EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

A Comprehensive Methodological Survey of Human Activity Recognition Across Diverse Data Modalities

Jungpil Shin iD, Najmul Hassan iD, Abu Saleh Musa Miah iD, Satoshi Nishimura

Sensors · 27.06.2025 · 25 (13) · 4028

DOI: 10.3390/s25134028 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 27.06.2025. Verfasst von Jungpil Shin und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan. Hauptthemen laut MEDLINE: Human Activities. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 415 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Competitive Research Fund of The University of Aizu, Japan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human Activity Recognition (HAR) systems aim to understand human behavior and assign a label to each action, attracting significant attention in computer vision due to their wide range of applications. HAR can leverage various data modalities, such as RGB images and video, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, and radar signals. Each modality provides unique and complementary information suited to different application scenarios. Consequently, numerous studies have investigated diverse approaches for HAR using these modalities. This survey includes only peer-reviewed research papers published in English to ensure linguistic consistency and academic integrity. This paper presents a comprehensive survey of the latest advancements in HAR from 2014 to 2025, focusing on Machine Learning (ML) and Deep Learning (DL) approaches categorized by input data modalities. We review both single-modality and multi-modality techniques, highlighting fusion-based and co-learning frameworks. Additionally, we cover advancements in hand-crafted action features, methods for recognizing human–object interactions, and activity detection. Our survey includes a detailed dataset description for each modality, as well as a summary of the latest HAR systems, accompanied by a mathematical derivation for evaluating the deep learning model for each modality, and it also provides comparative results on benchmark datasets. Finally, we provide insightful observations and propose effective future research directions in HAR.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Human ActivitiesHumansDeep LearningMachine LearningAlgorithms

Stichwörter der Autor:innen

classificationdeep learning (DL)diverse modalityhuman activity recognition (HAR)machine learning (ML)vision and sensor based HAR

Autor:innen und Institutionen

  • School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan.

ORCID-Profile: Jungpil Shin, Najmul Hassan, Abu Saleh Musa Miah

Förderung

  • Competitive Research Fund of The University of Aizu, Japan

Zitieren

APA

Shin, J., Hassan, N., Miah, A. S. M., & Nishimura, S. (2025). A Comprehensive Methodological Survey of Human Activity Recognition Across Diverse Data Modalities. Sensors, 25(13), 4028. https://doi.org/10.3390/s25134028

Vancouver

Shin J, Hassan N, Miah ASM, Nishimura S. A Comprehensive Methodological Survey of Human Activity Recognition Across Diverse Data Modalities. Sensors. 2025;25(13):4028. doi:10.3390/s25134028

BibTeX
@article{Shin2025,
  author = {Shin, Jungpil and Hassan, Najmul and Miah, Abu Saleh Musa and Nishimura, Satoshi},
  title = {A Comprehensive Methodological Survey of Human Activity Recognition Across Diverse Data Modalities},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {4028},
  doi = {10.3390/s25134028}
}
Kostenlos starten →