Impact Factor 4.106 | CiteScore 4.47
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Plant Sci. | doi: 10.3389/fpls.2019.01176

DeepCount: In-Field Automatic Quantification of Wheat Spikes Using Simple Linear Iterative Clustering and Deep Convolutional Neural Networks

  • 1Rothamsted Research (BBSRC), United Kingdom
  • 2Limagrain (France), France

Crop yield is an essential measure for breeders, researchers and farmers and is comprised of and may be calculated by the number of ears/m2, grains per ear and thousand grain weight. Manual wheat ear counting, required in breeding programmes to evaluate crop yield potential, is labour intensive and expensive; thus, the development of a real-time wheat head counting system would be a significant advancement.
In this paper, we propose a computationally efficient system called DeepCount to automatically identify and count the number of wheat spikes in digital images taken under the natural fields conditions. The proposed method tackles wheat spike quantification by segmenting an image into superpixels using Simple Linear Iterative Clustering (SLIC), deriving canopy relevant features, and then constructing a rational feature model fed into the deep Convolutional Neural Network (CNN) classification for semantic segmentation of wheat spikes. As the method is based on a deep learning model, it replaces hand-engineered features required for traditional machine learning methods with more efficient algorithms.
The method is tested on digital images taken directly in the field at different stages of ear emergence/maturity (using visually different wheat varieties), with different canopy complexities (achieved through varying nitrogen inputs), and different heights above the canopy under varying environmental conditions. In addition, the proposed technique is compared with a wheat ear counting method based on a previously developed edge detection technique and morphological analysis. The proposed approach is validated with image-based ear counting and ground-based measurements. The results demonstrate that the DeepCount technique has a high level of robustness regardless of variables such as growth stage and weather conditions, hence demonstrating the feasibility of the approach in real scenarios.
The system is a leap towards a portable and smartphone assisted wheat ear counting systems, results in reducing the labour involved and is suitable for high-throughput analysis. It may also be adapted to work on RGB images acquired from UAVs.

Keywords: wheat ear counting, crop yield, deep learning in agriculture, Semantic segmentation, Superpixels, phenotyping, automated phenotyping system, Machine learning in agriculture

Received: 18 Apr 2019; Accepted: 28 Aug 2019.

Copyright: © 2019 Sadeghi-Tehran, Virlet, Ampe, Reyns and Hawkesford. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Dr. Pouria Sadeghi-Tehran, Rothamsted Research (BBSRC), Harpenden, United Kingdom, pouria.sadeghi-tehran@rothamsted.ac.uk