Robust Pose Estimation Using the SwissRanger SR-3000 Camera
In this paper a robust method is presented to classify and estimate an objects pose from a real time range image and a low dimensional model. The model is made from a range image training set which is reduced dimensionally by a nonlinear manifold learning method named Local Linear Embedding (LLE). New range images are then projected to this model giving the low dimensional coordinates of the object pose in an efficient manner. The range images are acquired by a state of the art SwissRanger SR-3000 camera making the projection process work in real-time.
KeywordsRange Image Training Point Locally Linear Embedding Nonlinear Manifold Intrinsic Dimensionality
- 5.Bengio, Y., Paiement, J., Vincent, P.: Out-of-sample extensions for lle, isomap, mds, eigenmaps, and spectral clustering. Technical Report 1238, Université de Montréal (2004)Google Scholar
- 6.Ham, J., Lin, Y., Lee, D.: Learning nonlinear appearance manifolds for robot localization. In: IEEE Pacific Rim Conference on Communications, Computers and signal Processing, pp. 2971–2976 (2005)Google Scholar
- 7.de Ridder, D., Duin, R.: Locally linear embedding for classification. TUDelft, Pattern Recognition Group Technical Report Series, PH-2002-01 (2002)Google Scholar
- 8.Horn, B.K.P.: Robot Vision (MIT Electrical Engineering and Computer Science). The MIT Press, Cambridge (1986)Google Scholar
- 9.Balslev, I., Larsen, R.: Scape vision, a vision system for flexible binpicking in industry. IMM Industrial Visiondays, DTU (2006)Google Scholar