{"title":"Distance estimation using mono camera at different altitudes and pitch angles","authors":"Nurgeldy Praliyev, Viktor Remeli, Z. Szalay","doi":"10.1109/SAMI50585.2021.9378676","DOIUrl":null,"url":null,"abstract":"This article presents two prospective methods for vehicle distance estimation utilizing a single camera at different altitudes and camera pitch angles. A distance estimation procedure was conducted applying real-life visualization and homography approaches. Experimental outputs showed that the real-life visualization method overperforms the homography at all altitudes and distance ranges. The performance of the homography can be improved by locating the camera at higher locations with more pronounced tilt angles as it would provide less error / pixel at the cost of a reduced field of view. Overall, both introduced techniques perform better at higher camera positions and closer target distances. Application of mentioned methods in vehicles is a simple and economical way to improve their autonomy and reduce road risk level.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SAMI50585.2021.9378676","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This article presents two prospective methods for vehicle distance estimation utilizing a single camera at different altitudes and camera pitch angles. A distance estimation procedure was conducted applying real-life visualization and homography approaches. Experimental outputs showed that the real-life visualization method overperforms the homography at all altitudes and distance ranges. The performance of the homography can be improved by locating the camera at higher locations with more pronounced tilt angles as it would provide less error / pixel at the cost of a reduced field of view. Overall, both introduced techniques perform better at higher camera positions and closer target distances. Application of mentioned methods in vehicles is a simple and economical way to improve their autonomy and reduce road risk level.