EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

WE3DS: An RGB-D Image Dataset for Semantic Segmentation in Agriculture

Florian Kitzler iD, Norbert Barta iD, Reinhard W Neugschwandtner iD, Andreas Gronauer iD, Viktoria Motsch iD

Sensors · 01.03.2023 · 23 (5) · 2713

DOI: 10.3390/s23052713 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.03.2023. Verfasst von Florian Kitzler und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Sustainable Agricultural Systems, Institute of Agricultural Engineering, University of Natural Resources and Life Sciences Vienna, Pete…. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Government of Lower Austria, Government of Lower Austria and the private foundation Forum Morgen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Smart farming (SF) applications rely on robust and accurate computer vision systems. An important computer vision task in agriculture is semantic segmentation, which aims to classify each pixel of an image and can be used for selective weed removal. State-of-the-art implementations use convolutional neural networks (CNN) that are trained on large image datasets. In agriculture, publicly available RGB image datasets are scarce and often lack detailed ground-truth information. In contrast to agriculture, other research areas feature RGB-D datasets that combine color (RGB) with additional distance (D) information. Such results show that including distance as an additional modality can improve model performance further. Therefore, we introduce WE3DS as the first RGB-D image dataset for multi-class plant species semantic segmentation in crop farming. It contains 2568 RGB-D images (color image and distance map) and corresponding hand-annotated ground-truth masks. Images were taken under natural light conditions using an RGB-D sensor consisting of two RGB cameras in a stereo setup. Further, we provide a benchmark for RGB-D semantic segmentation on the WE3DS dataset and compare it with a solely RGB-based model. Our trained models achieve up to 70.7% mean Intersection over Union (mIoU) for discriminating between soil, seven crop species, and ten weed species. Finally, our work confirms the finding that additional distance information improves segmentation quality.

Schlagwörter

Stichwörter der Autor:innen

RGB-Dcrop farmingimage datasetsemantic segmentationstereo visionweed detection

Autor:innen und Institutionen

  • Department of Sustainable Agricultural Systems, Institute of Agricultural Engineering, University of Natural Resources and Life Sciences Vienna, Peter-Jordan-Straße 82, 1190 Vienna, Austria.
  • Department of Crop Sciences, Institute of Agronomy, University of Natural Resources and Life Sciences Vienna, Konrad Lorenz-Straße 24, 3430 Tulln an der Donau, Austria.

ORCID-Profile: Florian Kitzler, Norbert Barta, Reinhard W Neugschwandtner, Andreas Gronauer, Viktoria Motsch

Förderung

  • Government of Lower Austria
  • Government of Lower Austria and the private foundation Forum Morgen

Zitieren

APA

Kitzler, F., Barta, N., Neugschwandtner, R. W., Gronauer, A., & Motsch, V. (2023). WE3DS: An RGB-D Image Dataset for Semantic Segmentation in Agriculture. Sensors, 23(5), 2713. https://doi.org/10.3390/s23052713

Vancouver

Kitzler F, Barta N, Neugschwandtner RW, Gronauer A, Motsch V. WE3DS: An RGB-D Image Dataset for Semantic Segmentation in Agriculture. Sensors. 2023;23(5):2713. doi:10.3390/s23052713

BibTeX
@article{Kitzler2023,
  author = {Kitzler, Florian and Barta, Norbert and Neugschwandtner, Reinhard W and Gronauer, Andreas and Motsch, Viktoria},
  title = {WE3DS: An RGB-D Image Dataset for Semantic Segmentation in Agriculture},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {5},
  pages = {2713},
  doi = {10.3390/s23052713}
}
Kostenlos starten →