spacer
School of Computer Science The University of Adelaide Australia
Computer Science Home
About the School
Research
Staff Only
text zoom: S | M | L

School of Computer Science
Innova21 Building
THE UNIVERSITY OF ADELAIDE
SA 5005
AUSTRALIA
Email

Telephone: +61 8 8313 5586
Facsimile: +61 8 8313 4366


You are here: Computer Science > users > john

Plant Project:
5 minute plant presentation

Augmented Reality Projects:
Interactive Modelling for AR Applications
Bastian, J; Ward, B; Hill, R; van den Hengel, A; Dick A
9th IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2010, pp 199-205

Abstract: We present a method for estimating the 3D shape of an object from a sequence of images captured by a hand-held device. The method is well suited to augmented reality applications in that minimal user interaction is required, and the models generated are of an appropriate form. The method proceeds by segmenting the object in every image as it is captured and using the calculated silhouette to update the current shape estimate. In contrast to previous silhouette-based modelling approaches, however, the segmentation process is informed by a 3D prior based on the previous shape estimate. A voting scheme is also introduced in order to compensate for the inevitable noise in the camera position estimates. The combination of the voting scheme with the closed-loop segmentation process provides a robust and flexible shape estimation method. We demonstrate the approach on a number of scenes where segmentation without a 3D prior would be challenging.
Paper-PDF
@INBOOK{Bastian2010, pages = {199--205}, title = {Interactive modelling for AR applications}, publisher = {IEEE}, year = {2010},author = {Bastian, J and Ward, B and Hill, R and Van Den Hengel, A and Dick,A},booktitle = {9th IEEE International Symposium on Mixed and Augmented Reality ISMAR 2010},abstract = {We present a method for estimating the 3D shape of an object from a sequence of images captured by a hand-held device. The method is well suited to augmented reality applications in that minimal user interaction is required, and the models generated are of an appropriateform. The method proceeds by segmenting the object in every image as it is captured and using the calculated silhouette to update the current shape estimate. In contrast to previous silhouette-based modelling approaches, however, the segmentation process is informed by a 3D prior based on the previous shape estimate. A voting scheme is also introduced in order to compensate for the inevitable noise in the camera position estimates. The combination of the voting scheme with the closed-loop segmentation process provides a robust and flexible shape estimation method. We demonstrate the approach on a number of scenes where segmentation without a 3D prior would be challenging.}, url = {http://www.acvt.com.au/?p=91} }