This paper presents a method for automatic fruit detection in vineyards through the inspection of colour images obtained by a low cost RGB-D sensor placed on-board an agricultural vehicle. Image segmentation is obtained by using a pre-trained convolutional neural network, which receives input data, as sub-patches of known size, and performs the classification in a few classes of interest. Output scores are then used to create the probability maps for each class and, thus, pixel-by-pixel segmentation of the grape clusters. Field experiments prove the ability of the proposed processing to successfully segment grape clusters, with accuracy of 87.5%, despite the poor quality of the input images.

Deep learning-based image segmentation for grape bunch detection

Marani R.;Milella A.;Petitti A.;Reina G.
Conceptualization
2019-01-01

Abstract

This paper presents a method for automatic fruit detection in vineyards through the inspection of colour images obtained by a low cost RGB-D sensor placed on-board an agricultural vehicle. Image segmentation is obtained by using a pre-trained convolutional neural network, which receives input data, as sub-patches of known size, and performs the classification in a few classes of interest. Output scores are then used to create the probability maps for each class and, thus, pixel-by-pixel segmentation of the grape clusters. Field experiments prove the ability of the proposed processing to successfully segment grape clusters, with accuracy of 87.5%, despite the poor quality of the input images.
2019
12th European Conference on Precision Agriculture, ECPA 2019
978-90-8686-337-2
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/188712
Citazioni
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact