人走路的步態已被認為是一種很有潛力的辨識特徵應用，利用影像辨識技術，在遠距離或解析度較低的影像中來有效的辨識目標係本論文研究的課題。本論文提出一個步態辨識系統並應用在可變速度行走上，主要目的在於可以遠距離僅由步態判斷不同的人，並提高系統的穩定性與準確性。首先，提出利用平移方式建立步態能量圖得到更完整的步態週期，以增加訓練的資料量，特徵擷取係使用梯度直方圖結合等比縮小灰階圖建立之。接著，利用離散小波轉換抽取低頻小波成份當作特徵向量，最後，結合機率神經網路分類器進行特徵向量比對分類。本論文所提方法實際驗證於現有公開的OU-ISIR步態資料庫，實驗結果證實所提方法準確率可以達到98%以上，在±1Km/hour的速率變異下，準確率也可達到90%以上。

The thesis proposes a gait identification system with variable walking speeds. The main purpose is to judge the identity of individuals from a distance and improve the stability and accuracy of the system. This thesis employs the shift method to establish a gait energy image to obtain a more complete gait cycle and increases the amount of training data. By feature extraction, this thesis first combines the histogram of oriented gradients with the scale reduction grayscale image to obtain a basic feature, and then applies the discrete wavelet transformation to extract low-frequency wavelet as the feature vectors. For classification problem, the probabilistic neural network is adopted to perform the feature vector classification. The proposed scheme is actually verified by the OU-ISIR gait database. The simulation and verification results demonstrate that the correct classification rate of the proposed method can reach over 98%, and even the speed rate within ±1Km/hour, can be improved over 90%.

[1] M. P. MURRAY, A. B. DROUGHT, and R. C. KORY, "Walking Patterns of Normal Men," The Journal of Bone & Joint Surgery, vol. 46, no. 2, pp. 335-360, 1964.

[2] M. Burnfield, "Gait analysis: normal and pathological function," Journal of Sports Science and Medicine, vol. 9, no. 2, p. 353, 2010.

[3] M. A. R. Ahad, J. K. Tan, H. Kim, and S. Ishikawa, "Motion history image: its variants and applications," Machine Vision and Applications, journal article vol. 23, no. 2, pp. 255-281, March 01 2012

[4] A. F. Bobick and J. W. Davis, "The recognition of human movement using temporal templates," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 3, pp. 257-267, 2001

[5] L. Byungyun, S. Hong, H. Lee, and E. Kim, "Gait recognition system using decision-level fusion," in 2010 5th IEEE Conference on Industrial Electronics and Applications, 15-17 June 2010 2010, pp. 313-316

[6] P. Chattopadhyay, S. Sural, and J. Mukherjee, "Frontal Gait Recognition From Incomplete Sequences Using RGB-D Camera,", IEEE Trans. Inf. Forensic Secur., Article vol. 9, no. 11, pp. 1843-1856, Nov 2014

[7] P. Chattopadhyay, S. Sural, and J. Mukherjee, "Frontal Gait Recognition From Incomplete Sequences Using RGB-D Camera,", IEEE Trans. Inf. Forensic Secur., Article vol. 9, no. 11, pp. 1843-1856, Nov 2014

[8] X. L. Li, S. J. Maybank, S. C. Yan, D. C. Tao, and D. Xu, "Gait components and their application to gender recognition," , IEEE Trans. Syst. Man Cybern. Part C-Appl. Rev., Review vol. 38, no. 2, pp. 145-155, Mar 2008

[9] L. Lee and W. E. L. Grimson, "Gait analysis for recognition and classification," in Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition, 21-21 May 2002 2002, pp. 155-162

[10] J. Ryu and S. Kamata, "Front view gait recognition using Spherical Space Model with Human Point Clouds," in 2011 18th IEEE International Conference on Image Processing, 11-14 Sept. 2011 2011, pp. 3209-3212

[11] L. Wang, T. N. Tan, W. M. Hu, and H. Z. Ning, "Automatic gait recognition based on statistical shape analysis,", IEEE Trans. Image Process., Article vol. 12, no. 9, pp. 1120-1131, Sep 2003

[12] T. H. W. Lam, K. H. Cheung, and J. N. K. Liu, "Gait flow image: A silhouette-based gait representation for human identification,", Pattern Recognit., Article vol. 44, no. 4, pp. 973-987, Apr 2011

[13] X. Y. Ben, W. X. Meng, R. Yan, and K. J. Wang, "Kernel coupled distance metric learning for gait recognition and face recognition,", Neurocomputing, Article vol. 120, pp. 577-589, Nov 2013

[14] H. Ng, H. Tong, W. Tan, T. Yap, and J. Abdullah, "Gait classification with different covariate factors," in 2010 International Conference on Computer Applications and Industrial Electronics, 5-8 Dec. 2010 2010, pp. 463-467

[15] Y. Makihara et al., "The OU-ISIR Gait Database Comprising the Treadmill Dataset," IPSJ Transactions on Computer Vision and Applications, vol. 4, pp. 53-62, 2012

[16] A. F. Bobick and J. W. Davis, "The recognition of human movement using temporal templates," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 3, pp. 257-267, 2001

[17] W. Li, C. C. J. Kuo, and J. Peng, "Gait recognition via GEI subspace projections and collaborative representation classification," Neurocomputing, vol. 275, pp. 1932-1945, 2018/01/31/ 2018

[18] M. Alotaibi and A. Mahmood, "Improved gait recognition based on specialized deep convolutional neural network," Comput. Vis. Image Underst., vol. 164, pp. 103-110, 2017/11/01/ 2017

[19] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," in International Conference on Computer Vision & Pattern Recognition (CVPR '05), San Diego, United States, 2005-06-20 2005, vol. 1: IEEE Computer Society, pp. 886--893

[20] S. G. Mallat, "A THEORY FOR MULTIRESOLUTION SIGNAL DECOMPOSITION - THE WAVELET REPRESENTATION," , Ieee Transactions on Pattern Analysis and Machine Intelligence, Article vol. 11, no. 7, pp. 674-693, Jul 1989

[21] Specht, "Probabilistic neural networks for classification, mapping, or associative memory," in IEEE 1988 International Conference on Neural Networks, 24-27 July 1988 1988, pp. 525-532 vol.1

[22] A. M. Mood, Introduction to the theory of statistics (Introduction to the theory of statistics.). New York, NY, US: McGraw-Hill, 1950, pp. xiii, 433-xiii, 433.

[23] L. Wang, T. N. Tan, W. M. Hu, and H. Z. Ning, "Automatic gait recognition based on statistical shape analysis," , IEEE Trans. Image Process., Article vol. 12, no. 9, pp. 1120-1131, Sep 2003

[24] C. P. Lee, A. W. C. Tan, and S. C. Tan, "Gait recognition via optimally interpolated deformable contours," Pattern Recognition Letters, vol. 34, no. 6, pp. 663-669, 2013/04/15/ 2013.

[25] L. Zongyi and S. Sarkar, "Simplest representation yet for gait recognition: averaged silhouette," in Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 26-26 Aug. 2004 2004, vol. 4, pp. 211-214 Vol.4,

[26] E. Zhang, Y. Zhao, and W. Xiong, "Active energy image plus 2DLPP for gait recognition," Signal Process., vol. 90, no. 7, pp. 2295-2302, 2010/07/01/ 2010

[27] C. P. Lee, A. W. C. Tan, and S. C. Tan, "Gait probability image: An information-theoretic model of gait representation," J. Vis. Commun. Image Represent., vol. 25, no. 6, pp. 1489-1492, 2014/08/01/ 2014