MOPED: A scalable and low latency object recognition and pose estimation system

Manuel Martinez, Alvaro Collet, Siddhartha S Srinivasa
2010 2010 IEEE International Conference on Robotics and Automation  
The latency of a perception system is crucial for a robot performing interactive tasks in dynamic human environments. We present MOPED, a fast and scalable perception system for object recognition and pose estimation. MOPED builds on POSESEQ, a state of the art object recognition algorithm, demonstrating a massive improvement in scalability and latency without sacrificing robustness. We achieve this with both algorithmic and architecture improvements, with a novel feature matching algorithm, a
more » ... ybrid GPU/CPU architecture that exploits parallelism at all levels, and an optimized resource scheduler. Using the same standard hardware, we achieve up to 30x improvement on real-world scenes. M. Martinez and A. Collet are with The
doi:10.1109/robot.2010.5509801 dblp:conf/icra/MartinezCS10 fatcat:qf6vu2iymfbmlgggrkqsc5a6ey