{"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/ddd17-end-to-end-davis-driving-dataset","title":"DDD17: End-To-End DAVIS Driving Dataset","arxiv_id":"1711.01458","date":"2017-11-04","proceeding":null,"authors":["Jonathan Binas","Daniel Neil","Shih-Chii Liu","Tobi Delbruck"],"abstract":"Event cameras, such as dynamic vision sensors (DVS), and dynamic and\nactive-pixel vision sensors (DAVIS) can supplement other autonomous driving\nsensors by providing a concurrent stream of standard active pixel sensor (APS)\nimages and DVS temporal contrast events. The APS stream is a sequence of\nstandard grayscale global-shutter image sensor frames. The DVS events represent\nbrightness changes occurring at a particular moment, with a jitter of about a\nmillisecond under most lighting conditions. They have a dynamic range of >120\ndB and effective frame rates >1 kHz at data rates comparable to 30 fps\n(frames/second) image sensors. To overcome some of the limitations of current\nimage acquisition technology, we investigate in this work the use of the\ncombined DVS and APS streams in end-to-end driving applications. The dataset\nDDD17 accompanying this paper is the first open dataset of annotated DAVIS\ndriving recordings. DDD17 has over 12 h of a 346x260 pixel DAVIS sensor\nrecording highway and city driving in daytime, evening, night, dry and wet\nweather conditions, along with vehicle speed, GPS position, driver steering,\nthrottle, and brake captured from the car's on-board diagnostics interface. As\nan example application, we performed a preliminary end-to-end learning study of\nusing a convolutional neural network that is trained to predict the\ninstantaneous steering angle from DVS and APS visual data.","url_abs":"http://arxiv.org/abs/1711.01458v1","url_pdf":"http://arxiv.org/pdf/1711.01458v1.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":[{"paper_slug":"ddd17-end-to-end-davis-driving-dataset","repo_url":"https://github.com/SensorsINI/ddd20-utils","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"}],"methods":[],"datasets_introduced":[{"slug":"ddd17","name":"DDD17","full_name":"DAVIS Driving Dataset 2017"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.01458","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}