駕駛員疲勞特征提取方法的研究及檢測系統(tǒng)的設計
發(fā)布時間：2018-07-27 12:06
【摘要】：在經(jīng)濟與科技發(fā)展的推動作用下,越來越多的上班族以汽車作為交通工具,這樣既方便了出行又節(jié)省了時間。但是,道路上出現(xiàn)的事故伴隨著汽車的普遍應用也出現(xiàn)了井噴式的增長。根據(jù)調(diào)查研究與科學統(tǒng)計,在發(fā)生交通事故的各種原因中,疲勞駕駛成為主要原因。盡管如此,由于檢測技術及軟件處理的不成熟與不完善,使得檢測駕駛員疲勞程度的產(chǎn)品還不能得到廣泛的引用,從而沒能減輕甚至杜絕類似交通事故的發(fā)生,造成了不可估量的生命與財產(chǎn)的損失。本文以此為背景,并對行車過程中出現(xiàn)疲勞狀況時的面部表現(xiàn)進行觀察和分析,提取出疲勞面部信息,結合面部檢測及多特征處理技術,設計了能檢測疲勞狀態(tài)的系統(tǒng),并在系統(tǒng)上完成了算法驗證。此系統(tǒng)包括人臉檢測、疲勞特征提取和疲勞狀態(tài)判斷三個部分。其中,提取的面部特征有三個:眼睛特征、頭部特征和嘴部特征。文中首先對系統(tǒng)的需求和工作流程進行了分析,然后對各部分采用的算法進行了論述。在檢測之初,本文先采用了Adaboost算法,在計算出人臉Haar特征之后用于人臉的檢測。在算法的使用中發(fā)現(xiàn),其速度和對傾斜時人臉的檢測有很多不足。因此,在后期引入了KCF跟蹤算法,并把這兩者進行結合,在應用對比后發(fā)現(xiàn),此改進無論在時間上還是對傾斜人臉的檢測上,都有相當大的提升。然后,論述了眼睛特征提取、頭部特征提取和嘴部特征提取的方法:在提取眼睛狀態(tài)的時候,首先根據(jù)先驗知識確定眼睛子窗口,進行二值化處理之后利用灰度積分投影分別提取出單個眼睛窗口,并求出各眼睛區(qū)域的最小的外接矩形,以矩形面積大小確定眼睛狀態(tài);提取嘴部狀態(tài)時,根據(jù)先驗知識提取出鼻孔和嘴部區(qū)域,并針對傳統(tǒng)Canny邊緣檢測存在的不足采用自適應邊緣檢測算法得到鼻孔和嘴部輪廓,根據(jù)鼻孔到上下嘴唇間距離的比值確定出嘴巴的狀態(tài);對頭部特征的確定則是根據(jù)人臉矩形框坐標位置的變化得出的。在對疲勞特征提取算法進行論述之后,介紹了疲勞狀態(tài)判定的方法,針對利用單特征進行疲勞檢測存在的不足,提出融合眼睛特征、嘴部特征和頭部特征進行檢測的方法,該方法提高了檢測的正確率。本文在實驗室通過VS開發(fā)環(huán)境設計了疲勞駕駛檢測系統(tǒng),并在此系統(tǒng)上分別對采用單特征的疲勞檢測和多特征融合的疲勞檢測方法進行實驗驗證,結果表明:本文提出的融合多特征的疲勞檢測方法在準確率上有了明顯的提高。
[Abstract]:Driven by the development of economy and technology, more and more commuters use cars as means of transportation, which not only facilitates travel but also saves time. However, accidents on the road accompanied by the widespread use of cars also appeared blowout growth. According to investigation and scientific statistics, fatigue driving is the main cause of traffic accidents. However, due to the immaturity and imperfection of detection technology and software processing, the products used to detect drivers' fatigue degree can not be widely used, which can not reduce or even eliminate the occurrence of similar traffic accidents. Resulting in incalculable loss of life and property. Based on this background, this paper observed and analyzed the facial performance of fatigue state in the course of driving, extracted the fatigue facial information, combined with facial detection and multi-feature processing technology, designed a system to detect fatigue state. The algorithm is verified on the system. The system includes face detection, fatigue feature extraction and fatigue state judgment. Among them, there are three facial features extracted: eye features, head features and mouth features. In this paper, the requirements and workflow of the system are analyzed firstly, and then the algorithms used in each part are discussed. At the beginning of detection, Adaboost algorithm is used to detect face after Haar feature is calculated. In the use of the algorithm, it is found that there are many shortcomings in the speed and face detection of tilt. Therefore, the KCF tracking algorithm is introduced in the later period, and the two algorithms are combined. After application comparison, it is found that the improvement has a considerable improvement in both the time and the tilt face detection. Then, the methods of eye feature extraction, head feature extraction and mouth feature extraction are discussed. After binary processing, the single eye window is extracted by gray integral projection, and the smallest external rectangle of each eye region is obtained. The state of the eye is determined by the size of the rectangle area, and the state of the mouth is extracted. According to the prior knowledge, the nostril and mouth regions are extracted, and the adaptive edge detection algorithm is adopted to get the nostril and mouth contours according to the shortcomings of traditional Canny edge detection, and the state of the mouth is determined according to the ratio of the distance between the nostrils and the upper and lower lips. The determination of the head feature is based on the change of the coordinate position of the face rectangular frame. After discussing the algorithm of fatigue feature extraction, the method of fatigue state determination is introduced. Aiming at the shortcomings of fatigue detection using single feature, the method of combining eye feature, mouth feature and head feature is put forward. This method improves the accuracy of detection. In this paper, the fatigue driving detection system is designed in the lab by using vs development environment, and the fatigue detection method using single feature and multi-feature fusion is verified by experiments on this system. The results show that the proposed fatigue detection method with multiple features has a better accuracy.
【學位授予單位】：電子科技大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：U463.6;U495;TP391.41
本文編號：2147770
[Abstract]:Driven by the development of economy and technology, more and more commuters use cars as means of transportation, which not only facilitates travel but also saves time. However, accidents on the road accompanied by the widespread use of cars also appeared blowout growth. According to investigation and scientific statistics, fatigue driving is the main cause of traffic accidents. However, due to the immaturity and imperfection of detection technology and software processing, the products used to detect drivers' fatigue degree can not be widely used, which can not reduce or even eliminate the occurrence of similar traffic accidents. Resulting in incalculable loss of life and property. Based on this background, this paper observed and analyzed the facial performance of fatigue state in the course of driving, extracted the fatigue facial information, combined with facial detection and multi-feature processing technology, designed a system to detect fatigue state. The algorithm is verified on the system. The system includes face detection, fatigue feature extraction and fatigue state judgment. Among them, there are three facial features extracted: eye features, head features and mouth features. In this paper, the requirements and workflow of the system are analyzed firstly, and then the algorithms used in each part are discussed. At the beginning of detection, Adaboost algorithm is used to detect face after Haar feature is calculated. In the use of the algorithm, it is found that there are many shortcomings in the speed and face detection of tilt. Therefore, the KCF tracking algorithm is introduced in the later period, and the two algorithms are combined. After application comparison, it is found that the improvement has a considerable improvement in both the time and the tilt face detection. Then, the methods of eye feature extraction, head feature extraction and mouth feature extraction are discussed. After binary processing, the single eye window is extracted by gray integral projection, and the smallest external rectangle of each eye region is obtained. The state of the eye is determined by the size of the rectangle area, and the state of the mouth is extracted. According to the prior knowledge, the nostril and mouth regions are extracted, and the adaptive edge detection algorithm is adopted to get the nostril and mouth contours according to the shortcomings of traditional Canny edge detection, and the state of the mouth is determined according to the ratio of the distance between the nostrils and the upper and lower lips. The determination of the head feature is based on the change of the coordinate position of the face rectangular frame. After discussing the algorithm of fatigue feature extraction, the method of fatigue state determination is introduced. Aiming at the shortcomings of fatigue detection using single feature, the method of combining eye feature, mouth feature and head feature is put forward. This method improves the accuracy of detection. In this paper, the fatigue driving detection system is designed in the lab by using vs development environment, and the fatigue detection method using single feature and multi-feature fusion is verified by experiments on this system. The results show that the proposed fatigue detection method with multiple features has a better accuracy.
【學位授予單位】：電子科技大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：U463.6;U495;TP391.41
【參考文獻】
相關期刊論文 前10條
1 張雷;王延杰;劉艷瀅;孫宏海;何舒文;;基于相關濾波器的視覺目標跟蹤方法[J];光電子·激光;2015年07期
2 張欣婷;;血液酒精濃度對駕駛行為的影響研究[J];交通標準化;2014年23期
3 咼騰;馮桑;黃超;;基于生物電信號的駕駛疲勞檢測方法[J];汽車電器;2014年08期
4 王斐;王少楠;王惜慧;彭瑩;楊乙丁;;基于腦電圖識別結合操縱特征的駕駛疲勞檢測[J];儀器儀表學報;2014年02期
5 武瑛;;形態(tài)學圖像處理的應用[J];計算機與現(xiàn)代化;2013年05期
6 盛杰;鮑小軍;李博;;基于駕駛疲勞報警系統(tǒng)的研究[J];民營科技;2013年03期
7 宋曙光;;圖像邊緣檢測算法研究與分析[J];光機電信息;2010年09期
8 熊運霞;苗德華;馬林昌;郭世杰;鄧三鵬;;汽車駕駛員疲勞監(jiān)測技術研究現(xiàn)狀及發(fā)展趨勢[J];天津工程師范學院學報;2009年02期
9 許少凡;李凱鈿;狄紅衛(wèi);劉卓健;;基于瞳孔幾何特征的駕駛疲勞檢測嵌入式系統(tǒng)的設計[J];光學技術;2009年01期
10 李世進;;數(shù)字圖像的平滑處理[J];湖南科技學院學報;2008年12期
相關碩士學位論文 前10條
1 譚桂玲;基于多源信息融合的駕駛員疲勞預警技術研究[D];天津職業(yè)技術師范大學;2015年
2 柳露艷;駕駛員疲勞駕駛檢測系統(tǒng)的研究與實現(xiàn)[D];東華大學;2014年
3 蔣友毅;基于多特征的疲勞駕駛檢測系統(tǒng)的設計與實現(xiàn)[D];華中科技大學;2013年
4 沈進華;公共車輛安全營運調(diào)度管理系統(tǒng)的設計與實現(xiàn)[D];復旦大學;2012年
5 陳明初;基于人眼狀態(tài)的駕駛員疲勞檢測技術研究[D];重慶大學;2012年
6 劉三國;圖像銳化的研究[D];曲阜師范大學;2011年
7 趙有靈;基于計算機視覺的機車乘務員駕駛疲勞監(jiān)測研究[D];國防科學技術大學;2010年
8 王曉玉;基于圖像處理的駕駛員疲勞檢測方法研究[D];東北大學;2010年
9 柯明君;駕駛員疲勞視頻監(jiān)測系統(tǒng)設計與關鍵技術研究[D];國防科學技術大學;2008年
10 茅泉泉;基于統(tǒng)計理論的人臉檢測方法的研究[D];東南大學;2006年
，本文編號：2147770
本文鏈接：http://sikaile.net/kejilunwen/daoluqiaoliang/2147770.html
