Structure from motion estimation using a nonlinear Kalman filter

[摘要] ENGLISH ABSTRACT:Structure from Motion is defined as the problem of extracting the 3d motion of a cameramoving through a scene, as well as the 3d structure of the scene, from the image sequenceproduced by the camera over time. Several methods based on the Kalman filter havebeen proposed in the past, mostly based on the Extended Kalman filter. We proposean algorithm based on the dual Unscented Kalman filter to estimate the structure andmotion of an object under perspective projection. It is shown that the algorithm is stableand accurate under synthetic as well as real-world conditions.

[发布机构] Stellenbosch University