Abstract
The paper discusses the evolution of the single object motion shape estimation (MSE) problem. Given a sequence of 2-D video images of multiple moving objects, the problem is to track the 3-D motion of the objects and reconstruct their 3-D shapes. After selection of initial feature points (FPs), the SVD may be applied to a measurement matrix formed by the FPs sequentially tracked by a video system. The distribution of singular values first reveal the information about the number of objects at hand. Then, using an algebraic-based subspace clustering method, the FPs are mapped onto their corresponding objects. Thereafter, the motion and shape are be estimated from a matrix factorization.
Original language | English (US) |
---|---|
Pages | 413-422 |
Number of pages | 10 |
State | Published - Dec 1 1994 |
Event | Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94) - Ermioni, GREECE Duration: Sep 6 1994 → Sep 8 1994 |
Other
Other | Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94) |
---|---|
City | Ermioni, GREECE |
Period | 9/6/94 → 9/8/94 |
All Science Journal Classification (ASJC) codes
- Signal Processing
- Software
- Electrical and Electronic Engineering