Multi-frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects
Abstract:
We introduce new small-motion multi-frame equations applicable to the reconstruction of dynamic scenes in which points are allowed to move along straight-line paths with constant velocity. The motion equations apply to both static and dynamic points, thus prior segmentation is not necessary. We present a reconstruction algorithm of camera motion, scene structure, and point trajectories embedded into a multi-frame factorization principle which requires the minimum of 11 images and 7 points (out of which at least 3 are dynamic). 1
Citations
| 199 | The interpretation of moving retinal image – Longuet-Higgins, Prazdny - 1980 |
| 140 | Shape and Motion from Image Streams: A Factorization Method Part 3 - Detection and Tracking of Point Features – Tomasi, Kanade - 1991 |
| 80 | A multibody factorization method for independently moving-objects – Costeira, Kanade - 1998 |
| 58 | Multi-frame optical flow estimation using subspace constraints – Irani - 1999 |
| 46 | KLT: An implementation of the Kanade-Lucas-Tomasi feature tracker – Birchfield - 1998 |
| 31 | Reconstruction of a scene with multiple linearly moving objects – Han, Kanade - 2000 |
| 25 | Trajectory triangulation: 3D reconstruction of moving points from a monocular image sequence – Avidan, Shashua - 2000 |
| 20 | Homography tensors: On algebraic entities that represent three views of static or moving planar points – Shashua, Wolf - 2000 |
| 11 | Multi-frame alignment of planes – Zelnik-Manor, Irani - 1999 |

