (ICRA 2010) -
Duration: 7 May 2010 → …

Conference

ConferenceProceedings of the 2010 IEEE International Conference on Robotics and Automation (ICRA 2010)
Period7/05/10 → …

Fingerprint

Dive into the research topics of 'Motion Estimation Using Physical Simulation'. Together they form a unique fingerprint.

Cite this