基於深度信念網絡之疲勞駕駛監測系統

Drowsy Driver Detection Systems with Deep Belief Networks

翁景華(Weng, Ching Hua)

指導教授 ： 賴尚宏

國立清華大學/電機資訊學院/資訊工程學系/碩士(2015年)

https://doi.org/10.6843/NTHU.2015.00335

摘要

疲勞駕駛是引發交通事故的重要因素之一，而疲勞駕駛監測系統是防範並降低交通安全的危害。在目前的研究中，多數系統是以單一疲勞特徵來斷定駕駛的疲勞程度，此方法難以應用在複雜的環境裡；而目前更大的問題是缺乏一個標準且齊的資料庫，因此無法公平地評估疲勞監測系統的好壞。
此篇論文提出了兩個疲勞駕駛監測系統: 離散化組件深度信念網絡和多層次時間性深度信念網絡。在離散化組件深度信念網絡中，幾個疲勞特徵會先被抓取並且收集更細部的資訊來組成多個組件，離散化的組件接著會隨著時間相加，平均之後將資料輸入至深度信念網路的可見層，最後再加softmax函式去估測駕駛的疲勞程度。而在多層次時間性深度信念網絡中，幾個疲勞特徵(打哈欠，點頭和閉眼)會先用深度信念網絡來偵測，並以Hash方法來形成可觀察的輸出，接著在網絡上層有兩個隱馬可夫模型用來描述時間資訊以及描述疲勞特徵之間的互動關係，最後將隱馬可夫模型產生的估計值相減並隨著時間相加後，輸入至S型函數來判斷駕駛的疲勞程度。
為了解決資料庫問題與評估系統的能力，我們也收集了模擬疲勞駕駛的影片資料庫。影片囊括不同膚色的人、姓別、環境光亮程度以及開車時況，目的是希望可以達到資料庫的多樣性與可信度。最後我們將提出的兩個系統用收集好的資料庫去做測試與分析，實驗結果與幾個示範証實系統的實用性。

關鍵字

疲勞駕駛偵測 ； 離散隱馬可夫模型 ； 深度信念網絡 ； 臉部特徵點偵測 ； 車輛主動式安全防護

並列摘要

Drowsy driver alert systems have been developed to reduce and prevent car accidents. Existing vision-based systems are usually restricted to using visual cues, and they usually depend on tedious parameter tuning or cannot work under general conditions. One additional crucial issue is the lack of public datasets that can be used to evaluate the performance of different methods. In this thesis, we develop two novel systems, i.e. a Component-wise Discretized Deep Belief Network (CDDBN) system and a novel Hierarchical Temporal Deep Belief Network (HTDBN) system, for drowsy driver detection.
In CDDBN, after detecting drowsiness-related symptoms using traditional DHMMs and SVM, detailed facial feature are computed to construct several discretized components. The input visible units for DBN are formed by the average of the discretized vectors over a time duration and the softmax layer at the last hidden layer of DBN is to predict the level of drowsiness. In HTDBN, our scheme first extracts high-level facial and head feature representations and then uses them to recognize drowsiness-related symptoms. Two discrete-hidden Markov models that utilize a hash-based scheme are constructed on top of the DBNs. They are used to model and capture the interactive relations between eyes, mouth and head motions. Finally, the summed difference of DHMM likelihoods is used to determine the drowsiness level. To evaluate the performance of the drowsy driver detection systems, we also collect a large comprehensive video dataset containing driver videos of various ethnicities, genders, lighting conditions and driving scenarios. Experimental results demonstrate the feasibility of the proposed CDDBN and HTDBN framework for detecting drowsiness based on different visual cues.

並列關鍵字

Drowsy Driver Detection ； Discrete Hidden Markov Model ； Deep Belief Network ； Facial Landmark Detection ； Vehicle Active Safety

參考文獻

[2]. W. H. Organization. Global status report on road safety 2013: Supporting a decade of action: Summary, 2013. World Health Organization.

[4]. M.L. Jackson, R.J. Croft, G.A. Kennedy, K. Owens and M.E. Howard. Cognitive components of simulated driving performance: Sleep loss effects and predictors. Accident Analysis & Prevention, 50:438–444, Jan. 2013.

[5]. N. S. Foundation. Drowsy driving reduction act of 2015, 2014.

[8]. I. Teyeb, O. Jemai, M. Zaied, and C. Ben Amar. A drowsy driver detection system based on a new method of head posture estimation. Intelligent Data Engineering and Automated Learning, 8669:362–369, 2014.

[9]. Q. Ji, P. Lan, and C. Looney. A probabilistic framework for modeling and real-time monitoring human fatigue. IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, 36(5):862–875, Sept 2006.