{"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/an-empirical-evaluation-of-deep-learning-on","title":"An Empirical Evaluation of Deep Learning on Highway Driving","arxiv_id":"1504.01716","date":"2015-04-07","proceeding":null,"authors":["Brody Huval","Tao Wang","Sameep Tandon","Jeff Kiske","Will Song","Joel Pazhayampallil","Mykhaylo Andriluka","Pranav Rajpurkar","Toki Migimatsu","Royce Cheng-Yue","Fernando Mujica","Adam Coates","Andrew Y. Ng"],"abstract":"Numerous groups have applied a variety of deep learning techniques to\ncomputer vision problems in highway perception scenarios. In this paper, we\npresented a number of empirical evaluations of recent deep learning advances.\nComputer vision, combined with deep learning, has the potential to bring about\na relatively inexpensive, robust solution to autonomous driving. To prepare\ndeep learning for industry uptake and practical applications, neural networks\nwill require large data sets that represent all possible driving environments\nand scenarios. We collect a large data set of highway data and apply deep\nlearning and computer vision algorithms to problems such as car and lane\ndetection. We show how existing convolutional neural networks (CNNs) can be\nused to perform lane and vehicle detection while running at frame rates\nrequired for a real-time system. Our results lend credence to the hypothesis\nthat deep learning holds promise for autonomous driving.","url_abs":"http://arxiv.org/abs/1504.01716v3","url_pdf":"http://arxiv.org/pdf/1504.01716v3.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":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"lane-detection","task_name":"Lane Detection"},{"task_slug":"vehicle-detection","task_name":"vehicle detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lane-detection-on-caltech-lanes-cordova","task":"Lane Detection","dataset":"Caltech Lanes Cordova","model":"Overfeat CNN detector + DBSCAN","rank_in_archive_order":2,"of":2,"metrics":{"F1":"0.866"},"uses_additional_data":false},{"leaderboard":"/sota/lane-detection-on-caltech-lanes-washington","task":"Lane Detection","dataset":"Caltech Lanes Washington","model":"Overfeat CNN detector + DBSCAN","rank_in_archive_order":2,"of":2,"metrics":{"F1":"0.861"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1504.01716","atlas_url":"https://app.syntology.ai/?focus=1504.01716","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}