Results are reported from a research project on three-dimensional motion analysis. The work is based on stereo image sequences of a military vehicle. The analysis depends on the segmentation of the image and the matching of features between the two images. Preliminary results are given for an extension of the work to object recognition. Extracted features and the calculated parameters of motion are incorporated into a symbolic matching system. Object recognition is performed by the symbolic inexact matching of a representation of the photographs with a database of prototypes. The use of control points to furnish ground truth is discussed.
Determining Vehicle Motion from Stereo Image Sequences
1987
6 pages
Report
No indication
English
Photographic Techniques & Equipment , Cartography , Motion , Image processing , Data bases , Photographic images , Matching , Mathematical analysis , Military vehicles , Photographs , Prototypes , Recognition , Segmented , Sequences , Stereoscopic display systems , Surface truth , Symbols , Three dimensional , Pattern recognition , Extraction , Stereophotography , Moving targets , Robots , Motion analysis , Feature extraction
A Kalman Filter in Motion Analysis from Stereo Image Sequences
British Library Conference Proceedings | 1994
|Vehicle tracking and motion estimation based on stereo vision sequences
Tema Archive | 2013
|Vehicle tracking and motion estimation based on stereo vision sequences
Tema Archive | 2010
|