{"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/lost-and-found-detecting-small-road-hazards","title":"Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles","arxiv_id":"1609.04653","date":"2016-09-15","proceeding":null,"authors":["Peter Pinggera","Sebastian Ramos","Stefan Gehrig","Uwe Franke","Carsten Rother","Rudolf Mester"],"abstract":"Detecting small obstacles on the road ahead is a critical part of the driving\ntask which has to be mastered by fully autonomous cars. In this paper, we\npresent a method based on stereo vision to reliably detect such obstacles from\na moving vehicle. The proposed algorithm performs statistical hypothesis tests\nin disparity space directly on stereo image data, assessing freespace and\nobstacle hypotheses on independent local patches. This detection approach does\nnot depend on a global road model and handles both static and moving obstacles.\nFor evaluation, we employ a novel lost-cargo image sequence dataset comprising\nmore than two thousand frames with pixelwise annotations of obstacle and\nfree-space and provide a thorough comparison to several stereo-based baseline\nmethods. The dataset will be made available to the community to foster further\nresearch on this important topic. The proposed approach outperforms all\nconsidered baselines in our evaluations on both pixel and object level and runs\nat frame rates of up to 20 Hz on 2 mega-pixel stereo imagery. Small obstacles\ndown to the height of 5 cm can successfully be detected at 20 m distance at low\nfalse positive rates.","url_abs":"http://arxiv.org/abs/1609.04653v1","url_pdf":"http://arxiv.org/pdf/1609.04653v1.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":[],"methods":[],"datasets_introduced":[{"slug":"lost-and-found","name":"Lost and Found","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.04653","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}