Time-to-impact sensors in robot vision applications based on the near-sensor image processing concept

Anders Åström; Robert Forchheimer

doi:10.1117/12.905823

15 February 2012 Time-to-impact sensors in robot vision applications based on the near-sensor image processing concept

Anders Åström, Robert Forchheimer

Author Affiliations +

Proceedings Volume 8298, Sensors, Cameras, and Systems for Industrial and Scientific Applications XIII; 829808 (2012) https://doi.org/10.1117/12.905823
Event: IS&T/SPIE Electronic Imaging, 2012, Burlingame, California, United States

Abstract

Based on the Near-Sensor Image Processing (NSIP) concept and recent results concerning optical flow and Time-to- Impact (TTI) computation with this architecture, we show how these results can be used and extended for robot vision applications. The first case involves estimation of the tilt of an approaching planar surface. The second case concerns the use of two NSIP cameras to estimate absolute distance and speed similar to a stereo-matching system but without the need to do image correlations. Going back to a one-camera system, the third case deals with the problem to estimate the shape of the approaching surface. It is shown that the previously developed TTI method not only gives a very compact solution with respect to hardware complexity, but also surprisingly high performance.

Citation Download Citation

Anders Åström and Robert Forchheimer "Time-to-impact sensors in robot vision applications based on the near-sensor image processing concept", Proc. SPIE 8298, Sensors, Cameras, and Systems for Industrial and Scientific Applications XIII, 829808 (15 February 2012); https://doi.org/10.1117/12.905823

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE