臺灣博碩士論文加值系統

近年來科技日新月異，智慧型運輸系統(Intelligent Transportation System，ITS)已經成為現今研究最重要的議題之一。在現今智慧型運輸系統的應用之中，對於旅行者資訊、弱勢族群保護及車輛安全等方面都有很大的需求，而以嵌入式系統來實現驗證更能體現其實用性。本論文首先由GPS定位追蹤技術開始，以AJAX技術實現一個網頁端主控追蹤系統，能夠有效節省網路頻寬與系統負擔；接著考量到GPS的精準度限制，以擴展式卡曼濾波器(EKF)整合ZigBee與GPS來達到一個較高精度的行人導引輔助系統；最後在車輛安全上，提出了駕駛安全監控系統的概念。比起傳統的駕駛輔助系統，進一步以隱藏式馬可夫模型(HMM)辨識七種駕駛行為，並以模糊理論(Fuzzy)來推論駕駛危險程度，適時提醒駕駛人注意自己的狀態，確保行車安全。本論文針對定位追蹤與行人車輛安全在智慧型運輸系統應用做一簡要介紹，接著以三個主題：主控追蹤、行人導引與駕駛行為，分別針對智慧型運輸系統運用數位訊號處理與機器學習技術之理論與實作，並實現於嵌入式平台上。
在第二章中我們提出了一個結合AJAX 技術之網頁端主控追蹤系統，隨著GPS和網際網路技術的發展，追蹤系統在物流系統、車隊管理或是社群網路都有很多應用，而對使用者來說，以網頁來瀏覽相關資訊則是最為方便的方式之一。我們所設計的框架是針對以網頁為基礎的追蹤系統，著重在兩個主要的問題，一是冗餘的連接，對於提供位置資訊的被追蹤端，沒有需求的資訊傳輸會對行動網路造成浪費的頻寬以及多餘的服務費。二是在傳輸期間的數據不同步，根據傳輸架構的不同，使用者所要求資料的時間點跟提供資料的時間點可能會有不同步的情形發生。我們所提出的連線架構不僅解決上述問題，同時也設計了一個實現在OMAP3嵌入式平台的原型來驗證我們的系統，我們統計了使用者在不同上網媒介上的延遲時間，實驗結果指出即使在最壞的情況下，使用者仍可以達到實時監測的目標。
在第三章中，我們提出一個結合GPS與無線感測網路的行人導航系統，行人導航系統跟一般的車輛導航系統一樣都是為了協助使用者抵達他們想去的目的地，但是行人移動的方式跟車輛有很大的不同，也因此適合車輛導航系統的假設條件不一定能運用在行人導航系統上。對於行人來說，在某些地點GPS的精準度並不足以完成路徑的導引，因此當行人接近這些地點時，系統就需要有較高的定位能力來完成導航。在論文中我們把這類地點定義為特別感興趣的區域(Special Interest Zone，SIZ)，在這些區域周圍會佈上ZigBee無線感測器，當使用者在一般的區域中行走時，系統會使用A*演算法與GIS地圖及GPS資訊來導航，而當使用者接近SIZ時，則會動態的切換到以擴展式卡曼濾波器整合ZigBee資訊與GPS的定位機制，提供一個定位誤差介於0.6公尺到1公尺的定位結果。系統原型實作在DM6446嵌入式平台上，並在交大校園內進行實測。
在第四章中我們提出了一個駕駛安全監控系統，提供危險係數給使用者做為駕駛安全的指標。以駕駛安全輔助系統為基礎，進一步分析與監控駕駛行為，長時間監控駕駛，預防潛在的危險。本系統整合以影像處理技術為基礎之車道偏移警示系統、前車防碰撞警示系統，再加上三軸加速度計與GPS，提供車道偏移量，距前車距離，車輛本身移動的位置，速度與加速度的資訊，以一個二階段的演算法來推估駕駛行為的危險程度。第一個階段為駕駛行為偵測，利用隱性馬可夫模型辨識正常駕駛、加速、減速、飄移、變換車道、逼近前車這六種行為，後推算出各行為之程度。第二階段則是利用模糊理論來推論駕駛危險程度，搭配綠黃紅三種顏色警示，適時提醒駕駛人注意自己的狀態，確保行車安全。系統實作在TI DM3730雙核心嵌入式平台上，影像處理部分主要以DSP端來處理，周邊感測器控制與使用者圖形介面則在ARM上運行，有效發揮雙核心之優勢。系統驗證則是以實驗車Taiwan iTS-2於高快速道路及平面道路進行實車測試，駕駛行為辨識演算法可達到99%以上之偵測率。最後，在第五章的部分，我們整理了本篇論文的結論與未來的研究展望。

Due to the recent advances in vehicle technology, the intelligent transportation system (ITS) has become one of the important issues in the current studies. Among the researches of ITS, traveler information, vulnerable individual protection, and driving safety become more and more significant in the current days. For the case of tracking technology, a demand-driven architecture for web-based tracking systems is developed with asynchronous JavaScript and XML (AJAX) technology, which can effectively reduce the usage network bandwidth and system loading. For the case of pedestrian navigation, a localization-assistance system using global positioning system (GPS) and wireless sensor networks (WSN) is proposed. The data of GPS and WSN are fused through extended Kalman filter (EKF) to achieve a higher precision localization results for pedestrian navigation. Another critical issue in the ITS is the driving safety. A concept of the driving safety monitoring system is proposed. Seven predefined driving behaviors are recognized using hidden Markov models (HMM), and a danger degree is inferred by a fuzzy inference system (FIS). The driver is warned according to different danger degree to ensure the driving safety. In this dissertation, several algorithmic, practical, and integrated methods and systems are addressed for the above-mentioned applications. Additionally, these applications are implemented on the embedded platform.
In 0, a demand-driven architecture for web-based tracking systems is presented. With the convergence of the Internet and GPS, tracking systems have been developed in many applications such as cargo tracking systems, fleet management, and social networks. By integrating several technologies nowadays, this architecture is designed to improve the efficiency for the web-based tracking systems. The proposed architecture focuses on two problems. One is the redundant connection, causing the waste of bandwidth and fees during the connection period in the mobile network. The other is the data asynchronization during the period of transmission. We not only addressed the connection scheme to solve above issues, but also designed a prototype on an embedded platform for web-based tracking systems. The performance has also been evaluated for the total latency time when a user exploits different communication medium, and the results showed that the user can monitor the status of target in real time even in the worst case.
In Chapter 3, a pedestrian navigation system integrating GPS and WSN is described. Pedestrian navigation services guide people to reach their destinations as vehicle navigation services do. However, the moving way of people differs from vehicles, and the assumptions for vehicle navigation services are not suitable for pedestrian navigation. In some places, the accuracy of GPS is insufficient for pedestrian navigation. In these places, we deploy ZigBee-based sensor networks and call them special interest zones (SIZ). For navigation service, GPS and GIS technologies were used for guiding, and a modified A* algorithm was developed to implement the path planning function. When a user is close to SIZ, a dynamic swap mechanism enables the localization function to provide higher localization results. The localization algorithm using an EKF to fuse the data from ZigBee and GPS and obtain a localization error of less than 1 m, which the error was greatly reduced, compared with ZigBee-only or GPS-only approaches. Both services were successfully implemented on an embedded platform and evaluated on a real environment.
In Chapter 4, a reasoning-based framework for the monitoring of driving safety is proposed. The main objective is to provide drivers with an indicator of their danger level. The system integrates the image-based lane departure warning system, forward collision warning system, 3-axis accelerometer, and GPS, to provide the information of lane bias, the distance to the car in front, speed and longitudinal and lateral accelerations. The proposed framework involves two stages of danger-level alerts. The first stage is to recognize the driving behaviors, including normal driving, acceleration, deceleration, changing to the left lane or right lane, zigzag driving, and approaching the car in front. In addition to recognizing these driving events, the degree of each event is estimated according to its characteristics. In the second stage, the danger-level indicator, which warns the driver of a dangerous situation, is inferred by fuzzy logic rules that address the recognized driving events and their degrees. The proposed framework was successfully implemented on a TI DM3730-based embedded platform and was fully evaluated in a real road environment. The experimental results achieve a detection ratio of 99% for event recognition, compared with that achieved by the four existing methods. Finally, a brief conclusion and future work are given in Chapter 5

中文摘要.......................................i
Abstract.....................................iii
誌謝..........................................vi
Table of Contents............................vii
List of Figures..............................ix
List of Tables...............................xi
Chapter 1. Introduction ..................... 1
1.1 Motivation .............................. 2
1.2 The Proposed Approaches.................. 6
1.2.1 A Demand-Driven Architecture for Web-Based Tracking Systems ........... 6
1.2.2 A Localization-Assistance System using GPS and Wireless Sensor Networks for Pedestrian Navigation ................... 8
1.2.3 A Reasoning-Based Framework for Driving Safety Monitoring using Driving Event Recognition .................. 11
1.3 Organization ............................ 12
Chapter 2. The Demand-Driven Architecture for Web-Based Tracking Systems ...... 15
2.1 System Architecture ..................... 15
2.1.1 Central Management Subsystem (CMS) .... 16
2.1.2 Mobile Tracking Subsystem (MTS)........ 18
2.1.3 Web Monitor Subsystem (WMS) ........... 20
2.1.4 System Interactive Procedures ......... 22
2.2 Prototype and Implementation ............ 26
2.2.1 Prototype Development ................. 26
2.2.2 Functional Services ................... 28
2.2.3 Communication Performance ............. 31
Chapter 3. The Localization-Assistance System using GPS and Wireless Sensor Networks for Pedestrian Navigation ............................................. 34
3.1 System Overview ......................... 34
3.2 System Architecture ..................... 35
3.2.1 Hardware Overview ..................... 35
3.2.2 Software Architecture ................. 39
3.3 Navigation Module ....................... 40
3.3.1 A* Algorithm .......................... 40
3.3.2 A Modified A* Algorithm-Based Path Planning ..................................... 40
3.4 Localization Module ..................... 42
3.4.1 RSSI-Distance Modeling ................ 42
3.4.2 Data Preprocessing..................... 44
3.4.3 Position Estimation ................... 45
3.5 Dynamic Swap Module...................... 46
3.6 Experimental Results .................... 47
Chapter 4. The Reasoning-Based Framework for Driving Safety Monitoring using Driving Event Recognition .................................. 52
4.1 Related Work ............................ 52
4.1.1 The Driver’s States ................... 52
4.1.2 The Vehicle’s States .................. 54
4.1.3 The Hybrid ............................ 55
4.2 System Architecture ..................... 57
4.2.1 Hardware Overview ..................... 57
4.2.2 Software Architecture ................. 60
4.3 Setup of the Vehicle Behavior Model ..... 64
4.4 Driving Event Recognition ............... 66
4.4.1 Data Preprocessing..................... 67
4.4.2 Behavior Recognition .................. 69
4.5 Danger-Level Reasoning................... 71
4.5.1 Degree of Driving Events .............. 71
4.5.2 Design of Fuzzy Danger-Level Model .... 73
4.5.3 Hierarchical Decision Strategy of Fuzzy Rule Selection ......................... 74
4.6 Experimental Results .................... 77
Chapter 5. Conclusions and Future Work ...... 87
5.1 The Demand-Driven Architecture for Web-Based Tracking Systems ................. 87
5.2 The Localization-Assistance System using GPS and Wireless Sensor Networks for Pedestrian Navigation ......................... 88
5.3 The Reasoning-Based Framework for Driving Safety Monitoring using Driving Event Recognition ......................... 88
References .................................. 90

[1]M. A. Al-Taee, O. B. Khader, and N. A. Al-Saber, “Remote monitoring of vehicle diagnostics and location using a smart box with global positioning system and general packet radio service,” in Proc. IEEE Computer Systems and Applications, Amman, 2007, pp. 385–388.
[2]D. W. Ryoo and C. Bae, “Design of the wearable gadgets for life-log services based on UTC,” IEEE Trans. Consumer Electron., vol. 53, pp. 1477–1482, 2007.
[3]H. Lim, J. H. Yang, and Y. S. Lee, “The development of an ubiquitous learning system based on audio augmented reality,” in Proc. IEEE Control, Automation and Systems, Seoul, 2007, pp. 1072–1077.
[4]M. Modsching, R. Kramer, M. Riebeck, A. Stark, K. ten Hagen, and J. Kawalek, “Field trial on the efficiency and user experience of GPS based state of the art navigational systems for pedestrians,” in Proc. Positioning, Navigation and Communication, Hannover, 2007, pp. 129–134.
[5]P. I. Philippopoulos, G. Soulos, A. Krukowski, N. Argyreas, V. Gorgas, D. Kyriazanos, D. I. Axiotis, and S. C. A. Thomopoulos, “ToD: an intelligent location-based transport management system,” in Proc. IEEE Intelligent Vehicles, Istanbul, 2007, pp. 793–798.
[6]S. T. S. Thong, C. T. Han, and T. A. Rahman, “Intelligent fleet management system with concurrent GPS &; GSM real-time positioning technology,” in Proc. ITS Telecommunications, Sophia Antipolis, 2007, pp. 1–6.
[7]A. H. Mazinan, “Specific persons surveillance using satellite technique,” in Proc. Intelligent and Advanced Systems, Kuala Lumpur, 2007, pp. 474–478.
[8]D. Titica, O. Fratu, E. Stanescu, and S. Halunga-Fratu, “Simple location-based application development for mobile phones,” in Proc. Telecommunications in Modern Satellite, Cable and Broadcasting Services, Serbia, 2007, pp. 15–18.
[9]N. Chadil, A. Russameesawang, and P. Keeratiwintakorn, “Real-time tracking management system using GPS, GPRS and Google earth,” in Proc. Electrical Engineering/Electronics, Computer, Telecom. and Information Technology, Krabi, 2008, pp. 393–396.
[10]G. B. Al-Suwaidi and M. J. Zemerly, “Locating friends and family using mobile phones with global positioning system (GPS),” in Proc. Computer Systems and Applications, Rabat, 2009, pp. 555–558.
[11]S. Barbeau, M. A. Labrador, A. Perez, P. Winters, N. Georggi, D. Aguilar, and R. Perez, “Dynamic management of real-time location data on GPS-enabled mobile phones,” in Proc. Mobile Ubiquitous Computing, Systems, Services and Technologies, Valencia, 2008, pp. 343–348.
[12]L. Shen, C. Yang, F. Zhang, Y. Ren, L. Wu, and L. Zhu, “A scalable web GPS monitoring system based on AJAX push pattern,” in Proc. Geoinformatics, Fairfax, VA, 2009, pp. 1–5.
[13]B. F. Wu, Y. H. Chen, C. J. Chen, C. C. Kao, and P. C. Huang, “An efficient web-based tracking system through reduction of redundant connections,” in Proc. Advances in Neural Network Research and Applications, 2010, pp. 671–677.
[14]P. Barsocchi, S. Lenzi, and S. Chessa, “A novel approach to indoor RSSI localization by automatic calibration of the wireless propagation model,” in Proc. IEEE Vehicular Technology, 2009, pp. 1–5.
[15]J. Chen, X. J. Wu, P. Z. Wen, F. Ye, and J. W. Liu, “A new distributed localization algorithm for ZigBee wireless networks,” in Proc. Chinese Control and Decision Conference, 2009, pp. 4451–4456.
[16]H. J. Lee, M. Wicke, B. Kusy, and L. Guibas, “Localization of mobile users using trajectory matching,” in Proc. Mobile Computing and Networking, San Francisco, USA, 2008, pp. 123–128.
[17]M. Mendalka, L. Kulas, and K. Nyka, “Localization in wireless sensor networks based on ZigBee platform,” in Proc. IEEE Microwaves, Radar and Wireless Communications, 2008, pp. 1–4.
[18]S. Yun, J. Lee, Y. Chung, and E. Kim, “Centroid localization method in wireless sensor networks using TSK fuzzy modeling,” in Proc. Advanced Intelligent Systems, 2007, pp. 971–974.
[19]M. A. Quddus, W. Y. Ochieng, and R. B. Noland, “Current map-matching algorithms for transport applications: state-of-the art and future research directions,” Journal of Transportation Research Part C: Emerging Technologies, vol. 15, pp. 312–328, 2007.
[20]X. Yang and H. He, “GPS/DR integrated navigation system based on adaptive robust Kalman filtering,” in Proc. Microwave and Millimeter Wave Technology, 2008, pp. 1946–1949.
[21]E. D. Manley, H. A. Nahas, and J. S. Deogun, “Localization and tracking in sensor systems,” in Proc. Sensor Networks, Ubiquitous, and Trustworthy Computing, 2006, pp. 237–242.
[22]G. Mao, B. Fidan, and B. Anderson, “Wireless sensor network localization techniques,” Journal of Computer Networks, vol. 51, pp. 2529–2553, 2007.
[23]M. Ye, T. Chen, and C. Yu, “ZigBee-based positioning and navigation system for robot,” Journal of Convergence Information Technology, vol. 6, no. 1, pp. 135–146, 2011.
[24]T. Tang, Q. Guo, and M. Yang, “Support vector machine based particle swarm optimization localization algorithm in WSN,” Journal of Convergence Information Technology, vol. 7, no. 1, pp. 497–503, 2012.
[25]M. Sugano, T. Kawazoe, Y. Ohta, and M. Murata, “Indoor localization system using RSSI measurement of wireless sensor network based on Zigbee standard,” in Proc Wireless and Optical Communications, 2006, pp. 503–508.
[26]X. Kuang and H. Shao, “Maximum likelihood localization algorithm using wireless sensor networks,” in Proc. Innovative Computing, Information and Control, 2006, pp. 263–266.
[27]D. Fox, J. Hightower, H. Kauz, L. Liao, and D. Patterson, “Bayesian techniques for location estimation,” in Proc. Location-Aware Computing, 2003, pp. 16–18.
[28]B. Dawes and K. W. Chin, “A comparison of deterministic and probabilistic methods for indoor localization,” Journal of Systems and Software, vol. 84, pp. 442–451, 2011.
[29]M. A. Youssef, A. Agrawala, and A. U. Shankar, “WLAN location determination via clustering and probability distributions”, in Proc. Pervasive Computing and Communications, 2003, pp. 143–150.
[30]L. Zhao, W. Y. Ochieng, M. A. Quddus, and R. B. Noland, “An extended Kalman filter algorithm for integrating GPS and low cost dead reckoning system data for vehicle performance and emissions monitoring,” The Journal of Navigation, vol. 56, pp. 257–275, 2003.
[31]A. Stentz, “Optimal and efficient path planning for partially known environments,” Intelligent Unmanned Ground Vehicles, vol. 388, pp. 203–220, 1997.
[32]P. E. Hart, N. J. Nilsson, and B. Raphael, “A formal basis for the heuristic determination of minimum cost paths,” IEEE Trans. Systems Science and Cybernetics, vol. 4, pp. 100–107, 1968.
[33]T. Stoyanova, F. Kerasiotis, A. Prayati, and G. Papadopoulos, “Evaluation of impact factors on RSS accuracy for localization and tracking applications,” in Proc. Mobility Management and Wireless Access, 2007, pp. 9–16.
[34]T. Gandhi and M. M. Trivedi, “Vehicle surround capture: survey of techniques and a novel omni-video-based approach for dynamic panoramic surround maps,” IEEE Trans. Intelligent Transportation Systems, vol. 7, pp. 293–308, 2006.
[35]G. Yang, Y. Lin, and P. Bhattacharya, “A driver fatigue recognition model based on information fusion and dynamic Bayesian network,” Information Sciences, vol. 180, pp. 1942–1954, 2010.
[36]T. D’Orazio, M. Leo, C. Guaragnella, and A. Distante, “A visual approach for driver inattention detection,” Pattern Recognition, vol. 40, pp. 2341–2355, 2007.
[37]S. Zehang, G. Bebis, and R. Miller, “On-road vehicle detection: a review,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, pp. 694–711, 2006.
[38]J. C. McCall and M. M. Trivedi, “Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation,” IEEE Trans. Intelligent Transportation Systems, vol. 7, pp. 20–37, 2006.
[39]C. M. Feng, “Road accidents profile in Taiwan,” Journal of International Association of Traffic and Safety Sciences, vol. 31, no.1, pp. 138–139, 2007.
[40]T. Ehlgen, T. Pajdla, and D. Ammon, “Eliminating blind spots for assisted driving,” IEEE Trans. Intelligent Transportation Systems, vol. 9, pp. 657–665, 2008.
[41]T. Gandhi and M. M. Trivedi, “Vehicle surround capture: survey of techniques and a novel omni-video-based approach for dynamic panoramic surround maps,” IEEE Trans. Intelligent Transportation Systems, vol. 7, pp. 293–308, 2006.
[42]V. Kastrinaki, M. Zervakis, and K. Kalaitzakis, “A survey of video processing techniques for traffic applications,” Image and Vision Computing, vol. 21, pp. 359–381, 2003.
[43]Y. Dong, Z. Hu, K. Uchimura, and N. Murayama, “Driver inattention monitoring system for intelligent vehicles: A review,” IEEE Trans. Intelligent Transportation Systems, vol. 12, pp. 596–614, 2011.
[44]A. Doshi and M. M. Trivedi, “Tactical driver behavior prediction and intent inference: A review,” in Proc. IEEE Intelligent Transportation Systems, 2011, pp. 1892–1897.
[45]B. Atsumi, “Evaluation of mental condition on drivers by analysis of heart rate variability: measurement of mental stress and drowsiness by indexes of autonomic nervous system,” JSAE Review, vol. 16, pp. 110–110, 1995.
[46]K. Jiao, Z. Li, M. Chen, C. Wang, and S. Qi, “Effect of different vibration frequencies on heart rate variability and driving fatigue in healthy drivers,” International Archives of Occupational and Environmental Health, vol. 77, pp. 205–212, 2004.
[47]B. T. Jap, S. Lal, P. Fischer, and E. Bekiaris, “Using EEG spectral components to assess algorithms for detecting fatigue,” Expert Systems with Applications, vol. 36, pp. 2352–2359, 2009.
[48]M. V. M. Yeo, X. Li, K. Shen, and E. P. V. Wilder-Smith, “Can SVM be used for automatic EEG detection of drowsiness during car driving?” Safety Science, vol. 47, pp. 115–124, 2009.
[49]K. Q. Shen, X. P. Li, C. J. Ong, S. Y. Shao, and E. P. V. Wilder-Smith, “EEG-based mental fatigue measurement using multi-class support vector machines with confidence estimate,” Clinical Neurophysiology, vol. 119, pp. 1524–1533, 2008.
[50]C. T. Lin, R. C. Wu, S. F. Liang, W. H. Chao, Y. J. Chen, and T. P. Jung, “EEG-based drowsiness estimation for safety driving using independent component analysis,” IEEE Trans. Circuits and Systems I: Regular Papers, vol. 52, pp. 2726–2738, 2005.
[51]C. P. Chua, G. McDarby, and C. Heneghan, “Combined electrocardiogram and photoplethysmogram measurements as an indicator of objective sleepiness,” Physiological Measurement, vo1. 29, pp.857–868, 2008.
[52]S. K. L. Lal and A. Craig, “A critical review of the psychophysiology of driver fatigue,” Biological Psychology, vol. 55, pp. 173–194, 2001.
[53]G. Yang, Y. Lin, and P. Bhattacharya, “A driver fatigue recognition model based on information fusion and dynamic Bayesian network,” Information Sciences, vol. 180, pp. 1942–1954, 2010.
[54]L. M. Bergasa, J. Nuevo, M. A. Sotelo, R. Barea, and M. E. Lopez, “Real-time system for monitoring driver vigilance,” IEEE Trans. Intelligent Transportation Systems, vol. 7, pp. 63–77, 2006.
[55]Q. Ji and X. Yang, “Real-time eye, gaze, and face pose tracking for monitoring driver vigilance,” Real-Time Imaging, vol. 8, pp. 357–377, 2002.
[56]Q. Ji and X. Yang, “Real time visual cues extraction for monitoring driver vigilance,” Computer Vision Systems, vol. 2095, pp. 107–124, 2001.
[57]L. Yulan, M. L. Reyes, and J. D. Lee, “Real-time detection of driver cognitive distraction using support vector machines,” IEEE Trans. Intelligent Transportation Systems, vol. 8, pp. 340–350, 2007.
[58]A. B. Albu, B. Widsten, W. Tiange, J. Lan, and J. Mah, “A computer vision-based system for real-time detection of sleep onset in fatigued drivers,” in Proc. IEEE Intelligent Vehicles Symposium, 2008, pp. 25–30.
[59]J. Qiang, Z. Zhiwei, and P. Lan, “Real-time nonintrusive monitoring and prediction of driver fatigue,” IEEE Trans.Vehicular Technology, vol. 53, pp. 1052–1068, 2004.
[60]H. Ueno, M. Kaneda, and M. Tsukino, “Development of drowsiness detection system,” in Proc. Vehicle Navigation and Information Systems Conference, 1994, pp. 15–20.
[61]F. Friedrichs and B. Yang, “Drowsiness monitoring by steering and lane data based features under real driving conditions,” in Proc. European Signal Processing Conference, 2010, pp. 209–213.
[62]Y. J. Zhong, L. P. Du, K. Zhang, and X. H. Sun, “Localized energy study for analyzing driver fatigue state based on wavelet analysis,” in Proc. Wavelet Analysis and Pattern Recognition, vol. 4, 2007, pp. 1843–1846.
[63]K. Torkkola, N. Massey, and C. Wood, “Driver inattention detection through intelligent analysis of readily available sensors,” in Proc. IEEE Intelligent Transportation Systems, 2004, pp. 326–331.
[64]A. Eskandarian and A. Mortazavi, “Evaluation of a smart algorithm for commercial vehicle driver drowsiness detection,” in Proc. Intelligent Vehicles, 2007, pp. 553–559.
[65]S. Zehang, G. Bebis, and R. Miller, “On-road vehicle detection: a review,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, pp. 694–711, 2006.
[66]J. C. McCall and M. M. Trivedi, “Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation,” IEEE Trans. Intelligent Transportation Systems, vol. 7, pp. 20–37, 2006.
[67]Y. Liu, Z. Han, Z. Zhang, and J. Jiao, “Video-based hazardous event detection in the driving environment,” in Proc. Engineering Management, 2009, pp. 736–740.
[68]K. Inata, P. Raksincharoensak, and M. Nagai, “Driver behavior modeling based on database of personal mobility driving in urban area,” in Proc. International Conference on Control, Automation and System, 2008, pp. 2902–2907.
[69]Y. R. Huang, “Real time dangerous driving status detection,” in Proc. International Congress on Image and Signal Processing, vol. 1, 2011, pp. 414–418.
[70]Y. Zhou, W. Xu, H. Ning, Y. Gong, and T. Huang, “Detecting unsafe driving patterns using discriminative learning,” in Proc. IEEE International Conference on Multimedia and Expo, 2007, pp. 1431–1434.
[71]H. Ning, W. Xu, Y. Zhou, Y. Gong, and T. Huang, “A general framework to detect unsafe system states from multisensor data stream,” IEEE Trans. Intelligent Transportation Systems, vol. 11, no. 1, pp. 4–15, 2010.
[72]J. Wang, S. Zhu, and Y. Gong, “Driving safety monitoring using semisupervised learning on time series data,” IEEE Trans. Intelligent Transportation Systems, vol. 11, no. 3, pp. 728–737, 2010.
[73]G. S. Aoude, V. R. Desaraju, L. H. Stephens, and J. P. How, “Driver behavior classification at intersections and validation on large naturalistic data set,” IEEE Trans. Intelligent Transportation Systems, vol. 13, pp. 724–736, 2012.
[74]S. Sekizawa, S. Inagaki, T. Suzuki, S. Hayakawa, N. Tsuchida, T. Tsuda, and H. Fujinami, “Modeling and recognition of driving behavior based on stochastic switched ARX model,” IEEE Trans. Intelligent Transportation Systems, vol. 8, pp. 593–606, 2007.
[75]A. Sathyanarayana, S. Nageswaren, H. Ghasemzadeh, R. Jafari, and J.H. Hansen, “Body sensor networks for driver distraction identification,” in Proc. IEEE ICVES, 2008, pp. 120–125.
[76]J. C. McCall and M. M. Trivedi, “Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation,” IEEE Trans. Intelligent Transportation Systems, vol. 7, pp. 20–37, 2006.
[77]C. J. Chen, H. Y. Peng, B. F. Wu, and Y. H. Chen, “A real-time driving assistance and surveillance system,” Journal of Information Science and Engineering, vol. 25, pp. 1501–1523, 2009.
[78]B. F. Wu, Y. H. Chen, C. C. Kao, Y. F. Li, and C. J. Chen, “A vision-based collision warning system by surrounding vehicles detection,” KSII Trans. Internet and Information Systems, vol. 6, pp. 1203–1222, 2012.
[79]L. E. Baum and T. Petrie, “Statistical inference for probabilistic functions of finite state Markov chains,” Ann. Math. Stat., vol. 37, pp. 1554–1563, 1966.
[80]L. R. Rabiner, “A tutorial on hidden Markov models and selected applications in speech recognition,” in Proc. IEEE, vol. 77, no. 2, pp. 257–286, 1989.
[81]L. A. Zadeh, “Fuzzy sets,” Information and Control, vol. 8, pp. 338–353, 1965.