Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지

MRF Particle filter-based Multi-Touch Tracking and Gesture Likelihood Estimation

MRF 입자필터 멀티터치 추적 및 제스처 우도 측정

  • Received : 2014.03.13
  • Accepted : 2012.03.27
  • Published : 2015.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a method for multi-touch tracking using MRF-based particle filters and gesture likelihood estimation Each touch (of one finger) is considered to be one object. One of frequently occurring issues is the hijacking problem which means that an object tracker can be hijacked by neighboring object. If a predicted particle is close to an adjacent object then the particle's weight should be lowered by analysing the influence of neighboring objects for avoiding hijacking problem. We define a penalty function to lower the weights of those particles. MRF is a graph representation where a node is the location of a target object and an edge describes the adjacent relation of target object. It is easy to utilize MRF as data structure of adjacent objects. Moreover, since MRF graph representation is helpful to analyze multi-touch gestures, we describe how to define gesture likelihoods based on MRF. The experimental results show that the proposed method can avoid the occurrence of hijacking problems and is able to estimate gesture likelihoods with high accuracy.

본 논문에서는 멀티터치 추적 및 제스처 인식을 위하여 MRF기반 입자필터와 제스처 우도 측정 방법을 제안한다. 멀티터치 추적에서 자주 발생하는 문제 중 하나는 강탈 문제이며 터치 객체 추적기가 이웃 터치 객체에게 빼앗기는 현상을 가리킨다. 강탈 문제의 원인은 입자필터의 예측 입자들이 이웃 터치 객체에 가까이 갈 경우 입자의 가중치(우도)가 낮아야 하지만 이웃 객체 영향으로 높게 계산되는 오류 때문이다. 따라서 MRF를 기반으로 이웃 객체에 가까운 입자의 가중치를 낮추는 벌점함수를 정의한다. MRF가 멀티터치를 노드로 정의하고 거리가 가까운 이웃 멀티터치들을 에지로 표현한 그래프정보이므로 이웃 멀티터치들에 대한 데이터구조로 활용되기 쉽다. 또한 MRF 그래프 정보를 바탕으로 멀티터치 제스처 분석이 가능하다. 본 논문에서는 MRF를 기반으로 다양한 제스처 우도를 정의할 수 있는 방법을 서술한다. 실험 결과에서는 제안 방법이 효과적으로 강탈 현상을 회피하고 멀티터치 제스처 우도를 정확히 측정할 수 있음을 확인할 수 있다.

Keywords

References

  1. J. Y. Han, "Low-cost Multi-touch Sensing through Frustrated Total Internal Reflection," 18th Annu. Assoc. Comput. Machinery Symp. UI Software Tech, pp. 115-118, 2005.
  2. D. Reid, "An Algorithm fur Tracking Multiple Targets." IEEE Trans. on Automation and Control AC, Vol. 24, pp. 84-90, 1979.
  3. Y. Bar-Shalom and T. E. Fortmann, "Tracking and Data Association," Academic Press, Mathematics in Science and Engineering, 1988.
  4. T. Kirubarajan and Y. Bar-Shalom, "Probabilistic Data Association Techniques fur Target Trncking in Clutter." Proc. the IEEE, 92(3), pp. 536-557, 2004. https://doi.org/10.1109/JPROC.2003.823149
  5. Y. Bar-Shalom, T. Fortmann, and M Scheffe, "Joint Probabilistic Data Association for Multiple Targets in Clutter," Conf. on Information Sciences and Systems, 1980.
  6. RoboEarth Project, FP7-ICT-248942, 2010.
  7. G. Bishop and G. Welch, "An Introduction to the Kalman Filter," SIGGRAPH2001, Course 8, 2001..
  8. S. Arulampalam, S. Maskell, N. Gordon and T. Clapp, "A Tutorial on Particle Filters far On-Line Non-Linear/Non-Gaussian Bayesian Tracking," IEEE Tans. Signal Processing, vol. 50, pp. 174-189, 2002. https://doi.org/10.1109/78.978374
  9. D. Schulz, W. Burgard, D. Fox, and A B. Cremers, "Tracking Multiple Moving Targets with a Mobile Robot using Particle Filters and Statistical Data Association," IEEE Int. Conf. on Robotics and Automation, 2001.
  10. S. Oh, S. Russell, and S. Sastry, "Markov chain Monte Carlo data association for general multiple-target tracking problems," IEEE Conference on Decision and Control, 2004.
  11. M. Z. Islam, C. M. Oh, J. s. Lee, and C. W. Lee, "Multi-Part Histogram based Visual Tracking with Maximum of Posteriori," Int. Conf. on Camp. Engineering and Tech., 2010.
  12. Z. Khan, T. Balch, and F. Dellaert, "MCMC-based Particle Filtering far Tracking a Variable Number of Interacting Targets," IEEE Trans. on Pattern Analysis and Machine Inetelligence, Vol. 27(11), pp. 1005-1819, 2005.
  13. S. G. Kim, J. W. Kim, K T. Bae and C. W. Lee, "Multi-touch Interaction far Table-top Display," 16th International Conference on Artificial Reality and Telexistence, pp.1273-1282, 2006.