All publications from your selection

Download RAW file:
DOI:
Description: Artificial pollination is a heavy-duty task in pear cultivation. This research aims to develop a method to detect pear flowers to be pollinated from camera images, which is planned to mount as a robot vision. Two types of images exist: a distant view image and a close-up view image. Faster R-CNN (Regions with Convolutional Neural Networks) is applied to the distant view images to detect flower clusters. In addition, branch information, that is extracted by a multi-scale filter, in the distant view image is used to improve the accuracy of detection. Then Faster R-CNN is also used for the close-up view images to extract flowers to be pollinated. The Faster R-CNN models are trained by using the pear flower image data collected in real pear fields. The proposed models overperformed the model without the branch information.

Keywords:
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2021-06-11
Technical field:
Conference name: 5th CIGR International Conference and CSBE-SCGAB AGM 2021, Quebec City,QC, 11-14 May 2021.
Session name: World Congress on Computers in Agriculture and Natural Resources (WCCA 2)

Other information:
Type: Text.Abstract
Format:
Publication type: Presentation
Source:
Relation:
Coverage: Japan
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files: