Logo image
Back
SC-CAN: Spectral Convolution and Channel Attention Network for wheat stress classification
Journal article   Open access   Peer reviewed

SC-CAN: Spectral Convolution and Channel Attention Network for wheat stress classification

W.N. Khotimah, F. Boussaid, F. Sohel, L. Xu, D. Edwards, X. Jin and M. Bennamoun
Remote Sensing, Vol.14(17), Article 4288
2022
DOI: https://doi.org/10.3390/rs14174288
pdf
SC-CAN.pdfDownloadView
Published (Version of Record)CC BY V4.0,  Open Access
url
Free to Read *No subscription requiredView

Abstract

Biotic and abiotic plant stress (e.g., frost, fungi, diseases) can significantly impact crop production. It is thus essential to detect such stress at an early stage before visual symptoms and damage become apparent. To this end, this paper proposes a novel deep learning method, called Spectral Convolution and Channel Attention Network (SC-CAN), which exploits the difference in spectral responses of healthy and stressed crops. The proposed SC-CAN method comprises two main modules: (i) a spectral convolution module, which consists of dilated causal convolutional layers stacked in a residual manner to capture the spectral features; (ii) a channel attention module, which consists of a global pooling layer and fully connected layers that compute inter-relationship between feature map channels before scaling them based on their importance level (attention score). Unlike standard convolution, which focuses on learning local features, the dilated convolution layers can learn both local and global features. These layers also have long receptive fields, making them suitable for capturing long dependency patterns in hyperspectral data. However, because not all feature maps produced by the dilated convolutional layers are important, we propose a channel attention module that weights the feature maps according to their importance level. We used SC-CAN to classify salt stress (i.e., abiotic stress) on four datasets (Chinese Spring (CS), Aegilops columnaris (co(CS)), Ae. speltoides auchery (sp(CS)), and Kharchia datasets) and Fusarium head blight disease (i.e., biotic stress) on Fusarium dataset. Reported experimental results show that the proposed method outperforms existing state-of-the-art techniques with an overall accuracy of 83.08%, 88.90%, 82.44%, 82.10%, and 82.78% on CS, co(CS), sp(CS), Kharchia, and Fusarium datasets, respectively.

Details

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#2 Zero Hunger

Metrics

40 File views/ downloads
72 Record Views
11 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types
Domestic collaboration
International collaboration
Citation topics
4 Electrical Engineering, Electronics & Computer Science
4.169 Remote Sensing
4.169.91 Vegetation Mapping
Web Of Science research areas
Environmental Sciences
Geosciences, Multidisciplinary
Imaging Science & Photographic Technology
Remote Sensing
ESI research areas
Geosciences
Logo image