ICRA'09 Paper Abstract


Paper FrA2.16

Cohen, Benjamin (University of Pennsylvania), Byrne, Jeffrey (University of Pennsylvania)

Inertial Aided SIFT for Time to Collision Estimation

Scheduled for presentation during the Video Sessions "Video Session" (FrA2), Friday, May 15, 2009, 10:00−10:06, Room: ICR

2009 IEEE International Conference on Robotics and Automation, May 12 - 17, 2009, Kobe, Japan

This information is tentative and subject to change. Compiled on January 21, 2022

Keywords Range Sensing, Visual Navigation, Visual Tracking


Visual time to collision estimation for small or micro air vehicles is challenging due to aggressive 6-DOF motion, real time performance requirements and significant size, weight and power constraints of the platform. Collision detection using insect inspired optical flow based methods have been demonstrated in low power hardware implementations, but have not achieved the obstacle detection and false alarm rate performance necessary for practical deployment. This performance is sensitive to correspondence errors in the optical flow field, so one approach to improving performance is to use a richer feature set for correspondence, along with calibrated inertial information from the platform to aid correspondence. In this video, we show proof of concept results for such an approach using inertial aided SIFT feature correspondence for time to collision estimation on a small aerial vehicle. Estimation results are noisy, but encouraging, and given that SIFT feature correspondence has been demonstrated in real time on low power GPUs, it has the potential for small UAV integration.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2022 PaperCept, Inc.
Page generated 2022-01-21  09:53:02 PST  Terms of use