A comparative study of the robustness of two pose estimation techniques
Machine Vision and Applications - Special issue on performance evaluation
Model-Based Stereo-Tracking of Non-Polyhedral Objects for Automatic Disassembly Experiments
International Journal of Computer Vision - Special issue on image-based servoing
The Distribution of Target Registration Error in Rigid-Body, Point-Based Registration
IPMI '99 Proceedings of the 16th International Conference on Information Processing in Medical Imaging
Learning the Probability of Correspondences without Ground Truth
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Performance characterization in computer vision: A guide to best practices
Computer Vision and Image Understanding
Comparison of local image descriptors for full 6 degree-of-freedom pose estimation
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Dynamic 6DOF metrology for evaluating a visual servoing system
PerMIS '08 Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems
Mathematical metrology for evaluating a 6DOF visual servoing system
PerMIS '09 Proceedings of the 9th Workshop on Performance Metrics for Intelligent Systems
A framework for performance evaluation of model-based optical trackers
EGVE'08 Proceedings of the 14th Eurographics conference on Virtual Environments
EGVE'04 Proceedings of the Tenth Eurographics conference on Virtual Environments
Ground truth for evaluating 6 degrees of freedom pose estimation systems
Proceedings of the Workshop on Performance Metrics for Intelligent Systems
Hi-index | 0.00 |
In this paper, we apply two fundamental approaches toward evaluating a static, vision based, six-degree-of-freedom (6DoF) pose determination system that measures the position and orientation of a part. The first approach uses groundtruth carefully obtained from a laser tracker and the second approach doesn't use any external groundtruth. The evaluation procedure focuses on characterizing both the system's accuracy and precision as well as the effect of object viewpoints. For the groundtruth method, we first use a laser tracker for system calibration and then compare the calibrated output with the surveyed pose. In the method without external groundtruth, we evaluate the effect of viewpoint factors on the system's performance.