EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Future Pose Prediction from 3D Human Skeleton Sequence with Surrounding Situation

Tomohiro Fujita iD, Yasutomo Kawanishi iD

Sensors · 2023

DOI: 10.3390/s23020876 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Tomohiro Fujita und 1 weiteren Autor:innen. Beteiligte Einrichtung: Guardian Robot Project R-IH, RIKEN, Advanced Telecommunications Research Institute International, 3rd Floor, 2-2-2 Hikaridai, Seika-cho, Sorakugun, K…. Hauptthemen laut MEDLINE: Algorithms, Musculoskeletal System. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human pose prediction is vital for robot applications such as human–robot interaction and autonomous control of robots. Recent prediction methods often use deep learning and are based on a 3D human skeleton sequence to predict future poses. Even if the starting motions of 3D human skeleton sequences are very similar, their future poses will have variety. It makes it difficult to predict future poses only from a given human skeleton sequence. Meanwhile, when carefully observing human motions, we can find that human motions are often affected by objects or other people around the target person. We consider that the presence of surrounding objects is an important clue for the prediction. This paper proposes a method for predicting the future skeleton sequence by incorporating the surrounding situation into the prediction model. The proposed method uses a feature of an image around the target person as the surrounding information. We confirmed the performance improvement of the proposed method through evaluations on publicly available datasets. As a result, the prediction accuracy was improved for object-related and human-related motions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsMusculoskeletal SystemHumansMotionSkeleton

Stichwörter der Autor:innen

3D skeleton sequencepose predictionsurrounding information

Autor:innen und Institutionen

  • Guardian Robot Project R-IH, RIKEN, Advanced Telecommunications Research Institute International, 3rd Floor, 2-2-2 Hikaridai, Seika-cho, Sorakugun, Kyoto 619-0288, Japan.

ORCID-Profile: Tomohiro Fujita, Yasutomo Kawanishi

Zitieren

APA

Fujita, T., & Kawanishi, Y. (2023). Future Pose Prediction from 3D Human Skeleton Sequence with Surrounding Situation. Sensors. https://doi.org/10.3390/s23020876

Vancouver

Fujita T, Kawanishi Y. Future Pose Prediction from 3D Human Skeleton Sequence with Surrounding Situation. Sensors. 2023. doi:10.3390/s23020876

BibTeX
@article{Fujita2023,
  author = {Fujita, Tomohiro and Kawanishi, Yasutomo},
  title = {Future Pose Prediction from 3D Human Skeleton Sequence with Surrounding Situation},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23020876}
}
Kostenlos starten →