In the last few years, intelligent systems have been increasingly adopted in agriculture resulting in a significant increase of productivity and efficiency. Computer Vision plays a critical role in automation of agricultural operations, such as fresh market vegetable harvest and post-harvest. This paper describes current work at the Politecnico of Bari in collaboration with the University of Lecce in the development of vision-based algorithms for agricultural applications. Two case studies are analyzed dealing with radicchio and fennel cultivations, which are both widely grown in Italy. The first case study aims at developing a visual system to detect and localize accurately radicchio plants in the field for robotic harvesting purposes. We call this module the Radicchio Visual Localization (RVL). The second case study deals with post-harvest processing of fennel. A visual identification system is presented which controls a cutting device to remove automatically the parts of fennel unfit for the market, i.e. root and leaves, and produce high-quality market products. We call this module the Fennel Visual Identification (FVI). Both algorithms operate in real time and exploit intelligent color filtering and morphological operations. While the Radicchio Visual Localization deals with a typical eye-in-hand application as it utilizes a camera attached to a moving end-effector, the Fennel Visual Identification employs a ground-fixed camera. An in-depth description of both visual systems is presented along with detailed results obtained in laboratory and field experiments to asses their performance in terms of accuracy, repeatability, and robustness to noise and lighting variations.

Computer Vision Technology for Agricultural Robotics

REINA, GIULIO;
2006

Abstract

In the last few years, intelligent systems have been increasingly adopted in agriculture resulting in a significant increase of productivity and efficiency. Computer Vision plays a critical role in automation of agricultural operations, such as fresh market vegetable harvest and post-harvest. This paper describes current work at the Politecnico of Bari in collaboration with the University of Lecce in the development of vision-based algorithms for agricultural applications. Two case studies are analyzed dealing with radicchio and fennel cultivations, which are both widely grown in Italy. The first case study aims at developing a visual system to detect and localize accurately radicchio plants in the field for robotic harvesting purposes. We call this module the Radicchio Visual Localization (RVL). The second case study deals with post-harvest processing of fennel. A visual identification system is presented which controls a cutting device to remove automatically the parts of fennel unfit for the market, i.e. root and leaves, and produce high-quality market products. We call this module the Fennel Visual Identification (FVI). Both algorithms operate in real time and exploit intelligent color filtering and morphological operations. While the Radicchio Visual Localization deals with a typical eye-in-hand application as it utilizes a camera attached to a moving end-effector, the Fennel Visual Identification employs a ground-fixed camera. An in-depth description of both visual systems is presented along with detailed results obtained in laboratory and field experiments to asses their performance in terms of accuracy, repeatability, and robustness to noise and lighting variations.
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: http://hdl.handle.net/11587/106603
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
social impact