EUVIMEDEUVIMED entdecken
Crossref

Assessing the efficiency of pixel-based and object-based image classification using deep learning in an agricultural Mediterranean plain

Murat Bayazit, Cenk Dönmez, Süha Berberoglu

Environmental Monitoring and Assessment · 2025

DOI: 10.1007/s10661-024-13431-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Monitoring and Assessment, 2025. Verfasst von Murat Bayazit und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Remote Sensing and Geographical Information Systems, University of Cukurova, 01330, Adana, Turkey. mbayazit@student.cu.edu.tr. Hauptthemen laut MEDLINE: Deep Learning, Satellite Imagery, Environmental Monitoring, Agriculture. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 41 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advancements in satellite technology have greatly expanded data acquisition capabilities, making satellite imagery more accessible. Despite these strides, unlocking the full potential of satellite images necessitates efficient interpretation. Image classification, a widely adopted for extracting valuable information, has seen a surge in the application of deep learning methodologies due to their effectiveness. However, the success of deep learning is contingent upon the quality of the training data. In our study, we compared the efficiency of pixel-based and object-based classifications in Sentinel-2 satellite imagery using the Deeplabv3 deep learning method. The image sharpness was enhanced through a high-pass filter, aiding in data visualization and preparation. Deeplabv3 underwent training, leading to the development of classifiers following the extraction of training samples from the enhanced image. The majority zonal statistic method was implemented to assign class values to objects in the workflow. The accuracy of pixel-based and object-based classification was 83.1% and 83.5%, respectively, with corresponding kappa values of 0.786 and 0.791. These accuracies highlighted the efficient performance of the object-based method when integrated with a deep learning classifier. These results can serve as a valuable reference for future studies, aiding in the improvement of accuracy while potentially saving time and effort. By evaluating this nuanced impact pixel and object-based classification as well as on class-specific accuracy, this research contributes to the ongoing refinement of satellite image interpretation techniques in environmental applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSatellite ImageryEnvironmental MonitoringAgricultureMediterranean Region

Stichwörter der Autor:innen

AgricultureGISImage classificationNeural networksRemote sensing

Autor:innen und Institutionen

  • Department of Remote Sensing and Geographical Information Systems, University of Cukurova, 01330, Adana, Turkey. mbayazit@student.cu.edu.tr.
  • Leibniz Centre for Agricultural Landscape Research (ZALF), Eberswalder Straße 84, 15374, Müncheberg, Germany.
  • Department of Landscape Architecture, Remote Sensing and GIS Laboratory, University of Cukurova, Adana, 01330, Turkey.

Zitieren

APA

Bayazit, M., Dönmez, C., & Berberoglu, S. (2025). Assessing the efficiency of pixel-based and object-based image classification using deep learning in an agricultural Mediterranean plain. Environmental Monitoring and Assessment. https://doi.org/10.1007/s10661-024-13431-2

Vancouver

Bayazit M, Dönmez C, Berberoglu S. Assessing the efficiency of pixel-based and object-based image classification using deep learning in an agricultural Mediterranean plain. Environmental Monitoring and Assessment. 2025. doi:10.1007/s10661-024-13431-2

BibTeX
@article{Bayazit2025,
  author = {Bayazit, Murat and Dönmez, Cenk and Berberoglu, Süha},
  title = {Assessing the efficiency of pixel-based and object-based image classification using deep learning in an agricultural Mediterranean plain},
  journal = {Environmental Monitoring and Assessment},
  year = {2025},
  doi = {10.1007/s10661-024-13431-2}
}
Kostenlos starten →