Active, optical range imaging sensors
Machine Vision and Applications
Detecting Binocular Half-Occlusions: Empirical Comparisons of Five Approaches
IEEE Transactions on Pattern Analysis and Machine Intelligence
Advances in Computational Stereo
IEEE Transactions on Pattern Analysis and Machine Intelligence
Symmetric Stereo Matching for Occlusion Handling
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Boundary Identification and Triangulation of STL Model
BMEI '08 Proceedings of the 2008 International Conference on BioMedical Engineering and Informatics - Volume 01
| Hi-index | 0.00 |
Recent progress in stereo matching algorithms performance especially belief propagation algorithm encourages us greatly. However, it is difficult to develop a stable, real time and low cost shape measurement system. In this paper, we propose a novel laser-scanning based 3D measurement system to obtain depth information in real time. Efficient Belief Propagation algorithm is adopted to match the correspondent points of laser stripe between calibration image and measurement image. When laser beam is projected onto scene, occlusion problem will occur and influence 3D reconstruction accuracy. Outliers are detected by the ratio of the second highest peak over the highest peak. Experimental results demonstrate the feasibility of proposed approach.