{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ego-lane-analysis-system-elas-dataset-and","title":"Ego-Lane Analysis System (ELAS): Dataset and Algorithms","arxiv_id":"1806.05984","date":"2018-06-15","proceeding":null,"authors":["Rodrigo F. Berriel","Edilson de Aguiar","Alberto F. de Souza","Thiago Oliveira-Santos"],"abstract":"Decreasing costs of vision sensors and advances in embedded hardware boosted\nlane related research detection, estimation, and tracking in the past two\ndecades. The interest in this topic has increased even more with the demand for\nadvanced driver assistance systems (ADAS) and self-driving cars. Although\nextensively studied independently, there is still need for studies that propose\na combined solution for the multiple problems related to the ego-lane, such as\nlane departure warning (LDW), lane change detection, lane marking type (LMT)\nclassification, road markings detection and classification, and detection of\nadjacent lanes (i.e., immediate left and right lanes) presence. In this paper,\nwe propose a real-time Ego-Lane Analysis System (ELAS) capable of estimating\nego-lane position, classifying LMTs and road markings, performing LDW and\ndetecting lane change events. The proposed vision-based system works on a\ntemporal sequence of images. Lane marking features are extracted in perspective\nand Inverse Perspective Mapping (IPM) images that are combined to increase\nrobustness. The final estimated lane is modeled as a spline using a combination\nof methods (Hough lines with Kalman filter and spline with particle filter).\nBased on the estimated lane, all other events are detected. To validate ELAS\nand cover the lack of lane datasets in the literature, a new dataset with more\nthan 20 different scenes (in more than 15,000 frames) and considering a variety\nof scenarios (urban road, highways, traffic, shadows, etc.) was created. The\ndataset was manually annotated and made publicly available to enable evaluation\nof several events that are of interest for the research community (i.e., lane\nestimation, change, and centering; road markings; intersections; LMTs;\ncrosswalks and adjacent lanes). ELAS achieved high detection rates in all\nreal-world events and proved to be ready for real-time applications.","url_abs":"http://arxiv.org/abs/1806.05984v1","url_pdf":"http://arxiv.org/pdf/1806.05984v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"change-detection","task_name":"Change Detection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"self-driving-cars","task_name":"Self-Driving Cars"}],"methods":[],"datasets_introduced":[{"slug":"elas","name":"ELAS","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}