The Community for Technology Leaders
Green Image
Issue No. 09 - Sept. (2012 vol. 18)
ISSN: 1077-2626
pp: 1449-1459
V. Lepetit , KAIST GSCT UVR Lab., Daejeon, South Korea
Youngmin Park , Qualcomm Austria Res. Center, Wien, Austria
Woontack Woo , CVLab., ISIM, Lausanne, Switzerland
The contribution of this paper is two-fold. First, we show how to extend the ESM algorithm to handle motion blur in 3D object tracking. ESM is a powerful algorithm for template matching-based tracking, but it can fail under motion blur. We introduce an image formation model that explicitly consider the possibility of blur, and shows its results in a generalization of the original ESM algorithm. This allows to converge faster, more accurately and more robustly even under large amount of blur. Our second contribution is an efficient method for rendering the virtual objects under the estimated motion blur. It renders two images of the object under 3D perspective, and warps them to create many intermediate images. By fusing these images we obtain a final image for the virtual objects blurred consistently with the captured image. Because warping is much faster than 3D rendering, we can create realistically blurred images at a very low computational cost.
solid modelling, augmented reality, image matching, image motion analysis, image restoration, object tracking, rendering (computer graphics), 3D rendering, motion-blur, augmented reality, ESM algorithm, 3D object tracking, template matching-based tracking, image formation model, virtual objects, intermediate images, image fusion, Tracking, Rendering (computer graphics), Three dimensional displays, Cameras, Jacobian matrices, Robustness, Computational modeling, efficient second-order minimization., Augmented reality, computer vision, object tracking, object detection, motion-blur

V. Lepetit, Youngmin Park and Woontack Woo, "Handling Motion-Blur in 3D Tracking and Rendering for Augmented Reality," in IEEE Transactions on Visualization & Computer Graphics, vol. 18, no. , pp. 1449-1459, 2012.
87 ms
(Ver 3.3 (11022016))