Auto‐identification of two Sitophilus sibling species on stored wheat using deep convolutional neural network

Haiying Yang; Huiyi Zhao; Dufeng Zhang; Yang Cao; Shyh Wei Teng; Shaoning Pang; Xiaoguang Zhou; Yanyu Li

doi:10.1002/ps.6810

journal article Feb 10, 2022

Auto‐identification of two Sitophilus sibling species on stored wheat using deep convolutional neural network

Haiying Yang Huiyi Zhao

Dufeng Zhang Yang Cao

Shyh Wei Teng

Shaoning Pang Xiaoguang Zhou Yanyu Li

Pest Management Science Vol. 78 No. 5 pp. 1925-1937 · Wiley

View at Publisher Save 10.1002/ps.6810

Abstract

AbstractBACKGROUNDSitophilus oryzae and Sitophilus zeamais are the two main insect pests that infest stored grain worldwide. Accurate and rapid identification of the two pests is challenging because of their similar appearances. The S. zeamais adults are darker and shinier than S. oryzae in visible light. Convolutional neural network (CNN) can be applied for the effective differentiation due to its high effectiveness in object recognition.RESULTSWe propose a multilayer convolutional structure (MCS) feature extractor to extract insect characteristics within each layer of the CNN architecture. A region proposal network is adopted to determine the location of a potential pest in the wheat background. The precision of classification and the robustness of bounding box regression are increased by including deeper layer variables into the classification and bounding box regression subnets, as well as combining loss functions softmax and smooth L1. The proposed multilayer convolutional structure network (MCSNet) achieves the mean average precision of 87.89 ± 2.36% from the laboratory test, with an average detection speed of 0.182 ± 0.005 s per test. The model was further assessed with the field trials, and the obtained accuracy was 90.35 ± 3.12%. For all test conditions, the average precision for S. oryzae was higher than that for S. zeamais.CONCLUSIONThe proposed MCSNet model has demonstrated that it is a fast and accurate method for detecting sibling species from visible light images in both laboratory and field trials. This will ultimately be applied for pest management together with an upgraded industrial camera system, which has been installed in over 100 000 grain depots of China.

Topics

No keywords indexed for this article. Browse by subject →

References

48

[1]

10.1007/978-3-662-56125-6_1

[2]

Highland HA (1991)

[3]

Demissie G "Importance of husk covering on field infestation of maize by Sitophilus zeamais Motsch (Coleoptera: Curculionidae) at Bako, Western Ethiopia" Afric J Biotechnol (2008)

[4]

10.1590/s1519-566x2009000300017

[5]

10.1016/0022-474x(71)90014-2

[6]

10.1093/jee/65.2.434

[7]

10.1016/j.cropro.2012.12.010

[8]

10.5897/ajb09.821

[9]

10.1603/an10011

[10]

Rodrigues HE "Attractiveness of light‐emitting diodes (LEDs) of different wavelengths to the south American rice water weevil" Arq Inst Biol (2018)

[11]

10.1007/s13765-015-0056-4

[12]

10.1007/s13765-012-0006-3

[13]

10.1046/j.1570-7458.2003.00085.x

[14]

10.1016/0022-474x(94)00043-s

[15]

10.1016/s0022-474x(98)00017-4

[16]

10.1016/0022-474x(86)90041-x

[17]

10.1016/j.jspr.2017.08.004

[18]

10.1093/aesa/89.5.645

[19]

10.1016/s0022-474x(01)00056-x

[20]

10.1002/ps.3893

[21]

10.1016/j.compag.2017.11.039

[22]

10.1109/access.2020.3021830

[23]

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Shaoqing Ren, Kaiming He, Ross Girshick et al.

IEEE Transactions on Pattern Analysis and Machine... 10.1109/tpami.2016.2577031

[24]

Girshick R "Fast R‐CNN" IEEE Comput Soc (2015)

[25]

Girshick R "Rich features hierarchies for accurate object detection and semantic segmentation" IEEE Comput Soc (2014)

[26]

HadjiI&WildesRPWhat Do we Understand about Convolutional Networks? 2018. Available:https://arxiv.org/pdf/1803.08834.pdf[accessed 12 June 2020].

[27]

10.1109/access.2019.2909522

[28]

10.1038/s41598-018-38343-3

[29]

10.1016/j.compag.2016.02.003

[30]

Kumar R (2017) 10.1201/9781315365695

[31]

The Pascal Visual Object Classes (VOC) Challenge

Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al.

International Journal of Computer Vision 10.1007/s11263-009-0275-4

[32]

Bengio Y "No unbiased estimator of the variance of k‐fold cross‐validation" J Mach Learn Res (2004)

[33]

SimonyanKandZissermanA Very deep convolutional networks for large‐scale image recognition. arXiv:1409.1556 [cs.CV] (2015).http://arXiv.org/abs/1409.1556

[34]

Glorot X "Deep sparse rectifier neural networks" J Mach Learn Res (2011)

[35]

Fürnkranz J (2010)

[36]

Efthimiadis EN (2006)

[37]

Paiva AC (2020)

[38]

KingmaDandBaJ Adam: A Method for Stochastic Optimization 2015. Available:https://arxiv.org/pdf/1412.6980v8.pdf[accessed 21 April 2019]

[39]

Glorot X "Understanding the difficulty of training deep feedforward neural networks" J Mach Learn Res (2010)

[40]

O’Conner L (2015)

[41]

Deng J (2009)

[42]

10.1093/aesa/62.1.169

[43]

Goodfellow I (2016)

[44]

Recent advances in convolutional neural networks

Jiuxiang Gu, Zhenhua Wang, Jason Kuen et al.

Pattern Recognition 10.1016/j.patcog.2017.10.013

[45]

David R (2007) 10.1071/9780643094673

[46]

Deep learning models for plant disease detection and diagnosis

Konstantinos P. Ferentinos

Computers and Electronics in Agriculture 10.1016/j.compag.2018.01.009

[47]

Using Deep Learning for Image-Based Plant Disease Detection

Sharada P. Mohanty, David P. Hughes, Marcel Salathé

Frontiers in Plant Science 10.3389/fpls.2016.01419

[48]

10.1016/j.tifs.2006.06.005

Metrics

7

Citations

48

References

Details

Published: Feb 10, 2022
Vol/Issue: 78(5)
Pages: 1925-1937
License: View

Authors

H

Haiying Yang

Department of Automation Beijing University of Posts and Telecommunications Beijing P. R. China; Institute for Grain Storage and Logistics Academy of National Food and Strategic Reserves Administration Beijing P. R. China

H

Huiyi Zhao

Institute for Grain Storage and Logistics Academy of National Food and Strategic Reserves Administration Beijing P. R. China

D

Dufeng Zhang

Sinograin Chengdu Depot Co.Ltd Chengde Grain Depot, Sinograin Hebei P. R. China

Y

Yang Cao

Institute for Grain Storage and Logistics Academy of National Food and Strategic Reserves Administration Beijing P. R. China; China‐Australia Joint Centre for Postharvest Grain Biosecurity and Quality Research Beijing P. R. China

S

Shyh Wei Teng

School of Engineering, Information Technology and Physical Sciences Federation University Australia Mount Helen Australia

S

Shaoning Pang

School of Engineering, Information Technology and Physical Sciences Federation University Australia Mount Helen Australia

X

Xiaoguang Zhou

Department of Automation Beijing University of Posts and Telecommunications Beijing P. R. China

Y

Yanyu Li

Institute for Grain Storage and Logistics Academy of National Food and Strategic Reserves Administration Beijing P. R. China; China‐Australia Joint Centre for Postharvest Grain Biosecurity and Quality Research Beijing P. R. China

Funding

Murdoch University

China Agricultural University

Cite This Article

Haiying Yang, Huiyi Zhao, Dufeng Zhang, et al. (2022). Auto‐identification of two Sitophilus sibling species on stored wheat using deep convolutional neural network. Pest Management Science, 78(5), 1925-1937. https://doi.org/10.1002/ps.6810

Auto‐identification of two Sitophilus sibling species on stored wheat using deep convolutional neural network

You May Also Like