本文選題：深度學(xué)習(xí) + 卷積神經(jīng)網(wǎng)絡(luò)　； 參考：《廣東技術(shù)師范學(xué)院》2017年碩士論文

【摘要】：卷積神經(jīng)網(wǎng)絡(luò)是一種源于人工神經(jīng)網(wǎng)絡(luò)的深度學(xué)習(xí)方法。它具有局部連接、權(quán)值共享的特點(diǎn),同時能夠?qū)崿F(xiàn)特征的自動提取,它改善了傳統(tǒng)模式識別方法中特征提取難的問題,因此卷積神經(jīng)網(wǎng)絡(luò)廣泛應(yīng)用于自然語言處理、語音識別、推薦系統(tǒng)、計(jì)算機(jī)視覺等領(lǐng)域�；隈{駛員外部特征的疲勞駕駛檢測技術(shù)在多個方面取得了一定的進(jìn)展,但是駕駛員臉部特征提取的方法有待進(jìn)一步提高,同時駕駛員眼睛定位的時間較長,影響系統(tǒng)識別速率。論文將卷積神經(jīng)網(wǎng)絡(luò)應(yīng)用于人臉識別,對瞳孔定位算法進(jìn)行改進(jìn),有效地克服了原算法計(jì)算量大的問題,根據(jù)駕駛員眼睛在不同狀態(tài)下寬與高比例不同的特點(diǎn),實(shí)現(xiàn)了一種簡單可行的眼睛狀態(tài)判斷方法,并通過PERCLOS算法對駕駛員的疲勞狀態(tài)進(jìn)行判定。應(yīng)用卷積神經(jīng)網(wǎng)絡(luò)模型對ORL人臉庫實(shí)驗(yàn)得到識別率為85%,識別平均時間為20ms。改進(jìn)的Hough變換方法對駕駛員眼睛的定位準(zhǔn)確率和平均時間分別為92%和29ms,對駕駛員眼睛狀態(tài)的判斷正確率為83.9%。論文使用的疲勞駕駛檢測方法能比傳統(tǒng)的檢測方法取得更好的效果,設(shè)計(jì)基于人臉識別的疲勞駕駛檢測原型系統(tǒng),實(shí)現(xiàn)了駕駛員臉部特征檢測、眼睛定位、眼睛狀態(tài)判斷、疲勞判定等功能。實(shí)驗(yàn)結(jié)果表明,系統(tǒng)對疲勞的識別率為87.5%,疲勞判斷的響應(yīng)時間為17ms,有較好的實(shí)際應(yīng)用價值。
[Abstract]:Convolutional neural network is a kind of deep learning method derived from artificial neural network.It has the characteristics of local connection, weight sharing and automatic feature extraction. It improves the difficulty of feature extraction in traditional pattern recognition methods. Therefore, convolution neural network is widely used in natural language processing and speech recognition.Recommendation system, computer vision and other fields.Fatigue driving detection technology based on driver's external features has made some progress in many aspects, but the method of driver's facial feature extraction needs to be further improved, and the driver's eye location time is longer.It affects the recognition rate of the system.In this paper, the convolution neural network is applied to face recognition, and the pupillary location algorithm is improved, which effectively overcomes the problem that the original algorithm has a large amount of computation. According to the characteristics of the driver's eyes in different states, the width and the proportion of the eyes are different.A simple and feasible method for judging eye state is implemented, and the fatigue state of driver is judged by PERCLOS algorithm.By using convolutional neural network model, the recognition rate of ORL face database is 85% and the average recognition time is 20 Ms.The accuracy and average time of the improved Hough transform for eye localization are 92% and 29 msrespectively, and the correct rate for judging the eye state of the driver is 83.9%.The fatigue driving detection method used in this paper can achieve better results than the traditional detection method. A prototype system of fatigue driving detection based on face recognition is designed, which realizes driver's face feature detection, eye location, eye state judgment.Fatigue judgment and other functions.The experimental results show that the fatigue recognition rate of the system is 87.5 and the response time of fatigue judgment is 17mswhich has good practical application value.
【學(xué)位授予單位】：廣東技術(shù)師范學(xué)院
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 耿新,周志華,陳世福;基于混合投影函數(shù)的眼睛定位[J];軟件學(xué)報(bào);2003年08期

2 石堅(jiān),吳遠(yuǎn)鵬,卓斌,馬勇,許曉鳴;汽車駕駛員主動安全性因素的辨識與分析[J];上海交通大學(xué)學(xué)報(bào);2000年04期

3 王榮本,郭克友,儲江偉;一種基于Gabor小波的駕駛員眼部狀態(tài)識別方法的研究[J];中國圖象圖形學(xué)報(bào);2003年09期

4 鄭培,宋正河,周一鳴;基于PERCLOS的機(jī)動車駕駛員駕駛疲勞的識別算法[J];中國農(nóng)業(yè)大學(xué)學(xué)報(bào);2002年02期

5 葛如海;陳彥博;劉志強(qiáng);;基于計(jì)算機(jī)視覺的駕駛疲勞識別方法的研究[J];中國安全科學(xué)學(xué)報(bào);2006年09期

6 楊英;楊佳;盛敬;;基于膚色的駕駛員面部定位與跟蹤算法[J];東北大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年01期

7 顧佳玲;彭宏京;;增長式卷積神經(jīng)網(wǎng)絡(luò)及其在人臉檢測中的應(yīng)用[J];系統(tǒng)仿真學(xué)報(bào);2009年08期

8 郭永彩;李文濤;高潮;;基于PERCLOS的駕駛員疲勞檢測算法[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2009年08期

9 張希波;成波;馮睿嘉;;基于方向盤操作的駕駛?cè)似跔顟B(tài)實(shí)時檢測方法[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年07期

10 徐來;周德龍;;人眼檢測技術(shù)的方法研究[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2010年06期

相關(guān)碩士學(xué)位論文 前3條

1 陶勤勤;基于卷積神經(jīng)網(wǎng)絡(luò)和改進(jìn)支持向量機(jī)的人臉檢測[D];合肥工業(yè)大學(xué);2016年

2 張子夫;基于卷積神經(jīng)網(wǎng)絡(luò)的目標(biāo)跟蹤算法研究與實(shí)現(xiàn)[D];吉林大學(xué);2015年

3 夏阿南;基于人眼動態(tài)特性的駕駛疲勞檢測方法研究[D];大連海事大學(xué);2014年

，

本文編號：1731610