Abstract: This study uses neural networks to estimate three-Dimensional (3D) rigid motion parameters based on two-Dimensional (2D) motion fields. The motion fields are computed from image sequences. The neural networks update their weights by Newton-Raphson procedure for minimizing the error measures. Experimental results are presented for validating the proposed approach.
Yunhua Zhang , Yaming Wang , Sun Li and Wenqing Huang , 2007. S3D Motion Estimation Based on 2D Motion Field Using Neural Networks . Asian Journal of Information Technology, 6: 839-841.