Frequency-Enhanced Channel-Spatial Attention Module for Grain Pests Classification

Junwei Yu (), Yi Shen, Nan Liu and Quan Pan
Additional contact information
Junwei Yu: School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou 450001, China
Yi Shen: College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China
Nan Liu: Basis Department, PLA Information Engineering University, Zhengzhou 450001, China
Quan Pan: College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China

Agriculture, 2022, vol. 12, issue 12, 1-16

Abstract: For grain storage and protection, grain pest species recognition and population density estimation are of great significance. With the rapid development of deep learning technology, many studies have shown that convolutional neural networks (CNN)-based methods perform extremely well in image classification. However, such studies on grain pest classification are still limited in the following two aspects. Firstly, there is no high-quality dataset of primary insect pests specified by standard ISO 6322-3 and the Chinese Technical Criterion for Grain and Oil-seeds Storage (GB/T 29890). The images of realistic storage scenes bring great challenges to the identification of grain pests as the images have attributes of small objects, varying pest shapes and cluttered backgrounds. Secondly, existing studies mostly use channel or spatial attention mechanisms, and as a consequence, useful information in other domains has not been fully utilized. To address such limitations, we collect a dataset named GP10, which consists of 1082 primary insect pest images in 10 species. Moreover, we involve discrete wavelet transform (DWT) in a convolutional neural network to construct a novel triple-attention network (FcsNet) combined with frequency, channel and spatial attention modules. Next, we compare the network performance and parameters against several state-of-the-art networks based on different attention mechanisms. We evaluate the proposed network on our dataset GP10 and open dataset D0, achieving classification accuracy of 73.79% and 98.16%. The proposed network obtains more than 3% accuracy gains on the challenging dataset GP10 with parameters and computation operations slightly increased. Visualization with gradient-weighted class activation mapping (Grad-CAM) demonstrates that FcsNet has comparative advantages in image classification tasks.

Keywords: grain pest classification; visual attention mechanism; discrete wavelet transform; deep learning; computer vision (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/12/12/2046/pdf (application/pdf)
https://www.mdpi.com/2077-0472/12/12/2046/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:12:y:2022:i:12:p:2046-:d:987911

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().