A Solution to the Next Best View Problem for Automated Surface Acquisition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Point Correspondence Applied to Two-and Three-Dimensional Image Registration
IEEE Transactions on Pattern Analysis and Machine Intelligence
View planning for automated three-dimensional object reconstruction and inspection
ACM Computing Surveys (CSUR)
Robust surface matching for registration
3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
Self-calibration of a light striping system by matching multiple 3-D profile maps
3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
Hi-index | 0.00 |
Although the iterative closest point algorithm is very effective in registering range data, the quality of registration depends on the geometry of the sampled surfaces. This work presents a registration aid which can greatly reduce the possibility of catastrophic registration failure, increase the quality of registration and register range data which does not overlap. By placing the aid into the scene along with the object(s) of interest, range images taken from any vantage point within the range scanner's workspace can be registered onto a model of the aid and thus into a common reference frame. By considering the causes of registration failure, the surface of the aid is designed so that any range image taken of it from any point in the scanner's workspace will properly register with a model of the aid. The reliability of the aid is demonstrated with a Monte Carlo experiment and its utility is demonstrated with examples from an automated surface acquisition system.