Title :
3D model based pose determination in real-time: strategies, convergence, accuracy
Author :
Berger, Martin ; Auer, Thomas ; Bachler, Gemot ; Scherer, Stefan ; Pinz, Axel
Author_Institution :
Graz Univ. of Technol., Austria
Abstract :
In this paper, a new real-time model based pose determination system based on the Gauss-Newton method is described. Various model fitting strategies, which use gradient search, are discussed and compared. A novel strategy, the adaptive perpendicular search, is proposed for both matching ambiguity avoidance and convergence enforcement. The system is shown to be highly effective in practice, while keeping the computational cost low. A sufficient initial pose estimate as an input for the Gauss-Newton based methods is obtained from the parametric eigenspace. With certain restrictions, the overall pose determination system performs in real-time, as required in industrial applications
Keywords :
convergence of numerical methods; curve fitting; image matching; optimisation; real-time systems; search problems; stereo image processing; Gauss-Newton method; adaptive perpendicular search; ambiguity avoidance; convergence; model fitting; parametric eigenspace; pattern matching; pose determination; real-time model; Computational efficiency; Computer industry; Convergence; Electric variables measurement; Least squares methods; Newton method; Optimization methods; Real time systems; Recursive estimation; Robustness;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.902983