Resolution-Aware Fitting of Active Appearance Models to Low Resolution Images
Active Appearance Models (AAM) are compact representations of the shape and appearance of objects. Fitting AAMs to images is a difficult, non-linear optimization task. Traditional approaches minimize the L2 norm error between the model instance and the input image warped onto the model coordinate frame. While this works well for high resolution data, the fitting accuracy degrades quickly at lower resolutions. In this paper, we show that a careful design of the fitting criterion can overcome many of the low resolution challenges. In our resolution-aware formulation (RAF), we explicitly account for the finite size sensing elements of digital cameras, and simultaneously model the processes of object appearance variation, geometric deformation, and image formation. As such, our Gauss-Newton gradient descent algorithm not only synthesizes model instances as a function of estimated parameters, but also simulates the formation of low resolution images in a digital camera. We compare the RAF algorithm against a state-of-the-art tracker across a variety of resolution and model complexity levels. Experimental results show that RAF considerably improves the estimation accuracy of both shape and appearance parameters when fitting to low resolution data.
KeywordsRoot Mean Square Active Appearance Model Tracking Experiment Face Tracking Geometric Deformation
Unable to display preview. Download preview PDF.
- 2.Lucas, B.D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: Proc. of the 7th Int. Joint Conference on Artificial Intelligence, April 1981, pp. 674–679 (1981)Google Scholar
- 5.Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998)Google Scholar
- 6.Edwards, G.J., Taylor, C.J., Cootes, T.F.: Interpreting Face Images Using Active Appearance Models. In: Proc. of Int. Conf. on Automatic Face and Gesture Recognition, June 1998, pp. 300–305 (1998)Google Scholar
- 8.Baker, S., Gross, R., Matthews, I.: Lucas-Kanade 20 Years On: A Unifying Framework: Part 3. Robotics Institute Technical Report CMU-RI-TR-03-35, Carnegie Mellon University (November 2003)Google Scholar
- 12.Dedeoglu, G., Kanade, T., Baker, S.: The Asymmetry of Image Registration and its Application to Face Tracking. Robotics Institute Technical Report CMU-RI-TR-06-06, Carnegie Mellon University (February 2006)Google Scholar