本文關鍵詞： 人臉檢測 狀態(tài)識別 CNN PERCLOS 疲勞檢測　出處：《天津工業(yè)大學》2017年碩士論文　論文類型：學位論文

【摘要】：近年來交通事故頻發(fā),給國家和個人帶來了嚴重的財產(chǎn)損失。研究表明,疲勞駕駛是目前引發(fā)交通事故的主要原因之一,已經(jīng)引起許多國家和政府的重視,因此準確快速的駕駛員疲勞檢測的研究具有重要的意義。基于機器視覺的檢測方法以其非接觸性、實時性等優(yōu)點,成為駕駛員疲勞檢測的一個重要方法。眼睛和嘴部等狀態(tài)的檢測是疲勞檢測方法中的重要步驟,但是墨鏡遮擋及光照變化會對其產(chǎn)生影響。針對以上問題,本文使用紅外采集設備對駕駛員面部圖像進行采集,提出一種基于面部行為分析的駕駛員疲勞檢測方法,其中主要研究內(nèi)容包含人臉檢測及跟蹤、眼睛和嘴部區(qū)域檢測、面部狀態(tài)識別及疲勞檢測等。首先,通過基于AdaBoost的檢測檢測算法進行駕駛員面部檢測,為了提高檢測速度及準確率,本文結合基于KCF(Kernelized Correlation Filter)的跟蹤算法,對檢測到的人臉區(qū)域進行快速跟蹤;其次,通過級聯(lián)回歸的方法定位面部關鍵點,根據(jù)關鍵點位置提取眼睛和嘴部區(qū)域;最后,采用CNN(Convolution Neural Network)網(wǎng)絡模型對提取出的眼睛和嘴部區(qū)域進行狀態(tài)識別,得到眼睛和嘴部狀態(tài)后,計算 PERCLOS(Percentage of Eyelid Closure Over the Pupil Over Time)、眨眼頻率及打哈欠參數(shù)等,通過結合多個疲勞參數(shù)對駕駛員的疲勞狀態(tài)進行檢測。實驗結果表明,該方法在佩戴墨鏡情況下能夠更準確的檢測眼睛和嘴部狀態(tài),進而得到更準確的疲勞參數(shù)。與僅采用PERCLOS參數(shù)的方法相比,通過結合多個疲勞參數(shù)能夠得到更為準確的結果。
[Abstract]:The frequent occurrence of traffic accidents in recent years has brought serious property losses to countries and individuals. Studies show that fatigue driving is one of the main causes of traffic accidents at present and has attracted the attention of many countries and governments. Therefore, the research of accurate and fast driver fatigue detection is of great significance. The detection method based on machine vision has the advantages of non-contact, real-time and so on. The detection of eye and mouth is an important step in the fatigue detection method, but sunglasses occlusion and light change will have an impact on it. In this paper, the driver's facial images are collected with infrared acquisition equipment, and a driver fatigue detection method based on facial behavior analysis is proposed. The main research contents include face detection and tracking, eye and mouth region detection. First of all, the driver face detection is carried out through the detection algorithm based on AdaBoost. In order to improve the detection speed and accuracy, this paper combines the tracking algorithm based on KCF(Kernelized Correlation filter. The detected face region is tracked quickly. Secondly, the key points of the face are located by cascading regression, and the eye and mouth regions are extracted according to the key points. Finally, The CNN(Convolution Neural network model was used to recognize the state of the extracted eye and mouth regions, and then the PERCLOS(Percentage of Eyelid Closure Over the Pupil Over time, blink frequency and yawning parameters were calculated. The test results show that the method can detect the state of eyes and mouth more accurately in the case of wearing sunglasses. More accurate fatigue parameters can be obtained, and more accurate results can be obtained by combining multiple fatigue parameters compared with the method using only PERCLOS parameters.
【學位授予單位】：天津工業(yè)大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：U463.6;TP391.41

【參考文獻】

相關期刊論文 前8條

1 余禮楊;范春曉;明悅;;改進的核相關濾波器目標跟蹤算法[J];計算機應用;2015年12期

2 李月龍;靳彥;汪劍鳴;肖志濤;耿磊;;人臉特征點提取方法綜述[J];計算機學報;2016年07期

3 姚勝;李曉華;張衛(wèi)華;周激流;;基于LBP的眼睛開閉檢測方法[J];計算機應用研究;2015年06期

4 秦華標;李雪梅;仝錫民;黃宇駒;;復雜環(huán)境下基于多特征決策融合的眼睛狀態(tài)識別[J];光電子.激光;2014年04期

5 毛U，

本文編號：1535119