Dynamical Systems and Motion Vision
In this paper we show how the theory of dynamical systems can be employed to solve problems in motion vision. In particular we develop algorithms for the recovery of dense depth maps and motion parameters using state space observers or filters. Four different dynamical models of the imaging si...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6044 |
| _version_ | 1811096291210428416 |
|---|---|
| author | Heel, Joachim |
| author_facet | Heel, Joachim |
| author_sort | Heel, Joachim |
| collection | MIT |
| description | In this paper we show how the theory of dynamical systems can be employed to solve problems in motion vision. In particular we develop algorithms for the recovery of dense depth maps and motion parameters using state space observers or filters. Four different dynamical models of the imaging situation are investigated and corresponding filters/ observers derived. The most powerful of these algorithms recovers depth and motion of general nature using a brightness change constraint assumption. No feature-matching preprocessor is required. |
| first_indexed | 2024-09-23T16:41:33Z |
| id | mit-1721.1/6044 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:41:33Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/60442019-04-12T08:28:48Z Dynamical Systems and Motion Vision Heel, Joachim dynamical systems motion vision Kalman filter depth map smotion recovery In this paper we show how the theory of dynamical systems can be employed to solve problems in motion vision. In particular we develop algorithms for the recovery of dense depth maps and motion parameters using state space observers or filters. Four different dynamical models of the imaging situation are investigated and corresponding filters/ observers derived. The most powerful of these algorithms recovers depth and motion of general nature using a brightness change constraint assumption. No feature-matching preprocessor is required. 2004-10-04T14:36:47Z 2004-10-04T14:36:47Z 1988-04-01 AIM-1037 http://hdl.handle.net/1721.1/6044 en_US AIM-1037 54 p. 6308570 bytes 2508040 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | dynamical systems motion vision Kalman filter depth map smotion recovery Heel, Joachim Dynamical Systems and Motion Vision |
| title | Dynamical Systems and Motion Vision |
| title_full | Dynamical Systems and Motion Vision |
| title_fullStr | Dynamical Systems and Motion Vision |
| title_full_unstemmed | Dynamical Systems and Motion Vision |
| title_short | Dynamical Systems and Motion Vision |
| title_sort | dynamical systems and motion vision |
| topic | dynamical systems motion vision Kalman filter depth map smotion recovery |
| url | http://hdl.handle.net/1721.1/6044 |
| work_keys_str_mv | AT heeljoachim dynamicalsystemsandmotionvision |