Date of this Version
We use Sarnoff's next-generation video processor, the PVT-200, to demonstrate real-time algorithms for stereo processing, obstacle detection, and terrain estimation from stereo cameras mounted on a moving vehicle. Sarnoff's stereo processing and obstacle detection capabilities are currently being used in several Unmanned Ground Vehicle (UGV) programs, including MDARS-E and DEMO III. Sarnoff's terrain estimation capabilities are founded on a "model-based directed stereo" approach. We demonstrate ongoing collaborative research between Sarnoff and Universitat der Bundeswehr Miinchen, where we are studying vision processing for autonomous off-road navigation as part of the AUTONAVprogram.
Mandelbaum, R., McDowell, L., Bogoni, L., Reich, B., & Hansen, M. L. (1998). Real-Time Stereo Processing, Obstacle Detection, and Terrain Estimation from Vehicle Mounted Stereo Cameras. Retrieved from https://repository.upenn.edu/hms/19
Date Posted: 12 July 2007
This document has been peer reviewed.