Share Email Print

Proceedings Paper

Trinocular vision for automatic and robust 3D determination of the trajectories of moving objects
Author(s): Emmanuel P. Baltsavias; Dirk Stallmann
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An automatic procedure for tracking signalised points on multiple, differently moving surfaces will be described. The practical tests involve tracking of points on a person walking within a calibration frame. Three simultaneously acquiring CCD cameras, which are oriented using control points, provide the input data. For implementation, the hardware (H/W) and software (S/W) of a digital photogrammetric system have been used. The procedure includes extraction of the signalised points and finding corresponding points in all three images, thus providing 2-D and 3-D coordinates and tracking using the information in both image and object space. Reliability aspects such as occlusions, multiple solutions and different backgrounds will be analysed. The effect of a third image on reliability will be analysed.

Paper Details

Date Published: 1 August 1990
PDF: 10 pages
Proc. SPIE 1395, Close-Range Photogrammetry Meets Machine Vision, 139528 (1 August 1990); doi: 10.1117/12.2294323
Show Author Affiliations
Emmanuel P. Baltsavias, ETH Zurich (Switzerland)
Dirk Stallmann, ETH Zurich (Switzerland)

Published in SPIE Proceedings Vol. 1395:
Close-Range Photogrammetry Meets Machine Vision
Armin Gruen; Emmanuel P. Baltsavias, Editor(s)

© SPIE. Terms of Use
Back to Top