Acquiring Kinematics of Lower extremity with Kinect

Abstract

Gait analysis is used in monitoring the procedures of treatment and determining many illnesses notably musculoskeletal system disorders. Gait analysis has been carried out with divergent methods for a long time. In this study, kinematic parameters of lower human extremities are determined using Kinect, a camera called Time of Flight that is usually used in the entertainment sector. Kinect is recommended as a low-cost solution for existing gait analysis systems. Kinematic parameters that are used to analyze walking are found by filtering RGB images of colored markers that are attached to joints. 3D world coordinates of the marker centers were determined and labeled by mapping the depth information, which is obtained from Kinect, on RGB images. We used the Kalman filter to estimate the coordinates of markers when the coordinates cannot be accurately determined because of motion blurring. 15 kinematic parameters for each joint are extracted from the coordinates of these markers.

Keywords

• Human Motion Analysis
• Microsoft Kinect
• Kinematics
• Gait.

Kinect Kullanarak Alt Ekstremiteye Ait Kinematiğin Elde Edilmesi

Öz

Yürüyüş analizi, tedavi süreçlerinin izlenmesinde ve başta kas-iskelet sistemi rahatsızlıkları olmak üzere birçok hastalığın belirlenmesinde farklı teknikler kullanılarak yapılmaktadır. Bu çalışmada, genellikle eğlence sektöründe kullanılan Time of Flight adlı bir kamera olan Kinect kullanılarak alt insan ekstremitelerinin kinematik parametreleri belirlendi. Çalışmada önerilen sistem, mevcut yürüyüş analiz sistemleri için düşük maliyetli bir çözüm olarak önerildi. Yürümeyi analiz etmek için kullanılan kinematik parametreler, eklemlere eklenen renkli işaretçilerin RGB görüntülerini filtreleyerek bulundu. Kinect'ten elde edilen derinlik bilgisi RGB görüntüler üzerine haritalanarak işaretleyici merkezlerinin üç boyutlu dünya koordinatları belirlenmiş ve etiketlenmiştir. Hareket bulanıklığı nedeniyle koordinatların tam olarak belirlenemediği işaretçilerin konumları Kalman filtresi ile tahmin edildi. Her eklem için 15 kinetik parametre bu işaretçilerin koordinat bilgileri kullanılarak çıkarıldı.

Anahtar Kelimeler

• Yürüme Analizi
• Microsoft Kinect
• Yürüme Kinematiği.

Kaynakça

1. M. W. Whittle, Gait analysis: an introduction, vol. 3. 2002.
2. G. Yavuzer, “Three-dimensional quantitative gait analysis,” Acta Orthop. Traumatol. Turc., vol. 43, no. 2, pp. 94–101, 2009.
3. M. Whittle, “Clinical gait analysis: A review,” Hum. Mov. Sci., vol. 15, pp. 369–387, 1996.
4. D. H. Sutherland, “The evolution of clinical gait analysis part 1: Kinesiological EMG,” Gait and Posture, vol. 14. pp. 61–70, 2001.
5. D. H. Sutherland, “The evolution of clinical gait analysis: Part II kinematics,” Gait Posture, vol. 16, pp. 159–179, 2002.
6. D. H. Sutherland, “The evolution of clinical gait analysis part III--kinetics and energy assessment.,” Gait Posture, vol. 21, pp. 447–461, 2005.
7. H. Zhou and H. Hu, “Human motion tracking for rehabilitation—A survey,” Biomed. Signal Process. Control, vol. 3, no. 1, pp. 1–18, Jan. 2008.
8. S. E. M. L. R. G. Morris, R. Morris, and S. Lawson, “A review and evaluation of available gait analysis technologies, and their potential for the measurement of impact transmission,” Newcastle Univ., 2010.

9. F. Destelle, A. Ahmadi, N. E. O’Connor, K. Moran, A. Chatzitofis, D. Zarpalas, and P. Daras, “Low-cost accurate skeleton tracking based on fusion of kinect and wearable inertial sensors.” pp. 371–375, 2014.
10. E. Stone and M. Skubic, “Evaluation of an Inexpensive Depth Camera for Passive In-Home Fall Risk Assessment,” Proc. 5th Int. ICST Conf. Pervasive Comput. Technol. Healthc., 2011.
11. E. E. Stone and M. Skubic, “Passive in-home measurement of stride-to-stride gait variability comparing vision and Kinect sensing.,” Conf. Proc. IEEE Eng. Med. Biol. Soc., vol. 2011, pp. 6491–4, Jan. 2011.
12. [12] M. Gabel, R. Gilad-Bachrach, E. Renshaw, and A. Schuster, “Full body gait analysis with Kinect.,” Conf. Proc. IEEE Eng. Med. Biol. Soc., vol. 2012, pp. 1964–7, 2012.
13. Microsoft Research, “Kinect for Windows SDK beta,” Program. Guid., pp. 1–33, 2011.
14. Z. Zhang, “Microsoft Kinect Sensor and Its Effect,” IEEE Multimedia, vol. 19. pp. 4–10, 2012.
15. J. Heikkilä and O. Silvén, “A Four-step Camera Calibration Procedure with Implicit Image Correction.”
16. R. Laganière, OpenCV 2 Computer Vision Application Programming Cookbook. 2011.
17. C. L. Vaughan, B. L. Davis, L. Christopher, and J. C. O. Connor, Dynamics of human gait, vol. 26. 2005.
18. M. W. Whittle, Gait analysis: an introduction, vol. 3. 2002.
19. D. A. Winter, Biomechanics and motor control of human movement, Fourth Edition, vol. 2. 2009.
20. H. D. Cheng, X. H. Jiang, Y. Sun, and J. Wang, “Color image segmentation: Advances and prospects,” Pattern Recognit., vol. 34, no. 12, pp. 2259–2281, 2001.
21. G. Welch and G. Bishop, “An Introduction to the Kalman Filter,” In Pract., vol. 7, pp. 1–16, 2006.
22. S. S. Pathan, A. Al-Hamadi, and B. Michaelis, “Intelligent feature-guided multi-object tracking using Kalman filter,” in 2009 2nd International Conference on Computer, Control and Communication, 2009, pp. 1–6.
23. R. E. Kalman, “A New Approach to Linear Filtering and Prediction Problems,” Trans. ASME-Journal Basic Eng., vol. 82, no. Series D, pp. 35–45, 1960.
24. E. Cuevas, D. Zaldivar, and R. Rojas, “Kalman filter for vision tracking,” Measurement, no. August, pp. 1–18, 2005.
25. S. Park, S. Yu, J. Kim, S. Kim, and S. Lee, “3D hand tracking using Kalman filter in depth space,” EURASIP J. Adv. Signal Process., vol. 2012, no. 1, p. 36, Feb. 2012.
26. S.-K. Weng, C.-M. Kuo, and S.-K. Tu, “Video object tracking using adaptive Kalman filter,” Journal of Visual Communication and Image Representation, vol. 17, no. 6. pp. 1190–1208, 2006.
27. X. Li, K. Wang, W. Wang, and Y. Li, “A multiple object tracking method using Kalman filter,” Inf. Autom. …, vol. 1, no. 1, pp. 1862–1866, 2010.
28. C. Oz and M. A. L. I. Oz, “Developing and establishing a natural user interface based on Kinect sensor with artificial neural network,” Optoelectron. Adv. Mater. Commun., vol. 8, no. 11, pp. 1176–1186, 2014.