Home // eKNOW 2020, The Twelfth International Conference on Information, Process, and Knowledge Management // View article

Shoot Counting System Based on SegNet

Authors:
Funa Ito
Duke Maeda
Naoki Nakamura
Kenta Morita
Naoki Morita

Keywords: SegNet; Segmentation; Shoot; Pruning; Grapes.

Abstract:
In the present paper, we analyze an aerial photograph of a vineyard to count the number of shoots using SegNet, which is a tool for extracting the area of an object. However, occluded object regions make it difficult to recognize the hidden surface. The area of the object in the background is divided into two areas. It is thus necessary to connect the divided areas to obtain the correct number of shoots. Here, we propose a system that combines adjacent pixels and then connects all parts of the segmented area based on the segmentation output.

Pages: 66 to 68

Copyright: Copyright (c) IARIA, 2020

Publication date: March 22, 2020

Published in: conference

ISSN: 2308-4375

ISBN: 978-1-61208-765-8

Location: Valencia, Spain

Dates: from November 21, 2020 to November 25, 2020