Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/80090
Título: | From raw measurements to human pose - a dataset with low-cost and high-end inertial-magnetic sensor data |
Autor(es): | Palermo, Manuel Cerqueira, Sara M. André, João Pereira, António Santos, Cristina |
Palavras-chave: | Human Pose Estimation Inertial Data Dataset |
Data: | 30-Set-2022 |
Editora: | Nature Research |
Revista: | Scientific Data |
Citação: | Palermo, M., Cerqueira, S.M., André, J. et al. From raw measurements to human pose - a dataset with low-cost and high-end inertial-magnetic sensor data. Sci Data 9, 591 (2022). https://doi.org/10.1038/s41597-022-01690-y |
Resumo(s): | Wearable technology is expanding for motion monitoring. However, open challenges still limit its widespread use, especially in low-cost systems. Most solutions are either expensive commercial products or lower performance ad-hoc systems. Moreover, few datasets are available for the development of complete and general solutions. This work presents 2 datasets, with low-cost and high-end Magnetic, Angular Rate, and Gravity(MARG) sensor data. Provides data for the complete inertial pose pipeline analysis, starting from raw data, sensor-to-segment calibration, multi-sensor fusion, skeleton-kinematics, to complete Human pose. Contains data from 21 and 10 participants, respectively, performing 6 types of sequences, presenting high variability and complex dynamics with almost complete range-of-motion. Amounts to 3.5 M samples, synchronized with a ground-truth inertial motion capture system. Presents a method to evaluate data quality. This database may contribute to develop novel algorithms for each pipeline's processing steps, with applications in inertial pose estimation algorithms, human movement forecasting, and motion assessment in industrial or rehabilitation settings. All data and code to process and analyze the complete pipeline is freely available. |
Tipo: | Artigo |
Descrição: | This database is accompanied by a folder with all the scripts used to process and handle the data described. It is openly hosted in Zenodo: https://doi.org/10.5281/zenodo.5801927 Additionally, an extended code repository is available on Github (https://github.com/ManuelPalermo/HumanInertialPose.git) with updated code to not only process the data described, but also calculate kinematics, visualize and evaluate the resulting motions and offers extended support for general inertial pose estimation pipelines. All scripts are based on the Python programming language and, thus, open source. The code contains a permissive MIT license for unrestricted usage. |
URI: | https://hdl.handle.net/1822/80090 |
DOI: | 10.1038/s41597-022-01690-y |
e-ISSN: | 2052-4463 |
Versão da editora: | https://www.nature.com/articles/s41597-022-01690-y |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CMEMS - Artigos em revistas internacionais/Papers in international journals |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
s41597-022-01690-y.pdf | 10,24 MB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons