SpikeletFCN: Counting Spikelets from Infield Wheat Crop Images Using Fully Convolutional Networks

Tahani Alkhudaydi, Ji Zhou, Beatriz De La Iglesia

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)
15 Downloads (Pure)

Abstract

Currently, crop management through automatic monitoring is growing momentum, but presents various challenges. One key challenge is to quantify yield traits from images captured automatically. Wheat is one of the three major crops in the world with a total demand expected to exceed 850 million tons by 2050. In this paper we attempt estimation of wheat spikelets from high-definition RGB infield images using a fully convolutional model. We propose also the use of transfer learning and segmentation to improve the model. We report cross validated Mean Absolute Error (MAE) and Mean Square Error (MSE) of 53.0, 71.2 respectively on 15 real field images. We produce visualisations which show the good fit of our model to the task. We also concluded that both transfer learning and segmentation lead to a very positive impact for CNN-based models, reducing error by up to 89%, when extracting key traits such as wheat spikelet counts.
Original languageEnglish
Title of host publicationLecture Notes in Computing Science
PublisherSpringer
Pages3-13
ISBN (Electronic)978-3-030-20912-4
ISBN (Print)978-3-030-20911-7
DOIs
Publication statusPublished - 2019

Publication series

NameArtificial Intelligence and Soft Computing
Volume11508
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Cite this