本研究提出一個基於傳統機器學習與深度學習架構, 以紅外(熱感)攝影機在夜間拍攝而得的公開資料集CASIA-C作為影像源, 比較倆架構在夜間步態辨識及預測方面的有效性. 機器學習架構使用k-近鄰演算法(K-Nearest Neighbors, KNN), 深度學習架構則使用長短期記憶之卷積神經網路(Convolutional Long Short Term Memory, Conv LSTM). 倆架構設計流程分別有, 對二維序列輪廓影像前處理、特徵提取、相似度與距離計算. 最終的實驗結果表明, 不同行走條件下的夜間步態辨識和預測存在顯著差異. 傳統機器學習架構的最高辨識準確率最高可達12.77%, 而深度學習架構的最高辨識準確率最高可達61.86%. 從這點來看, 在深度學習架構相同的數據處理方式下, 夜間步態略優於傳統機器學習. 該結果也可以為未來步態識別研究的專家和新手提供參考.

This paper proposed a traditional machine learning and deep learning architecture based on a public data set captured by infrared (thermal) cameras at night as the image source and compares the performance results of the two architectures in night gait recognition and prediction. The machine learning model uses K-Nearest Neighbors (KNN), and the deep learning model uses Convolutional Long Short Term Memory (ConvLSTM). Both model architecture design process includes two-dimensional contour image preprocessing, feature extraction, data normalization, and similarity classification between the two architectures. The final experimental results show that there are significant differences in night gait recognition and prediction under different walking conditions. The highest accuracy rate of identification by the traditional machine learning model is 12.77%, while the highest accuracy rate of identification by the deep learning model is 61.86%. From this point of view, the night gait is slightly better than the traditional machine learning model under the same data processing method in the deep learning model. The results can also serve as a reference for experts and novices in future gait recognition research.

[1] D. Palma and P. L. Montessoro, “Biometric-based human recognition systems: An overview,” in Recent Advances in Biometrics (M. Sarfraz, ed.), ch. 2, Rijeka: IntechOpen, 2022.
[2] Q. U. A. Rana, M. Khan, A. Haq, S. Zaidi, W. Sajjad, A. Khan, M. Khan, and M. Irfan, “A review of coronavirus disease-2019 (covid-19),” vol. 16, pp. 265–279, 05 2020.
[3] C. Shen, S. Yu, J. Wang, G. Q. Huang, and L. Wang, “A comprehensive survey on deep gait recognition: Algorithms, datasets and challenges,” 2022.
[4] C. F. G. dos Santos, D. de Souza Oliveira, L. A. Passos, R. G. Pires, D. F. S. Santos, L. P. Valem, T. P. Moreira, M. C. S. Santana, M. Roder, J. P. Papa, and D. Colombo, “Gait recognition based on deep learning: A survey,” ACM Computing Surveys, vol. 55, pp. 1–34, mar 2023.
[5] A. Sepas-Moghaddam and A. Etemad, “Deep gait recognition: A survey,” 2021.
[6] I. Rida, N. Almaadeed, and S. Al-ma’adeed, “Robust gait recognition: A comprehensive survey,” IET Biometrics, vol. 8, 01 2019.
[7] M. D. Marsico and A. Mecca, “A survey on gait recognition via wearable sensors,” ACM Comput. Surv., vol. 52, aug 2019.
[8] C. Wan, L. Wang, and V. V. Phoha, “A survey on gait recognition,” ACM Comput. Surv., vol. 51, aug 2018.
[9] I. Bouchrika, “A survey of using biometrics for smart visual surveillance: Gait recognition,”2018.
[10] J. P. Singh, S. Jain, S. Arora, and U. P. Singh, “Vision-based gait recognition: A survey,” IEEE Access, vol. 6, pp. 70497–70527, 2018.
[11] J. Wang, M. She, S. Nahavandi, and A. Kouzani, “A review of vision-based gait recognition methods for human identification,” in 2010 International Conference on Digital Image Computing: Techniques and Applications, pp. 320–327, 2010.
[12] D. Gafurov, “A survey of biometric gait recognition: Approaches, security and challenges,” 01 2007.
[13] J. Singh, S. Jain, S. Arora, and D. U. Singh, “A survey of behavioral biometric gait recognition: Current success and future perspectives,” Archives of Computational Methods in Engineering, vol. 28, 11 2019.
[14] P. Connor and A. Ross, “Biometric recognition by gait: A survey of modalities andfeatures,” Computer Vision and Image Understanding, vol. 167, pp. 1–27, 2018. 33
[15] D. Tan, K. Huang, S. Yu, and T. Tan, “Efficient night gait recognition based on template matching,” in 18th International Conference on Pattern Recognition (ICPR’06), vol. 3, pp. 1000–1003, 2006.
[16] D. Tan, K. Huang, S. Yu, and T. Tan, “Recognizing night walkers based on one pseudoshape representation of gait,” in 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8, 2007.
[17] X. Wang and S. Hosseinyalamdary, “Human detection based on a sequence of thermal images using deep learning,” ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLII-2/W13, pp. 127–132, 06 2019.
[18] M. Rai, “Thermal imaging system and its real time applications: a survey,” Journal of Engineering Technology, vol. 62, 06 2018.
[19] R. Gade and T. B. Moeslund, “Thermal cameras and applications: a survey,” Machine Vision and Applications, vol. 25, pp. 245–262, 2013.
[20] S. A. F. Manssor, S. Sun, and M. A. M. Elhassan, “Real-time human recognition at night via integrated face and gait recognition technologies,” Sensors, vol. 21, no. 13, 2021.
[21] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779–788, 2016.
[22] C.-P. Lee, A. Tan, and K. Lim, “Review on vision-based gait recognition: Representations, classification schemes and datasets,” American Journal of Applied Sciences, vol. 14, pp. 252–266, 02 2017.
[23] M. Piccardi, “Background subtraction techniques: a review,” in 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583), vol. 4, pp. 3099–3104 vol.4, 2004.
[24] R. C. Gonzalez and R. E. Woods, Digital Image Processing. Pearson Education, 4th ed., 2018.
[25] C.-Y. Yam and M. S. Nixon, Gait Recognition, Model-Based, pp. 633–639. Boston, MA: Springer US, 2009.
[26] J. C. O. Christopher L. Vaughan, Brian Leigh Davis, Dynamics of Human Gait. Human Kinetics Publishers, 2th ed., 1992.
[27] T. Stöckel, R. Jacksteit, M. Behrens, R. Skripitz, R. Bader, and A. Mau-Moeller, “The mental representation of the human gait in young and older adults,” Frontiers in Psychology, vol. 6, p. 943, 06 2015.
[28] J. Han and B. Bhanu, “Individual recognition using gait energy image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 2, pp. 316–322, 2006.
[29] X. Chen, X. Luo, J. Weng, W. Luo, H. Li, and Q. Tian, “Multi-view gait image generation for cross-view gait recognition,” IEEE Transactions on Image Processing, vol. 30, pp. 3041–3055, 2021. 34
[30] S. Yu, D. Tan, and T. Tan, “A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition,” in 18th International Conference on Pattern Recognition (ICPR’06), vol. 4, pp. 441–444, 2006.
[31] Y. Makihara, R. Sagawa, Y. Mukaigawa, T. Echigo, and Y. Yagi, “Gait recognition using a view transformation model in the frequency domain,” in Computer Vision – ECCV 2006 (A. Leonardis, H. Bischof, and A. Pinz, eds.), (Berlin, Heidelberg), pp. 151–163, Springer Berlin Heidelberg, 2006.
[32] C. Song, Y. Huang, Y. Huang, N. Jia, and L. Wang, “Gaitnet: An end-to-end network for gait based human identification,” Pattern Recognition, vol. 96, p. 106988, 2019.
[33] K. Bashir, T. Xiang, and S. Gong, “Gait recognition without subject cooperation,” Pattern Recognition Letters, vol. 31, no. 13, pp. 2052–2060, 2010. Meta-heuristic Intelligence Based Image Processing.
[34] Q. Cheng, B. Fu, and H. Chen, “Gait recognition based on pca and lda,” 2009.
[35] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.
[36] Z. Wu, Y. Huang, L. Wang, X. Wang, and T. Tan, “A comprehensive study on crossview gait based human identification with deep cnns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 1–1, 03 2016.
[37] X. Shi, Z. Chen, H. Wang, D.-Y. Yeung, W.-k. Wong, and W.-c. Woo, “Convolutional lstm network: A machine learning approach for precipitation nowcasting,” 2015.
[38] X. Shi, Z. Gao, L. Lausen, H. Wang, D.-Y. Yeung, W.-k. Wong, and W.-c. Woo, “Deep learning for precipitation nowcasting: A benchmark and a new model,” 2017.
[39] H. Iwama, M. Okumura, Y. Makihara, and Y. Yagi, “The ou-isir gait database comprising the large population dataset and performance evaluation of gait recognition,” IEEE Trans. on Information Forensics and Security, vol. 7, Issue 5, pp. 1511–1521, Oct. 2012.
[40] S. Yu, D. Tan, and T. Tan, “A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition,” in 18th International Conference on Pattern Recognition (ICPR’06), vol. 4, pp. 441–444, 2006.
[41] W. Zhu, “Classification of mnist handwritten digit database using neural network,” 2018.
[42] Z. J. Wang, R. Turko, O. Shaikh, H. Park, N. Das, F. Hohman, M. Kahng, and D. H. Chau, “CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization,” IEEE Transactions on Visualization and Computer Graphics (TVCG), 2020.
[43] “CNN Explainer [Online] Available:.” https://poloclub.github.io/cnn-explainer/.
[44] B. Lake, R. Salakhutdinov, J. Gross, and J. Tenenbaum, “One shot learning of simple visual concepts,” in Proceedings of the 33rd Annual Conference of the Cognitive Science Society, 2011. 35
[45] J. Bromley, J. W. Bentz, L. Bottou, I. Guyon, Y. LeCun, C. Moore, E. Säckinger, and R. Shah, “Signature verification using a ”siamese” time delay neural network,”in Int. J. Pattern Recognit. Artif. Intell., 1994.
[46] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, pp. 1735–1780, 1997.
[47] J. L. Elman, “Finding structure in time,” Cogn. Sci., vol. 14, pp. 179–211, 1990.
[48] W. Zaremba, I. Sutskever, and O. Vinyals, “Recurrent neural network regularization,” 2014.
[49] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling,” 2014.
[50] B. Decann and A. Ross, “Gait curves for human recognition, backpack detection and silhouette correction in a nighttime environment,” Proceedings of SPIE - The International Society for Optical Engineering, vol. 7667, 04 2010.
[51] Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni, “Generalizing from a few examples: A survey on few-shot learning,” ACM computing surveys (csur), vol. 53, no. 3, pp. 1–34, 2020.
[52] S. Feng and M. F. Duarte, “Few-shot learning-based human activity recognition,” Expert Systems with Applications, vol. 138, p. 112782, 2019.
[53] X. Wang, Y. Hua, E. Kodirov, and N. M. Robertson, “Ranked list loss for deep metric learning,” 2019.
[54] “CASIA Dataset [Online]. Available:.” http://www.cbsr.ia.ac.cn/english/GaitDatabases.asp.
[55] F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A unified embedding for face recognition and clustering,” in 2015 IEEE Conference on Computer Vision and PatternRecognition (CVPR), IEEE, jun 2015.