SepPoseEstimation

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

2D / 3D Pose Estimation

Advisor: Prof. Navab Supervision by: Martin Groher

Abstract

By pose we mean the transformation needed to map an object model from its inherent coordinate system into agreement with the sensory data.[8] In other words, given a world object in the object coordinate system (OCS) and a camera taking an image in the camera coordinate system (CCS) we want to determine a rotation and a translation from OCS to CCS by only using information from model and camera image.
Determining the pose from 2D image and 3D model information is used in many fields of Computer Science, like robotics, Augmented Reality, etc. There are numerous ways to estimate the pose with, e.g. line or point correspondences, or even without any corresponding information given.
This SEP will implement different pose estimation algorithms and test them in a suitable way also against already established code.
Following algorithms shall be implemented:

  • 3-point algorithm of Haralick
  • 4-point algorithm of Horaud
  • Robust Estimation
  • Testing against POSIT, SoftPOSIT (already implemented)

A general interest in Computer Vision is advisable, programming language will be C++.

Resources

CVonline: Foundations about 2D-3D Pose Estimation

Literature

[1] R. Haralick, H. Joo, C. Lee, X. Zhuang, V Vaidya, and M. Kim. Pose estimation from corresponding point data. IEEE Trans on Systems, Man and Cybernetics, 19(6):1426--1445, Nov. 1989
[2] R. Haralick, C. Lee, K. Ottenberg, and M. No¨ lle, “Analysis and Solutions of the Three Point Perspective Pose Estimation Problem,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 592-598, June 1991.
[3] R. Horaud, B. Conio, O. Leboulleux, and B. Lacolle, “An Analytic Solution for the Perspective 4-Point Problem,” Computer Vision, Graphics, and Image Processing, vol. 47, pp. 33-44, 1989.
[4] M. Fischler and R. Bolles,“RandomSample Consensus:AParadigm for Model Fitting with Applications to Image Analysis and Automated Cartography,” Comm. ACM, vol. 24, pp. 381-395, 1981.
[5] D. DeMenthon and L.S. Davis, “Model-Based Object Pose in 25 Lines of Code,” Int’l J. Computer Vision, vol. 15, pp. 123-144, 1995.
[6] Philip David, Daniel DeMenthon, Ramani Duraiswami and Hanan Samet, "SoftPOSIT: Simultaneous Pose and Correspondence Determination", International Journal of Computer Vision, 59, No. 3, September-October 2004, pp. 259-284.
[7] Y. Liu, T.S. Huang, and O.D. Faugeras, “Determination of Camera Location from 2-D to 3-D Line and Point Correspondences,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 28-37, 1990.
[8] N. Navab and O.D. Faugeras, “Monocular Pose Determination From Lines: Critical Sets and Maximum Number of Solutions,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 254-260, June 1993.
[8] Grimson W.E.L Object Recognition by Computer. The MIT Press, Cambridge, MA, 1990

Students.ProjectForm
Title: 2D / 3D Pose Estimation
Abstract: "By pose we mean the transformation needed to map an object model from its inherent coordinate system into agreement with the sensory data."[1] In other words: given a world object in the object coordinate system (OCS) and a camera taking an image in the camera coordinate system (CCS) we want to determine a rotation and a translation from OCS to CCS by only using information from model and camera image.
Determining the pose from 2D image and 3D model information is used in many fields of Computer Science, like robotics, Augmented Reality, etc. There are numerous ways to estimate the pose with, e.g. line or point correspondences, or even without any corresponding information given.
Student: Christian Waechter
Director: Nassir Navab
Supervisor: Martin Groher
Type: SEP
Status: finished
Start:  
Finish:  


Edit | Attach | Refresh | Diffs | More | Revision r1.8 - 07 Mar 2007 - 19:03 - MartinGroher