{"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/road-user-detection-in-videos","title":"Road User Detection in Videos","arxiv_id":"1903.12049","date":"2019-03-28","proceeding":null,"authors":["Hughes Perreault","Guillaume-Alexandre Bilodeau","Nicolas Saunier","Pierre Gravel"],"abstract":"Successive frames of a video are highly redundant, and the most popular\nobject detection methods do not take advantage of this fact. Using multiple\nconsecutive frames can improve detection of small objects or difficult examples\nand can improve speed and detection consistency in a video sequence, for\ninstance by interpolating features between frames. In this work, a novel\napproach is introduced to perform online video object detection using two\nconsecutive frames of video sequences involving road users. Two new models,\nRetinaNet-Double and RetinaNet-Flow, are proposed, based respectively on the\nconcatenation of a target frame with a preceding frame, and the concatenation\nof the optical flow with the target frame. The models are trained and evaluated\non three public datasets. Experiments show that using a preceding frame\nimproves performance over single frame detectors, but using explicit optical\nflow usually does not.","url_abs":"http://arxiv.org/abs/1903.12049v1","url_pdf":"http://arxiv.org/pdf/1903.12049v1.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":"road-user-detection-in-videos","repo_url":"https://github.com/hu64/RN-VID","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"video-object-detection","task_name":"Video Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}