{"title":"基于眼动信号的机动车驾驶员疲劳评价","authors":"Xing Liu, Lecai Cai, Zhiming Wu, Shaosong Duan, Keyuan Tang, Chaoyang Zhang","doi":"10.1109/ICCEAI52939.2021.00018","DOIUrl":null,"url":null,"abstract":"Fatigue driving is one of the main causes of traffic accidents, and it has a great impact on road safety. One of the most effective fatigue driving detection methods is based on the machine vision using the characteristics of driver's eye. However, this accuracy of the method is influenced by the light environment during driving. In order to address the problem, a method is proposed to detect the fatigue driving. In this method, the homomorphic filtering is first used to preprocess the image to eliminate the effect of various lighting environment;then the face of driver is detected based on the Local Binary Pattern(LBP) based method considering its rapid image processing speed and the key points of the face and eyes were extracted using direct shape regression network (DSRN); finally, the features such as blink frequency, blink duration and PERCLOS are calculated based on the key points and the support vector machine is used to build classifier to identify the fatigue state of drivers. The results show that the proposed method can identify the fatigue state with relatively high accuracy.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evaluation of Motor Vehicle Driver Fatigue Based on Eye Movement Signals\",\"authors\":\"Xing Liu, Lecai Cai, Zhiming Wu, Shaosong Duan, Keyuan Tang, Chaoyang Zhang\",\"doi\":\"10.1109/ICCEAI52939.2021.00018\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Fatigue driving is one of the main causes of traffic accidents, and it has a great impact on road safety. One of the most effective fatigue driving detection methods is based on the machine vision using the characteristics of driver's eye. However, this accuracy of the method is influenced by the light environment during driving. In order to address the problem, a method is proposed to detect the fatigue driving. In this method, the homomorphic filtering is first used to preprocess the image to eliminate the effect of various lighting environment;then the face of driver is detected based on the Local Binary Pattern(LBP) based method considering its rapid image processing speed and the key points of the face and eyes were extracted using direct shape regression network (DSRN); finally, the features such as blink frequency, blink duration and PERCLOS are calculated based on the key points and the support vector machine is used to build classifier to identify the fatigue state of drivers. The results show that the proposed method can identify the fatigue state with relatively high accuracy.\",\"PeriodicalId\":331409,\"journal\":{\"name\":\"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCEAI52939.2021.00018\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCEAI52939.2021.00018","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Evaluation of Motor Vehicle Driver Fatigue Based on Eye Movement Signals
Fatigue driving is one of the main causes of traffic accidents, and it has a great impact on road safety. One of the most effective fatigue driving detection methods is based on the machine vision using the characteristics of driver's eye. However, this accuracy of the method is influenced by the light environment during driving. In order to address the problem, a method is proposed to detect the fatigue driving. In this method, the homomorphic filtering is first used to preprocess the image to eliminate the effect of various lighting environment;then the face of driver is detected based on the Local Binary Pattern(LBP) based method considering its rapid image processing speed and the key points of the face and eyes were extracted using direct shape regression network (DSRN); finally, the features such as blink frequency, blink duration and PERCLOS are calculated based on the key points and the support vector machine is used to build classifier to identify the fatigue state of drivers. The results show that the proposed method can identify the fatigue state with relatively high accuracy.