Title: Analysis of off-the-shelf stereo camera system bumblebee XB3 for the fruit volume and leaf area estimation
Authors : Seatovic, Dejan
Meiser, Vincent
Brand, Martin
Scherly, Daniel
Proceedings: Proceedings of the international conference Ag. Eng., AgEng2014
Pages : 1
Pages to: 8
Conference details: AgEng2014 Engineering for Improving Resource Efficiency, Zürich, 6. - 10. Juli 2014
Issue Date: 2014
License (according to publishing contract) : Licence according to publishing contract
Type of review: Peer review (Publication)
Language : English
Subjects : Visual perception; Sensor evaluation
Subject (DDC) : 004: Computer science
Abstract: The paper describes a set of simulated and real-world experiments to determine the total leaf area and fruit volume of a fruit tree using 3-dimensional data gathered from colour stereo images. Initially, the accuracy of the stereo algorithms is determined, and then the method for leaf area computation is developed and tested on particular trees with a known leaf area. Finally, leaf area computation is carried out on a number of images of real fruit trees obtained in the ICT-AGRI project 3D-Mosaic. Furthermore, limitations of the system are shown using the example of fruit volume and leaf area computation from orchard data. Several stereo al-gorithms are compared with regard to their accuracy and performance. The experimental system consisting of several sensors and software components is briefly explained, enabling rebuilding of the system with minimum effort with respect to construction and software devel-opment. Lastly, recommendations are proposed for the scientific and industrial teams inter-ested in similar problems on selecting sensors and open-source and BSD software compo-nents to successfully approach this complex problem.
Departement: School of Engineering
Organisational Unit: Institute of Mechatronic Systems (IMS)
Publication type: Conference Paper
URI: https://digitalcollection.zhaw.ch/handle/11475/7102
Appears in Collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.