Authors : Yaming Wang , Li Sun , Jueliang Hu , Yunhua Zhang and Wenqing Huang
Abstract: 3D rigid motion estimation from images is crucial for many important applications. In this study, an approach is proposed for 3D rigid motion estimation from feature points using feed-forward neural-networks. The correspondence of feature points between consecutive images is assumed to be established beforehand. The proposed neural network is composed of 3 layers and 3 points are randomly selected from all points on the object to train the network using Newton-Raphson procedure. Experimental results from synthetic data are presented for validating the proposed approach.
Yaming Wang , Li Sun , Jueliang Hu , Yunhua Zhang and Wenqing Huang , 2008. Neural Networks Approach to 3D Rigid Motion Estimation from Feature Points. International Journal of Soft Computing, 3: 201-204.