Kontrol Gerakan Objek 3D Augmented Reality Berbasis Titik Fitur Wajah dengan POSIT

  • Heri Pratikno Institut Bisnis dan Informatika Stikom Surabaya
Keywords: Augmented Reality, Titik Fitur Wajah, POSIT, Objek 3D

Abstract

Augmented Reality (AR) is a technique in computerscience that combines real world conditions with the computercomputation results in the form of 2D or 3D graphics. In this study,a method and application implementation in Augmented Reality environment with markerless was discussed. In the markerless technique, interaction process between humans and computers becomes more natural and intuitive than the marker based techniques. Markerless techniques applied in this study used facial feature points so that the result is more robust for the head objectdoes not produce light. The main problem in this area of researchis how the process of controlling the 3D object movement does notexperience anomalies such as railroad phenomenon, where the theeyes catch as if the distance between the two railroads narrower atthe farther view. This study used POSIT (Pose from Orthography and Scale with ITeration), where the position and orientation of the 3D objects were projected in orthographic from facial featurepoints with scaling, so the change in the distance between the faceand the webcam were proportional to the big - small changes of 3D objects. The next step was iteration process carried out four to fivetimes to look for the smallest error factor to obtain the best pose.

References

M. Haller, M. Billinghurst, Bruce Thomas, Emerging Technologies of Augmented Reality: Interface and Design. IDEA GROUP PUBLISHING, 2007.

Daniel F. DeMenthon, Larry S. Davis, Model-Based Object Pose in 25 Lines of Code. International Journal of Computer Vision. Volume 15. Numbers 1-2. pages 123-141, 1995.

Yuan. J.S.C., A General Photogrammatric Method for Determining Object Position and Orientation. IEEE Trans. on Robotics and Automation. vol. 5. pp. 129-142. 1989.

Lowe, D.G, Perceptual Organization and Visual recognition, Kluwer Academic Publishers. 1985.

Tsai, R.Y., An Effisient and Accurate Camera Calibration Technique for 3D Machine Vision. Proceeding of IEEE Conference on Computer Vision and Pattern Recognition. Miami Beach. Florida. pp. 364-374. 1986.

Araujo H., Carceroni Rodrigo L. Brown Christopher M., A Fully Projective Formulation to Improve the Accuracy of Lowe’s Pose Estimation Algorithm, Computer Vision and Images Understanding. Volume 70. Pages 227-238. 1998.

Resmana Lim. Davina. Sivia R., Pelacakan dan estimasi Pose Video wajah 3 Dimensi. Jurnal Teknik Elektro. volume 2. nomer 2. UK Petra. 2002.

Sunu Wibarama, Fundamental Techniques For 3D Computer Vision, A Tutorial for Entry Level Researcher, Tutorial 3D Reconstruction. v1.0, Gadjah Mada University. Indonesia. 2011.

Gibson, J.J., The Perception of the Visual World, Houghton Mifflin, pages 235. Cambrigde. Massachusetts. USA. 1950.

Martins Pedro. Batista Jorge, Accurate Single View Model-Based head Pose Estimation, 8th IEEE International Conference on Automatic Face and Gesture Recognition. pages 1-6. 2008.

D. Oberkampf, D. F. DeMenthon, Larry S. Davis. Iterative Pose Estimation using Coplanar Feature Points. Computer Vision and Image Understanding. vol. 63 no. 3. pages 495-511. May 1996.

How to Cite
Heri Pratikno. (1). Kontrol Gerakan Objek 3D Augmented Reality Berbasis Titik Fitur Wajah dengan POSIT. Jurnal Nasional Teknik Elektro Dan Teknologi Informasi, 4(1), 16-24. Retrieved from https://journal.ugm.ac.id/v3/JNTETI/article/view/3029
Section
Articles