Dynamic Time Warping in Gait Classificationof Motion Capture Data
The method of gait identification based on the nearest neighbor classification technique with motion similarity assessment by the dynamic time warping is proposed. The model based kinematic motion data, represented by the joints rotations coded by Euler angles and unit quaternions is used. The different pose distance functions in Euler angles and quaternion spaces are considered. To evaluate individual features of the subsequent joints movements during gait cycle, joint selection is carried out. To examine proposed approach database containing 353 gaits of 25 humans collected in motion capture laboratory is used. The obtained results are promising. The classifications, which takes into consideration all joints has accuracy over 91%. Only analysis of movements of hip joints allows to correctly identify gaits with almost 80% precision.
[1] Boyd J.E. Little J.J. Biometric Gait Identification, Lecture Notes in
Computer Science 3161 Springer 2005.
[2] Świtoński, A., Mucha, R., Danowski, D., Mucha, M., Cieślar, G.,
Wojciechowski, K., Sieroń, A., Human identification based on a
kinematical data of a gait, Electrical Review, 2011.
[3] Poppe R., Vision-based human motion analysis: An overview, Computer
Vision and Image Understanding, 2007.
[4] Pushpa M., Arumugamz G., An Efficient Gait Recognition System For
Human Identification Using Modified ICA, International Journal of
Computer Science and Information Technology, vol. 2, no. 1, 2010
[5] Liang W., Tieniu T., , Huazhong N., and Weiming H., Silhouette
Analysis-Based Gait Recognition for Human Identification, IEEE
Transactions on Pattern Analysis and Machine Intelligence vol. 25, no.
12, 2003.
[6] M. Cheng, M. Ho, C.Huang
,
Gait Analysis For Human Identification
Through Manifold Learning and HMM, Pattern Recognition, Volume 41
Issue 8, 2541-2553, 2008.
[7] Świtoński, A., Polański, A., Wojciechowski, K. Human identification
based on the reduced kinematic data of the gait, IEEE 7th International
Symposium on Image and Signal Processing and Analysis, 2011.
[8] Świtoński, A., Polański, A., Wojciechowski, K. Human identification
based on gait paths , Advanced Concepts for Intelligent Vision Systems,
LNCS, 2011.
[9] Zonghua Zhang,Nikolaus F Troje:, View-independent person
identification from human gait, Neurocomputing 69, 2005
[10] Pogorelc B., Gams M., Diagnosing Health Problems from Gait Patterns
of Elderly, Engineering in Medicine and Biology Society (EMBC), 2010
Annual International Conference of the IEEE, pp. 2238 - 2241, ISBN:
978-1-4244-4123-5.
[11] Zifchock R., Davis I., Higginson J., Royer T., The symmetry angle: A
novel, robust method of quantifying asymmetry, Gait & Posture,
Volume 27, Issue 4, May 2008, Pages 622-627.
[12] Omar S. Mian, Susanne A. Schneider, Petra Schwingenschuh, Kailash
P. Bhatia and Brian L. Day, Gait in SWEDDs Patients: Comparison with
Parkinson-s Disease Patients and Healthy Controls, Movement
Disorders, (2011), DOI: 10.1002/mds.23684.
[13] Lakany H., Extracting a diagnostic gait signature, Pattern Recognition,
Volume 41, Issue 5, May 2008, Pages 1627-1637disease, Clinical
Biomechanics, Volume 16, Issue 6, July 2001, Pages 459-470.
[14] Muller M., Roder T.: A Relational Approach to Content-based Analysis
of Motion Capture Data. Vol. 36 of Computational Imaging and Vision,
ch. 20, 477-506, 2007.
[15] Kale A., Sundaresan A., Rajagopalan A. N., Cuntoor N. P., Roy-
Chowdhury A. K., Kr├╝ger V., Chellappa R.: Identification of Humans
Using Gait, IEEE Transactions On Image Processing, Vol. 13, No. 9,
2004.
[16] Cheng M., Ho M., Huang C.
,
Gait Analysis For Human Identification
Through Manifold Learning and HMM.
[17] Krzeszkowski T., Michalczuk A., Switonski A., Josiński H, Kwolek B.,
Markerless 3D Human Motion Capture for Gait Characterization and
Recognition, ICCVG, LNCS, 2012.
[18] Myers C., Rabiner L., Rosenberg A., \Performance tradeo_s in dynamic
time warping algorithms for isolated word recognition,"Acoustics,
Speech, and Signal Processing [see also IEEE Transactions onSignal
Processing], IEEE Transactions on, vol. 28, no. 6, pp. 623{635,1980.
[19] Sakoe H., Chiba S., \Dynamic programming algorithm optimization for
spoken word recognition," Acoustics, Speech and Signal Processing,
IEEE Transactions on, vol. 26, no. 1, pp. 43{49, 1978.
[20] Kovar L., Gleicher M., Pighin F.. Motion graphs. ACM, Trans. Graph.,
2002.
[21] Johnson M. Exploiting Quaternions to Support Expressive Interactive
CharacterMotion. PhD thesis, Massachusetts Institute of Technology,
2003.
[22] Keogh J., Pazzan M J., Derivative Dynamic Time Warping, First SIAM
International Conference on Data Mining, 2001.
[23] Kulbacki M., Segen J., Bak A., Unsupervised Learning Motion Models
Using Dynamic Time Warping, Proceedings of the IIS'2002 Symposium
on Intelligent Information Systems, 2002.
[24] Munich M., Perona P., Continous Dynamic Time Warrping for
trnaslation-invariant curve alignmentwith applicatiomn to signature
verification, Proc. of the 7th International Conference on Computer
Vision (ICCV-99), Korfu, Greece, September, 1999.
[25] Zhou F., de la Torre F., Canonical Time Warping for Alignment of
Human Behavior, Neural Information Processing Systems, 2009.
[26] Hold G.A., Reinder M.J., Hendrics E.A., Multi-Dimensional Dynamic
Time Warping for Gesture Recognition, Thirteenth annual conference of
the Advanced School for Computing and Imaging, 2007.
[27] Martin M., Maycock J., Schmidt P., Kramer O., Recognition of Manual
Actions Using Vector Quantization and Dynamic Time Warping Lecture
Notes in Computer Science, 2010, Volume 6076/2010.
[28] Kale A.A., Cuntoor N.P., Yegnanarayana B., Rajagopalan A.N.,
Chellappa R., "Gait Analysis for Human Identification", ;in Proc.
AVBPA, 2003, pp.706-714.
[29] Boulgouris N. V., Plataniotis K. N., Hatzinakos, D. Gait Recognition
Using Dynamic Time Warping, IEEE International Workshop on
Multimedia Signal Processing ,Sienna, Italy, September 2004.
[30] Sakoe H., Chiba S., Dynamic Programming Algorihtm Optimization for
Spoken Word Recognition, IEEE Transactions on Acoustics, Speech
and Signal Processing Vol.. ASSP-26, No. 1, 1978.
[1] Boyd J.E. Little J.J. Biometric Gait Identification, Lecture Notes in
Computer Science 3161 Springer 2005.
[2] Świtoński, A., Mucha, R., Danowski, D., Mucha, M., Cieślar, G.,
Wojciechowski, K., Sieroń, A., Human identification based on a
kinematical data of a gait, Electrical Review, 2011.
[3] Poppe R., Vision-based human motion analysis: An overview, Computer
Vision and Image Understanding, 2007.
[4] Pushpa M., Arumugamz G., An Efficient Gait Recognition System For
Human Identification Using Modified ICA, International Journal of
Computer Science and Information Technology, vol. 2, no. 1, 2010
[5] Liang W., Tieniu T., , Huazhong N., and Weiming H., Silhouette
Analysis-Based Gait Recognition for Human Identification, IEEE
Transactions on Pattern Analysis and Machine Intelligence vol. 25, no.
12, 2003.
[6] M. Cheng, M. Ho, C.Huang
,
Gait Analysis For Human Identification
Through Manifold Learning and HMM, Pattern Recognition, Volume 41
Issue 8, 2541-2553, 2008.
[7] Świtoński, A., Polański, A., Wojciechowski, K. Human identification
based on the reduced kinematic data of the gait, IEEE 7th International
Symposium on Image and Signal Processing and Analysis, 2011.
[8] Świtoński, A., Polański, A., Wojciechowski, K. Human identification
based on gait paths , Advanced Concepts for Intelligent Vision Systems,
LNCS, 2011.
[9] Zonghua Zhang,Nikolaus F Troje:, View-independent person
identification from human gait, Neurocomputing 69, 2005
[10] Pogorelc B., Gams M., Diagnosing Health Problems from Gait Patterns
of Elderly, Engineering in Medicine and Biology Society (EMBC), 2010
Annual International Conference of the IEEE, pp. 2238 - 2241, ISBN:
978-1-4244-4123-5.
[11] Zifchock R., Davis I., Higginson J., Royer T., The symmetry angle: A
novel, robust method of quantifying asymmetry, Gait & Posture,
Volume 27, Issue 4, May 2008, Pages 622-627.
[12] Omar S. Mian, Susanne A. Schneider, Petra Schwingenschuh, Kailash
P. Bhatia and Brian L. Day, Gait in SWEDDs Patients: Comparison with
Parkinson-s Disease Patients and Healthy Controls, Movement
Disorders, (2011), DOI: 10.1002/mds.23684.
[13] Lakany H., Extracting a diagnostic gait signature, Pattern Recognition,
Volume 41, Issue 5, May 2008, Pages 1627-1637disease, Clinical
Biomechanics, Volume 16, Issue 6, July 2001, Pages 459-470.
[14] Muller M., Roder T.: A Relational Approach to Content-based Analysis
of Motion Capture Data. Vol. 36 of Computational Imaging and Vision,
ch. 20, 477-506, 2007.
[15] Kale A., Sundaresan A., Rajagopalan A. N., Cuntoor N. P., Roy-
Chowdhury A. K., Kr├╝ger V., Chellappa R.: Identification of Humans
Using Gait, IEEE Transactions On Image Processing, Vol. 13, No. 9,
2004.
[16] Cheng M., Ho M., Huang C.
,
Gait Analysis For Human Identification
Through Manifold Learning and HMM.
[17] Krzeszkowski T., Michalczuk A., Switonski A., Josiński H, Kwolek B.,
Markerless 3D Human Motion Capture for Gait Characterization and
Recognition, ICCVG, LNCS, 2012.
[18] Myers C., Rabiner L., Rosenberg A., \Performance tradeo_s in dynamic
time warping algorithms for isolated word recognition,"Acoustics,
Speech, and Signal Processing [see also IEEE Transactions onSignal
Processing], IEEE Transactions on, vol. 28, no. 6, pp. 623{635,1980.
[19] Sakoe H., Chiba S., \Dynamic programming algorithm optimization for
spoken word recognition," Acoustics, Speech and Signal Processing,
IEEE Transactions on, vol. 26, no. 1, pp. 43{49, 1978.
[20] Kovar L., Gleicher M., Pighin F.. Motion graphs. ACM, Trans. Graph.,
2002.
[21] Johnson M. Exploiting Quaternions to Support Expressive Interactive
CharacterMotion. PhD thesis, Massachusetts Institute of Technology,
2003.
[22] Keogh J., Pazzan M J., Derivative Dynamic Time Warping, First SIAM
International Conference on Data Mining, 2001.
[23] Kulbacki M., Segen J., Bak A., Unsupervised Learning Motion Models
Using Dynamic Time Warping, Proceedings of the IIS'2002 Symposium
on Intelligent Information Systems, 2002.
[24] Munich M., Perona P., Continous Dynamic Time Warrping for
trnaslation-invariant curve alignmentwith applicatiomn to signature
verification, Proc. of the 7th International Conference on Computer
Vision (ICCV-99), Korfu, Greece, September, 1999.
[25] Zhou F., de la Torre F., Canonical Time Warping for Alignment of
Human Behavior, Neural Information Processing Systems, 2009.
[26] Hold G.A., Reinder M.J., Hendrics E.A., Multi-Dimensional Dynamic
Time Warping for Gesture Recognition, Thirteenth annual conference of
the Advanced School for Computing and Imaging, 2007.
[27] Martin M., Maycock J., Schmidt P., Kramer O., Recognition of Manual
Actions Using Vector Quantization and Dynamic Time Warping Lecture
Notes in Computer Science, 2010, Volume 6076/2010.
[28] Kale A.A., Cuntoor N.P., Yegnanarayana B., Rajagopalan A.N.,
Chellappa R., "Gait Analysis for Human Identification", ;in Proc.
AVBPA, 2003, pp.706-714.
[29] Boulgouris N. V., Plataniotis K. N., Hatzinakos, D. Gait Recognition
Using Dynamic Time Warping, IEEE International Workshop on
Multimedia Signal Processing ,Sienna, Italy, September 2004.
[30] Sakoe H., Chiba S., Dynamic Programming Algorihtm Optimization for
Spoken Word Recognition, IEEE Transactions on Acoustics, Speech
and Signal Processing Vol.. ASSP-26, No. 1, 1978.
@article{"International Journal of Information, Control and Computer Sciences:63950", author = "Adam Świtoński and Agnieszka Michalczuk and Henryk Josiński and Andrzej Polański and KonradWojciechowski", title = "Dynamic Time Warping in Gait Classificationof Motion Capture Data", abstract = "The method of gait identification based on the nearest neighbor classification technique with motion similarity assessment by the dynamic time warping is proposed. The model based kinematic motion data, represented by the joints rotations coded by Euler angles and unit quaternions is used. The different pose distance functions in Euler angles and quaternion spaces are considered. To evaluate individual features of the subsequent joints movements during gait cycle, joint selection is carried out. To examine proposed approach database containing 353 gaits of 25 humans collected in motion capture laboratory is used. The obtained results are promising. The classifications, which takes into consideration all joints has accuracy over 91%. Only analysis of movements of hip joints allows to correctly identify gaits with almost 80% precision.
", keywords = "Biometrics, dynamic time warping, gait identification, motion capture, time series classification, quaternion distance functions, attribute ranking.", volume = "6", number = "11", pages = "1510-6", }
