9 January 1997 Recovery of superquadric primitives from a range image using GA
Author Affiliations +
Proceedings Volume 2910, Rapid Product Development Technologies; (1997) https://doi.org/10.1117/12.263356
Event: Photonics East '96, 1996, Boston, MA, United States
This paper describes a method for recovering volumetric shape descriptions of 3D objects from range image. The models of shape primitives are superquadrics. The model parameters defined the shape are obtained by using genetic algorithm. The fitting energy evaluated the difference in both depth form the object center and the distribute of the normal vector between input range image and the model surfaces. When the next generation is made the model parameters are independent each other, so the crossover is applied each parameter independently. In order to overcome the local minima problem, we employ a mutation strategy and a elitist preserving strategy. After the model parameters are obtained, the remained parameters are set. We applied the proposed method to recover nondeformed superellipsoids from synthetic range image.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hideki Tanahashi, Hideki Tanahashi, Noriyasu Murakami, Noriyasu Murakami, Kazuhiko Yamamoto, Kazuhiko Yamamoto, } "Recovery of superquadric primitives from a range image using GA", Proc. SPIE 2910, Rapid Product Development Technologies, (9 January 1997); doi: 10.1117/12.263356; https://doi.org/10.1117/12.263356


Adaptive adjacency graphs
Proceedings of SPIE (June 22 1993)
Matching sets of 3D segments
Proceedings of SPIE (September 22 1999)
Model group indexing for recognition
Proceedings of SPIE (January 31 1991)
Shape from contour methods using object-based heuristics
Proceedings of SPIE (April 08 1993)
3D primitive reconstruction using the line segment
Proceedings of SPIE (March 24 2003)
GRUPO: a 3-D structure recognition system
Proceedings of SPIE (August 31 1990)

Back to Top