In EDS ansehen

Evaluation of linear combination of views for object recognition: Chapter 5

Gespeichert in:
Bibliographische Detailangaben
Titel: Evaluation of linear combination of views for object recognition: Chapter 5
Autoren: Zografos, Vasileios, 1978, Buxton, Bernard
Quelle: ADVANCES IN INTELLIGENT INFORMATION PROCESSING: Tools and Applications. :85-106
Schlagwörter: intelligent information processing, video compression, remote sensing, Image Processing, Pattern Recognition, International Conference, MATHEMATICS, MATEMATIK
Beschreibung: In this work, we present a method for model-based recognition of 3d objects from a small number of 2d intensity images taken from nearby, but otherwise arbitrary viewpoints. Our method works by linearly combining images from two (or more) viewpoints of a 3d object to synthesise novel views of the object. The object is recognised in a target image by matching to such a synthesised, novel view. All that is required is the recovery of the linear combination parameters, and since we are working directly with pixel intensities, we suggest searching the parameter space using a global, evolutionary optimisation algorithm combined with a local search method in order efficiently to recover the optimal parameters and thus recognise the object in the scene. We have experimented with both synthetic data and real-image, public databases.
Dateibeschreibung: print
Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-52182
Datenbank: SwePub
Beschreibung
Abstract:In this work, we present a method for model-based recognition of 3d objects from a small number of 2d intensity images taken from nearby, but otherwise arbitrary viewpoints. Our method works by linearly combining images from two (or more) viewpoints of a 3d object to synthesise novel views of the object. The object is recognised in a target image by matching to such a synthesised, novel view. All that is required is the recovery of the linear combination parameters, and since we are working directly with pixel intensities, we suggest searching the parameter space using a global, evolutionary optimisation algorithm combined with a local search method in order efficiently to recover the optimal parameters and thus recognise the object in the scene. We have experimented with both synthetic data and real-image, public databases.