ePrints Repository

Motion estimation using physical simulation

Duff, Damien Jade and Wyatt, Jeremy and Stolkin, Rustam (2010) Motion estimation using physical simulation. In: IEEE International Conference on Robotics and Automation, May 3-7 2010, Alaska, USA.

PDF - PDFLatex and CutePDF (1543Kb)Updated Version

URL of Published Version: http://dx.doi.org/10.1109/ROBOT.2010.5509590

Identification Number/DOI: doi:10.1109/ROBOT.2010.5509590

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.

Type of Work:Conference or Workshop Item
Date:03 May 2010 (Publication)
School/Faculty:Colleges (2008 onwards) > College of Engineering & Physical Sciences
Department:School of Computer Science
Keywords:physical cognition, physics simulation, 2D image sequences , computer generated object sequences , RANSAC , feasible object dynamics , full trajectory estimate , gradient descent refinement , least-squares estimation procedure , monocular visual motion estimation , physical simulation , video image sequences
Subjects:QA75 Electronic computers. Computer science
QA76 Computer software
QC Physics
Institution:University of Birmingham
Copyright Holders:IEEE
ID Code:977
Export Reference As : ASCII + BibTeX + Dublin Core + EndNote + HTML + METS + MODS + OpenURL Object + Reference Manager + Refer + RefWorks
Share this item :
QR Code for this page

Repository Staff Only: item control page