The 2011 Solutions in Perception Challenge (SPC) presented an international collection of teams with the opportunity to develop algorithms that could positively identify and accurately locate in space an arbitrary collection of artifacts. Researchers at the National Institute of Standards and Technology (NIST) generated a series of artifacts synonymous with industrial parts, a modular fixturing system capable of accurately and precisely positioning the artifacts within a 6 degree of freedom (6DOF) work volume, and a relative pose scoring metric to quantify an algorithm's performance. Competing teams were presented with training and validation training sets consisting of red-green-blue (RGB) color images and 3D point cloud data of the artifacts. The top performers achieved over 70% accuracy in translation and pose estimation. In this paper we discuss the design of NIST's contributions, and present the teams' results from the 2011 SPC.
Proceedings Title: 2012 Performance Metrics for Intelligent Systems Workshop
Conference Dates: March 20-22, 2012
Conference Location: College Park, MD
Pub Type: Conferences
Ground Truth, 6DOF Metrology, Laser Tracker, Fixtures