C-velocity: A cumulative frame to segment objects from egomotion
| Autor: | S. Bouchafa, B. Zavidovique |
|---|---|
| Rok vydání: | 2009 |
| Předmět: |
Sequence
business.industry Frame (networking) Motion (geometry) Scale (descriptive set theory) Space (mathematics) Computer Graphics and Computer-Aided Design Planar Pattern recognition (psychology) Computer vision Computer Vision and Pattern Recognition Noise (video) Artificial intelligence business Mathematics |
| Zdroj: | Pattern Recognition and Image Analysis. 19:583-590 |
| ISSN: | 1555-6212 1054-6618 |
| DOI: | 10.1134/s1054661809040038 |
| Popis: | This paper deals with extracting 3D-planar structures of a moving scene from a 2D-image sequence. The camera is assumed on board a vehicle moving straight so that the dominant apparent motion generates a scale change along images. We introduce the concept of c-velocity space. That is a cumulative frame in which planar surfaces are transformed into straight lines. Equations ruling the phenomenon are given and explained. Then results on synthetic images are shown to meet the theory. Eventually results on real data are commented on as for the uncertainty introduced by the location of the FOE and other types of noise. The article is published in the original. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink