{"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/periphery-fovea-multi-resolution-driving","title":"Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention","arxiv_id":"1903.09950","date":"2019-03-24","proceeding":null,"authors":["Ye Xia","Jinkyu Kim","John Canny","Karl Zipser","David Whitney"],"abstract":"Inspired by human vision, we propose a new periphery-fovea multi-resolution\ndriving model that predicts vehicle speed from dash camera videos. The\nperipheral vision module of the model processes the full video frames in low\nresolution. Its foveal vision module selects sub-regions and uses\nhigh-resolution input from those regions to improve its driving performance. We\ntrain the fovea selection module with supervision from driver gaze. We show\nthat adding high-resolution input from predicted human driver gaze locations\nsignificantly improves the driving accuracy of the model. Our periphery-fovea\nmulti-resolution model outperforms a uni-resolution periphery-only model that\nhas the same amount of floating-point operations. More importantly, we\ndemonstrate that our driving model achieves a significantly higher performance\ngain in pedestrian-involved critical situations than in other non-critical\nsituations.","url_abs":"http://arxiv.org/abs/1903.09950v1","url_pdf":"http://arxiv.org/pdf/1903.09950v1.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":"periphery-fovea-multi-resolution-driving","repo_url":"https://github.com/pascalxia/periphery_fovea_driving","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.09950","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}