EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Analyzing Data Modalities for Cattle Weight Estimation Using Deep Learning Models

Hina Afridi, Mohib Ullah iD, Øyvind Nordbø, Solvei Cottis Hoff, Siri Furre, Anne Guro Larsgard, Faouzi Alaya Cheikh

Journal of Imaging · 21.03.2024 · 10 (3) · 72

DOI: 10.3390/jimaging10030072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 21.03.2024. Verfasst von Hina Afridi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, Norway. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Council of Norway, Norwegian University of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We investigate the impact of different data modalities for cattle weight estimation. For this purpose, we collect and present our own cattle dataset representing the data modalities: RGB, depth, combined RGB and depth, segmentation, and combined segmentation and depth information. We explore a recent vision-transformer-based zero-shot model proposed by Meta AI Research for producing the segmentation data modality and for extracting the cattle-only region from the images. For experimental analysis, we consider three baseline deep learning models. The objective is to assess how the integration of diverse data sources influences the accuracy and robustness of the deep learning models considering four different performance metrics: mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE), and R-squared (R2). We explore the synergies and challenges associated with each modality and their combined use in enhancing the precision of cattle weight prediction. Through comprehensive experimentation and evaluation, we aim to provide insights into the effectiveness of different data modalities in improving the performance of established deep learning models, facilitating informed decision-making for precision livestock management systems.

Schlagwörter

Stichwörter der Autor:innen

cattle weight estimationdata modalitiesdeep learning modelsdepth informationsegmentation

Autor:innen und Institutionen

  • Department of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, Norway.
  • Geno SA, Storhamargata 44, 2317 Hamar, Norway.
  • Norsvin SA, Storhamargata 44, 2317 Hamar, Norway.
  • TYR SA, Storhamargata 44, 2317 Hamar, Norway.

ORCID-Profile: Mohib Ullah

Förderung

  • Research Council of Norway
  • Norwegian University of Science and Technology

Zitieren

APA

Afridi, H., Ullah, M., Nordbø, Ø., Hoff, S. C., Furre, S., Larsgard, A. G., & Cheikh, F. A. (2024). Analyzing Data Modalities for Cattle Weight Estimation Using Deep Learning Models. Journal of Imaging, 10(3), 72. https://doi.org/10.3390/jimaging10030072

Vancouver

Afridi H, Ullah M, Nordbø Ø, Hoff SC, Furre S, Larsgard AG, et al. Analyzing Data Modalities for Cattle Weight Estimation Using Deep Learning Models. Journal of Imaging. 2024;10(3):72. doi:10.3390/jimaging10030072

BibTeX
@article{Afridi2024,
  author = {Afridi, Hina and Ullah, Mohib and Nordbø, Øyvind and Hoff, Solvei Cottis and Furre, Siri and Larsgard, Anne Guro and Cheikh, Faouzi Alaya},
  title = {Analyzing Data Modalities for Cattle Weight Estimation Using Deep Learning Models},
  journal = {Journal of Imaging},
  year = {2024},
  volume = {10},
  number = {3},
  pages = {72},
  doi = {10.3390/jimaging10030072}
}
Kostenlos starten →