3-D motion estimation, understanding, and prediction from nosiy image sequences
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
We discuss the problem of recovering the 3-D motion and structure. An algorithm for computing the camera motion and the orientation of planar surface is developed. It solves for the 3-D motion and structure iteratively given two successive image frames. We improve the solution by solving the ordinary differential equations which describe the evolution of motion and structure over time. The solution is further improved by exploiting the temporal coherence of 3-D motion. We develop the ordinary differential equations which describe the evolution of the parameters in terms of the current parameters and the measurements. The extended Kalman filter is then used to update the solution of the differential equations. The robustness of the entire process is demonstrated by the experiment with a moving camera which “flies” over a terrain model.