CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2003 vol.25 Issue No.07 - July
Issue No.07 - July (2003 vol.25)
Takeo Kanade , IEEE
<p><b>Abstract</b>—In this paper, we describe a reconstruction method for multiple motion scenes, which are scenes containing multiple moving objects, from uncalibrated views. Assuming that the objects are moving with constant velocities, the method recovers the scene structure, the trajectories of the moving objects, the camera motion, and the camera intrinsic parameters (except skews) simultaneously. We focus on the case where the cameras have unknown and varying focal lengths while the other intrinsic parameters are known. The number of the moving objects is automatically detected without prior motion segmentation. The method is based on a unified geometrical representation of the static scene and the moving objects. It first performs a projective reconstruction using a bilinear factorization algorithm and, then, converts the projective solution to a Euclidean one by enforcing metric constraints. Experimental results on synthetic and real images are presented.</p>
Structure from motion, motion segmentation, camera calibration, dynamic scene reconstruction, computer vision.
Mei Han, Takeo Kanade, "Multiple Motion Scene Reconstruction with Uncalibrated Cameras", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.25, no. 7, pp. 884-894, July 2003, doi:10.1109/TPAMI.2003.1206517