Translator Disclaimer
8 October 2015 Parsing optical scanned 3D data by Bayesian inference
Author Affiliations +
Proceedings Volume 9675, AOPC 2015: Image Processing and Analysis; 967532 (2015) https://doi.org/10.1117/12.2202969
Event: Applied Optics and Photonics China (AOPC2015), 2015, Beijing, China
Abstract
Optical devices are always used to digitize complex objects to get their shapes in form of point clouds. The results have no semantic meaning about the objects, and tedious process is indispensable to segment the scanned data to get meanings. The reason for a person to perceive an object correctly is the usage of knowledge, so Bayesian inference is used to the goal. A probabilistic And-Or-Graph is used as a unified framework of representation, learning, and recognition for a large number of object categories, and a probabilistic model defined on this And-Or-Graph is learned from a relatively small training set per category. Given a set of 3D scanned data, the Bayesian inference constructs a most probable interpretation of the object, and a semantic segment is obtained from the part decomposition. Some examples are given to explain the method.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hanwei Xiong, Jun Xu, Chenxi Xu, and Ming Pan "Parsing optical scanned 3D data by Bayesian inference", Proc. SPIE 9675, AOPC 2015: Image Processing and Analysis, 967532 (8 October 2015); https://doi.org/10.1117/12.2202969
PROCEEDINGS
5 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

3D surface digitizing and modeling development at ITRI
Proceedings of SPIE (June 27 2000)
Building a 3D wireframe CAD model for an existing prismatic...
Proceedings of SPIE (September 12 1995)
Recovering primitives in 3D CAD meshes
Proceedings of SPIE (January 27 2011)
Wrapping 3D scanning data
Proceedings of SPIE (March 05 1998)

Back to Top