作者: T. Ruland , T. Pajdla , L. Kruger
DOI: 10.1109/CVPR.2012.6247781
关键词: Artificial intelligence 、 Robot end effector 、 Function (mathematics) 、 Control theory 、 Benchmark (computing) 、 Estimator 、 Calibration (statistics) 、 Robot kinematics 、 Upper and lower bounds 、 Parameter space 、 Computer science 、 Mathematical optimization
摘要: This paper introduces simultaneous globally optimal hand-eye self-calibration in both its rotational and translational components. The main contributions are new feasibility tests to integrate the calibration problem into a branch-and-bound parameter space search. presented method constitutes first guaranteed estimator for optimization of components with respect cost function based on reprojection errors. system is evaluated synthetic real world scenarios. employed benchmark dataset published online1 create common point reference evaluation algorithms.