{"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/oxiod-the-dataset-for-deep-inertial-odometry","title":"OxIOD: The Dataset for Deep Inertial Odometry","arxiv_id":"1809.07491","date":"2018-09-20","proceeding":null,"authors":["Changhao Chen","Peijun Zhao","Chris Xiaoxuan Lu","Wei Wang","Andrew Markham","Niki Trigoni"],"abstract":"Advances in micro-electro-mechanical (MEMS) techniques enable inertial\nmeasurements units (IMUs) to be small, cheap, energy efficient, and widely used\nin smartphones, robots, and drones. Exploiting inertial data for accurate and\nreliable navigation and localization has attracted significant research and\nindustrial interest, as IMU measurements are completely ego-centric and\ngenerally environment agnostic. Recent studies have shown that the notorious\nissue of drift can be significantly alleviated by using deep neural networks\n(DNNs), e.g. IONet. However, the lack of sufficient labelled data for training\nand testing various architectures limits the proliferation of adopting DNNs in\nIMU-based tasks. In this paper, we propose and release the Oxford Inertial\nOdometry Dataset (OxIOD), a first-of-its-kind data collection for\ninertial-odometry research, with all sequences having ground-truth labels. Our\ndataset contains 158 sequences totalling more than 42 km in total distance,\nmuch larger than previous inertial datasets. Another notable feature of this\ndataset lies in its diversity, which can reflect the complex motions of\nphone-based IMUs in various everyday usage. The measurements were collected\nwith four different attachments (handheld, in the pocket, in the handbag and on\nthe trolley), four motion modes (halting, walking slowly, walking normally, and\nrunning), five different users, four types of off-the-shelf consumer phones,\nand large-scale localization from office buildings. Deep inertial tracking\nexperiments were conducted to show the effectiveness of our dataset in training\ndeep neural network models and evaluate learning-based and model-based\nalgorithms. The OxIOD Dataset is available at: http://deepio.cs.ox.ac.uk","url_abs":"http://arxiv.org/abs/1809.07491v1","url_pdf":"http://arxiv.org/pdf/1809.07491v1.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":"oxiod","name":"OxIOD","full_name":"Oxford Inertial Odometry Dataset"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.07491","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}