17 May 2013 An architecture for online semantic labeling on UGVs
Author Affiliations +
Abstract
We describe an architecture to provide online semantic labeling capabilities to field robots operating in urban environments. At the core of our system is the stacked hierarchical classifier developed by Munoz et al., which classifies regions in monocular color images using models derived from hand labeled training data. The classifier is trained to identify buildings, several kinds of hard surfaces, grass, trees, and sky. When taking this algorithm into the real world, practical concerns with difficult and varying lighting conditions require careful control of the imaging process. First, camera exposure is controlled by software, examining all of the image's pixels, to compensate for the poorly performing, simplistic algorithm used on the camera. Second, by merging multiple images taken with different exposure times, we are able to synthesize images with higher dynamic range than the ones produced by the sensor itself. The sensor 's limited dynamic range makes it difficult to, at the same time, properly expose areas in shadow along with high albedo surfaces that are directly illuminated by the sun. Texture is a key feature used by the classifier, and under /over exposed regions lacking texture are a leading cause of misclassifications. The results of the classifier are shared with higher-lev elements operating in the UGV in order to perform tasks such as building identification from a distance and finding traversable surfaces.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Arne Suppé, Arne Suppé, Luis Navarro-Serment, Luis Navarro-Serment, Daniel Munoz, Daniel Munoz, Drew Bagnell, Drew Bagnell, Martial Hebert, Martial Hebert, } "An architecture for online semantic labeling on UGVs", Proc. SPIE 8741, Unmanned Systems Technology XV, 87410R (17 May 2013); doi: 10.1117/12.2015806; https://doi.org/10.1117/12.2015806
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Minefield image synthesis tool
Proceedings of SPIE (June 20 1995)
A simple approach to a vision-guided unmanned vehicle
Proceedings of SPIE (October 24 2005)
HDR imaging and color constancy two sides of the...
Proceedings of SPIE (January 25 2011)
Robotic concepts for urban operations
Proceedings of SPIE (July 17 2002)
Autonomous vehicle maneuvering
Proceedings of SPIE (February 14 1992)
Visually guided touching and manual tracking
Proceedings of SPIE (March 11 1993)

Back to Top