Exploiting Depth and Intensity Information for Head Pose Estimation with Random Forests and Tensor Models
Real-time accurate head pose estimation is required for several applications. Methods based on 2D images might not provide accurate and robust head pose measurements due to large head pose variations and illumination changes. Robust and accurate head pose estimation can be achieved by integrating intensity and depth information. In this paper we introduce a head pose estimation system that employs random forests and tensor regression algorithms. The former allow the modeling of large head pose variations using large sets of training data, while the latter allow the estimation of more accurate head pose parameters. The combination of the above mentioned methods results in more robust and accurate predictions for large head pose variations. We also study the fusion of different sources of information (intensity and depth images) to determine how their combination affects the performance of a head pose estimation system. The efficiency of the proposed framework is tested on the Biwi Kinect Head Pose dataset, where it is shown that the proposed methodology outperforms typical random forests.
KeywordsRandom Forest Leaf Node Depth Data Feature Channel Large Head
Unable to display preview. Download preview PDF.
- 1.Fanelli, G., Gall, J., Van Gool, L.: Real Time Head Pose Estimation with Random Regression Forests. In: Computer Vision and Pattern Recognition, CVPR, pp. 617–624 (2011)Google Scholar
- 5.Breitenstein, M.D., Kuettel, D., Weise, T., Van Gool, L., Pfister, H.: Real-time face pose estimation from single range images. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8 (2008)Google Scholar
- 7.Seemann, E., Nickel, K., Stiefelhagen, R.: Head pose estimation using stereo vision for human-robot interaction. In: Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 626–631 (2004)Google Scholar
- 8.Morency, L.P., Sundberg, P., Darrell, T.: Pose estimation using 3D view-based eigenspaces. In: IEEE International Workshop on Analysis and Modeling of Faces and Gestures, AMFG 2003, pp. 45–52 (2003)Google Scholar
- 9.Osadchy, M., Cun, Y.L., Miller, M.L.: Synergistic Face Detection and Pose Estimation with Energy-Based Models. J. Mach. Learn. Res. 8, 1197–1215 (2007)Google Scholar
- 10.Vatahska, T., Bennewitz, M., Behnke, S.: Feature-based head pose estimation from images. In: 2007 7th IEEE-RAS International Conference on Humanoid Robots, pp. 330–335. IEEE (2007)Google Scholar
- 11.Whitehill, J., Movellan, J.R.: A discriminative approach to frame-by-frame head pose tracking. In: 8th IEEE International Conference on Automatic Face Gesture Recognition, FG 2008, pp. 1–7 (2008)Google Scholar
- 14.Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 187–194. ACM Press/Addison-Wesley Publishing Co. (1999)Google Scholar
- 15.Storer, M., Urschler, M., Bischof, H.: 3d-mam: 3d morphable appearance model for efficient fine head pose estimation from still images. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, pp. 192–199. IEEE (2009)Google Scholar
- 16.Cristinacce, D., Cootes, T.: Feature detection and tracking with constrained local models, pp. 929–938 (2006)Google Scholar