EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring

Marcus Jenkins iD, Kirsty A Franklin iD, Malcolm A C Nicoll iD, Nik C Cole iD, Kevin Ruhomaun, Vikash Tatayah, Michal Mackiewicz iD

Sensors · 14.12.2024 · 24 (24) · 8002

DOI: 10.3390/s24248002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.12.2024. Verfasst von Marcus Jenkins und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing Sciences, University of East Anglia (UEA), Norwich, NR4 7TJ, UK. Hauptthemen laut MEDLINE: Time-Lapse Imaging, Animals, Wild. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monitoring animal populations is crucial for assessing the health of ecosystems. Traditional methods, which require extensive fieldwork, are increasingly being supplemented by time-lapse camera-trap imagery combined with an automatic analysis of the image data. The latter usually involves some object detector aimed at detecting relevant targets (commonly animals) in each image, followed by some postprocessing to gather activity and population data. In this paper, we show that the performance of an object detector in a single frame of a time-lapse sequence can be improved by including spatio-temporal features from the prior frames. We propose a method that leverages temporal information by integrating two additional spatial feature channels which capture stationary and non-stationary elements of the scene and consequently improve scene understanding and reduce the number of stationary false positives. The proposed technique achieves a significant improvement of 24% in mean average precision (mAP@0.05:0.95) over the baseline (temporal feature-free, single frame) object detector on a large dataset of breeding tropical seabirds. We envisage our method will be widely applicable to other wildlife monitoring applications that use time-lapse imaging.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Time-Lapse ImagingAnimals, WildAnimalsImage Processing, Computer-AssistedAlgorithmsEcosystemBirdsEnvironmental Monitoring

Stichwörter der Autor:innen

YOLOcamera-trap imageryobject detectionspatio-temporal featurestemporal featurestime-lapse imagerywildlife monitoring

Autor:innen und Institutionen

  • School of Computing Sciences, University of East Anglia (UEA), Norwich, NR4 7TJ, UK.
  • School of Biological Sciences, University of East Anglia (UEA), Norwich NR4 7TJ, UK.
  • Institute of Zoology, Zoological Society of London, Regent's Park, London NW1 4RY, UK.
  • Durrell Wildlife Conservation Trust, Les Augrès Manor, Trinity, Jersey JE3 5BP, UK.
  • Mauritian Wildlife Foundation, Grannum Road, Vacoas 73418, Mauritius.
  • National Parks and Conservation Service (Government of Mauritius), Ministry of Agro-Industry, Food Security, Blue Economy and Fisheries, Head Office, Reduit, Mauritius.

ORCID-Profile: Marcus Jenkins, Kirsty A Franklin, Malcolm A C Nicoll, Nik C Cole, Michal Mackiewicz

Zitieren

APA

Jenkins, M., Franklin, K. A., Nicoll, M. A. C., Cole, N. C., Ruhomaun, K., Tatayah, V., & Mackiewicz, M. (2024). Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring. Sensors, 24(24), 8002. https://doi.org/10.3390/s24248002

Vancouver

Jenkins M, Franklin KA, Nicoll MAC, Cole NC, Ruhomaun K, Tatayah V, et al. Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring. Sensors. 2024;24(24):8002. doi:10.3390/s24248002

BibTeX
@article{Jenkins2024,
  author = {Jenkins, Marcus and Franklin, Kirsty A and Nicoll, Malcolm A C and Cole, Nik C and Ruhomaun, Kevin and Tatayah, Vikash and Mackiewicz, Michal},
  title = {Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {24},
  pages = {8002},
  doi = {10.3390/s24248002}
}
Kostenlos starten →