{"title":"A-pillar Blind Spot Display Algorithm Based on Line of Sight","authors":"Shi-Xian Sui, Tianjun Li, Shengyong Chen","doi":"10.1109/CCET55412.2022.9906348","DOIUrl":null,"url":null,"abstract":"The closed load-bearing structure of a car is designed to decrease the injuries to drivers in traffic accidents, however, such a design also results in many blind spots in driving which are the main cause of a number of car crashes. A-pillar blind spots elimination can make for safer driving. Therefore, this paper proposes an algorithm that utilizes a screen mounted on the A-pillar to display its blind spots in real time and uses a wide-angle camera to capture a panoramic view outside the car. We use a binocular vision system detecting facial features to calculate the driver’s head pose and the 3D coordinates of the pupil center. After obtaining the pupil centers and coordinates of the four corners of the A-pillar display screen, the blind spot can be calculated through the angular relationship between the driver’s line of sight and the outside wide-angle camera’s angle of view. Considering the possibility that the pupil center detection may fail when the driver is not looking at the A-pillar, we propose a compensation method to indirectly calculate the pupil center by using the camera above the driver’s head. We carried out a simulation experiment using a display screen replacing the A-pillar, which showed that our algorithm could display the blind spots occluded by the display screen well.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCET55412.2022.9906348","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
The closed load-bearing structure of a car is designed to decrease the injuries to drivers in traffic accidents, however, such a design also results in many blind spots in driving which are the main cause of a number of car crashes. A-pillar blind spots elimination can make for safer driving. Therefore, this paper proposes an algorithm that utilizes a screen mounted on the A-pillar to display its blind spots in real time and uses a wide-angle camera to capture a panoramic view outside the car. We use a binocular vision system detecting facial features to calculate the driver’s head pose and the 3D coordinates of the pupil center. After obtaining the pupil centers and coordinates of the four corners of the A-pillar display screen, the blind spot can be calculated through the angular relationship between the driver’s line of sight and the outside wide-angle camera’s angle of view. Considering the possibility that the pupil center detection may fail when the driver is not looking at the A-pillar, we propose a compensation method to indirectly calculate the pupil center by using the camera above the driver’s head. We carried out a simulation experiment using a display screen replacing the A-pillar, which showed that our algorithm could display the blind spots occluded by the display screen well.