A Deep Regression Approach for Human Activity Recognition Under Partial Occlusion
International Journal of Neural Systems · 2023
DOI: 10.1142/s0129065723500478 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Neural Systems, 2023. Verfasst von Ioannis Vernikos und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics and Telecommunications, University of Thessaly, 3rd Km Old National Road Lamia-Athens, Lamia 35132, Greece. Hauptthemen laut MEDLINE: Human Activities, Neural Networks, Computer. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Smart digital applications and tools for the effective promotion and enhancement of the Ionian Islands biodiversity.
Abstract (Originalsprache)
In real-life scenarios, Human Activity Recognition (HAR) from video data is prone to occlusion of one or more body parts of the human subjects involved. Although it is common sense that the recognition of the majority of activities strongly depends on the motion of some body parts, which when occluded compromise the performance of recognition approaches, this problem is often underestimated in contemporary research works. Currently, training and evaluation is based on datasets that have been shot under laboratory (ideal) conditions, i.e. without any kind of occlusion. In this work, we propose an approach for HAR in the presence of partial occlusion, in cases wherein up to two body parts are involved. We assume that human motion is modeled using a set of 3D skeletal joints and also that occluded body parts remain occluded during the whole duration of the activity. We solve this problem using regression, performed by a novel deep Convolutional Recurrent Neural Network (CRNN). Specifically, given a partially occluded skeleton, we attempt to reconstruct the missing information regarding the motion of its occluded part(s). We evaluate our approach using four publicly available human motion datasets. Our experimental results indicate a significant increase of performance, when compared to baseline approaches, wherein networks that have been trained using only nonoccluded or both occluded and nonoccluded samples are evaluated using occluded samples. To the best of our knowledge, this is the first research work that formulates and copes with the problem of HAR under occlusion as a regression task.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Informatics and Telecommunications, University of Thessaly, 3rd Km Old National Road Lamia-Athens, Lamia 35132, Greece.
- Department of Informatics, Ionian University, 7 Tsirigoti Square, Corfu 49100, Greece.
- Department of Informatics and Computer Engineering, University of West Attica, Egaleo Park, Agiou Spyridonos Street, 12243 Egaleo, Athens, Greece.
Förderung
- Smart digital applications and tools for the effective promotion and enhancement of the Ionian Islands biodiversity
Zitieren
APA
Vernikos, I., Spyrou, E., Kostis, I. A., Mathe, E., & Mylonas, P. (2023). A Deep Regression Approach for Human Activity Recognition Under Partial Occlusion. International Journal of Neural Systems. https://doi.org/10.1142/s0129065723500478
Vancouver
Vernikos I, Spyrou E, Kostis IA, Mathe E, Mylonas P. A Deep Regression Approach for Human Activity Recognition Under Partial Occlusion. International Journal of Neural Systems. 2023. doi:10.1142/s0129065723500478
BibTeX
@article{Vernikos2023,
author = {Vernikos, Ioannis and Spyrou, Evaggelos and Kostis, Ioannis-Aris and Mathe, Eirini and Mylonas, Phivos},
title = {A Deep Regression Approach for Human Activity Recognition Under Partial Occlusion},
journal = {International Journal of Neural Systems},
year = {2023},
doi = {10.1142/s0129065723500478}
}
EUVIMED