{"title":"A 160-fps Embedded Lane Departure Warning System","authors":"B. H. P. Prasad, S. Yogamani","doi":"10.1109/ICCVE.2012.47","DOIUrl":null,"url":null,"abstract":"In this paper, we discuss a Hough-transform based Lane Departure Warning system implemented on a high performance Texas Instruments' C6x DSP running at 600MHz. We discuss the DSP implementation aspects and demonstrate how architecture-aware design of highly optimized algorithms can produce a high performance system reaching up to 160 fps on a 720x480 video stream. The implementation was tested on several test video sequences captured using a front facing camera fitted on the front bumper of a car and tested as well as on synthetic videos. We obtained an overall accuracy of 99.1% detection rate with 5% false positives.","PeriodicalId":182453,"journal":{"name":"2012 International Conference on Connected Vehicles and Expo (ICCVE)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 International Conference on Connected Vehicles and Expo (ICCVE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCVE.2012.47","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
In this paper, we discuss a Hough-transform based Lane Departure Warning system implemented on a high performance Texas Instruments' C6x DSP running at 600MHz. We discuss the DSP implementation aspects and demonstrate how architecture-aware design of highly optimized algorithms can produce a high performance system reaching up to 160 fps on a 720x480 video stream. The implementation was tested on several test video sequences captured using a front facing camera fitted on the front bumper of a car and tested as well as on synthetic videos. We obtained an overall accuracy of 99.1% detection rate with 5% false positives.