Titel: Learning metric volume estimation of fruits and vegetables from short monocular video sequences

We present a novel approach for extracting metric volume information of fruits and vegetables from short monocular video sequences and associated inertial data recorded with a hand-held smartphone. Estimated segmentation masks from a pre-trained object detector are fused with the predicted change in relative pose obtained from the inertial data to predict the class and volume of the objects of interest. Our approach works with simple RGB video frames and inertial data which are readily available from modern smartphones. It does not require reference objects of known size in the video frames. Using a balanced validation dataset, we achieve a classification accuracy of 95% and a mean absolute percentage error for the volume prediction of 16% on untrained objects, which is comparable to state-of-the-art results requiring more elaborated data recording setups. A very accurate estimation of the model uncertainty is achieved through ensembling and the use of Gaussian negative log-likelihood loss. The dataset used in our experiments including ground-truth volume information is available at

Schlagworte: Deep learning; Computer vision; Image Recognition
Publikationstyp: Beitrag in Zeitschrift (Autorenschaft)
Erscheinungsdatum: 21.03.2023 (Online)
Erschienen in: Heliyon
zur Publikation
 ( Cell Press; )
Titel der Serie: -
Bandnummer: 9
Heftnummer: 4
Erstveröffentlichung: Ja
Version: -
Seite: S. e14722 - e14722


Keine Version vorhanden
Erscheinungsdatum: 21.03.2023
ISBN (e-book): -
eISSN: -
Homepage: -
Open Access
  • In einem Open-Access-Journal erschienen


Organisation Adresse
Fakultät für Technische Wissenschaften
Institut für Intelligente Systemtechnologien
Universitätsstraße 65-67
9020 Klagenfurt am Wörthersee
zur Organisation
Universitätsstraße 65-67
AT - 9020  Klagenfurt am Wörthersee


  • 102001 - Artificial Intelligence
  • 102018 - Künstliche Neuronale Netze
  • 102019 - Machine Learning
  • 303009 - Ernährungswissenschaften
  • Public Health
  • Science Citation Index Expanded (SCI Expanded)
Informationen zum Zitationsindex: Master Journal List
Peer Reviewed
  • Ja
  • Science to Science (Qualitätsindikator: I)
Klassifikationsraster der zugeordneten Organisationseinheiten:
  • Control of Networked Systems


Organisation Adresse
Silicon Austria Labs GmbH
High Tech Campus Villach ‑ Europastraße 12
9524 Villach
Österreich - Kärnten
High Tech Campus Villach ‑ Europastraße 12
AT - 9524  Villach
Philips Domestic Appliances Austria GmbH
Koningsbergerstraße 11
9020 Klagenfurt am Wörthersee
Österreich - Kärnten
Koningsbergerstraße 11
AT - 9020  Klagenfurt am Wörthersee

Beiträge der Publikation

Keine verknüpften Publikationen vorhanden