EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sensor Fusion Approach for Multiple Human Motion Detection for Indoor Surveillance Use-Case

Ali Abbasi iD, Sandro Queirós iD, Nuno M C da Costa iD, Jaime C Fonseca iD, João Borges iD

Sensors · 14.04.2023 · 23 (8) · 3993

DOI: 10.3390/s23083993 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.04.2023. Verfasst von Ali Abbasi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Algorithmic Center, University of Minho, 4800-058 Azurém, Portugal. Hauptthemen laut MEDLINE: Culture, Optic Flow. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FCT–Fundação para a Ciência e Tecnologia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-human detection and tracking in indoor surveillance is a challenging task due to various factors such as occlusions, illumination changes, and complex human-human and human-object interactions. In this study, we address these challenges by exploring the benefits of a low-level sensor fusion approach that combines grayscale and neuromorphic vision sensor (NVS) data. We first generate a custom dataset using an NVS camera in an indoor environment. We then conduct a comprehensive study by experimenting with different image features and deep learning networks, followed by a multi-input fusion strategy to optimize our experiments with respect to overfitting. Our primary goal is to determine the best input feature types for multi-human motion detection using statistical analysis. We find that there is a significant difference between the input features of optimized backbones, with the best strategy depending on the amount of available data. Specifically, under a low-data regime, event-based frames seem to be the preferred input feature type, while higher data availability benefits the combined use of grayscale and optical flow features. Our results demonstrate the potential of sensor fusion and deep learning techniques for multi-human tracking in indoor surveillance, although it is acknowledged that further studies are needed to confirm our findings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CultureOptic FlowHumansLightingMotionResearch Design

Stichwörter der Autor:innen

event-based dataindoor surveillancemulti-modal datamultiple human motion detection and trackingneuromorphic vision sensorsensor fusion

Autor:innen und Institutionen

  • Algorithmic Center, University of Minho, 4800-058 Azurém, Portugal.
  • School of Medicine, University of Minho, 4710-057 Gualtar, Portugal.
  • 2Ai-School of Technology, IPCA, 4750-810 Barcelos, Portugal.

ORCID-Profile: Ali Abbasi, Sandro Queirós, Nuno M C da Costa, Jaime C Fonseca, João Borges

Förderung

  • FCT–Fundação para a Ciência e Tecnologia

Zitieren

APA

Abbasi, A., Queirós, S., da Costa, N. M. C., Fonseca, J. C., & Borges, J. (2023). Sensor Fusion Approach for Multiple Human Motion Detection for Indoor Surveillance Use-Case. Sensors, 23(8), 3993. https://doi.org/10.3390/s23083993

Vancouver

Abbasi A, Queirós S, da Costa NMC, Fonseca JC, Borges J. Sensor Fusion Approach for Multiple Human Motion Detection for Indoor Surveillance Use-Case. Sensors. 2023;23(8):3993. doi:10.3390/s23083993

BibTeX
@article{Abbasi2023,
  author = {Abbasi, Ali and Queirós, Sandro and da Costa, Nuno M C and Fonseca, Jaime C and Borges, João},
  title = {Sensor Fusion Approach for Multiple Human Motion Detection for Indoor Surveillance Use-Case},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {8},
  pages = {3993},
  doi = {10.3390/s23083993}
}
Kostenlos starten →