本論文提出了將人臉識別功能與校正車體晃動測距誤差以及避障功能結合於兩輪機器人，使得機器人在照護及居家環境都能有更好的追蹤效果。兩輪機器人平衡或是移動時，會因為兩輪車機體晃動導致測距值的不穩定，本論文除了讓Kinect感應器的驅動馬達能自動使感應器保持水平外，也使用智慧型的預測方式來修正測距誤差值，增加測距值與避障決策的精準度。測距避障的部分則藉由Kinect感應器的深度影像完成，並將測距值與移動指令上傳至MySQL資料庫供兩輪機器人使用。在人臉識別的功能，本研究使用LBPH演算法完成，並以UART傳送資訊給兩輪機器人。並以實驗以及圖表驗證本論文提出的功能。

This thesis proposes to combine the correction of robotic body sway ranging error, obstacle avoidance function and face recognition function in two-wheeled robots for the purpose of enabling the robots to have better tracking results in both personal care and home environments. When the two-wheeled robots autonomously balances or moves, the ranging value will be unstable due to the shaking of the two-wheeled robots. In addition to using the Kinect sensor's drive motor to automatically maintain the level of sensor, this paper also uses a smart prediction method to correct the ranging error value in order to increase the accuracy of ranging value and the obstacle avoidance decision. The obstacle avoidance function is completed by the depth image of the Kinect sensor, and the ranging value and the movement instruction are uploaded to the MySQL database. This study uses the LBPH algorithm to complete the face recognition function and sends information to the two-wheeled robots with the universal asynchronous receiver-transmitter. Finally, in order to verify the proposed method, some experiments are performed.

參考文獻
[1] F. Kung, "Design of agile two-wheeled robot with machine vision," 2017 International Conference on Robotics, Automation and Sciences (ICORAS), Melaka, 2017, pp. 1-5.
[2] T. Ahonen, A. Hadid and M. Pietikainen, "Face Description with Local Binary Patterns: Application to Face Recognition," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037-2041, Dec. 2006.
[3] H. Filali, J. Riffi, A. M. Mahraz and H. Tairi, "Multiple face detection based on machine learning," 2018 International Conference on Intelligent Systems and Computer Vision (ISCV), Fez, 2018, pp. 1-8.
[4] J. I. Flores-Delgado, L. G. Martínez-Santos, R. Lozano, I. Gonzalez-Hernandez and D. A. Mercado, "Embedded control using monocular vision: Face tracking," 2017 International Conference on Unmanned Aircraft Systems (ICUAS), Miami, FL, USA, 2017, pp. 1285-1291.
[5] K. R. Kakkirala, S. R. Chalamala and S. K. Jami, "Thermal Infrared Face Recognition: A Review," 2017 UKSim-AMSS 19th International Conference on Computer Modelling & Simulation (UKSim), Cambridge, United Kingdom, 2017, pp. 55-60.
[6] Z. Yu, F. Liu, R. Liao, Y. Wang, H. Feng and X. Zhu, "Improvement of Face Recognition Algorithm Based on Neural Network," 2018 10th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), Changsha, 2018, pp. 229-234.
[7] A. L. Ramadhani, P. Musa and E. P. Wibowo, "Human face recognition application using pca and eigenface approach," 2017 Second International Conference on Informatics and Computing (ICIC), Jayapura, 2017, pp. 1-5.
[8] 深度影像 https://www.zhihu.com/question/37920173.
[9] Kinect感應器 https://zh.wikipedia.org/wiki/Kinect.
[10] M. Limin and Z. Peiyi, "The medical service robot interaction based on kinect," 2017 IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS), Srivilliputhur, 2017, pp. 1-7.
[11] K. Goyal, K. Agarwal and R. Kumar, "Face detection and tracking: Using OpenCV," 2017 International conference of Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, 2017, pp. 474-478.
[12] T. Ojala, M. Pietikäinen, and D. Harwood (1994), "Performance evaluation of texture measures with classification based on Kullback discrimination of distributions", Proceedings of the 12th IAPR International Conference on Pattern Recognition (ICPR 1994), vol. 1, pp. 582 - 585.
[13] Kinect內部攝影機 https://archive.eettaiwan.com/www.eettaiwan.com/ART_8800636709_480502_NT_588d3aa8.HTM