A two-stage classification approach for the detection of spider mite- infested cotton using UAV multispectral imagery

ABSTRACT Spider mites are important pests that cause severe economic damage to cotton. They feed on underside of leaves, piercing the chloroplast-containing cells, resulting in foliar damage and yield reduction. This paper proposed a two-stage classification approach for mite-infestation detection based on machine learning methods. Two cotton fields were selected for study, and the UAV imagery collection and concurrent ground investigation were conducted on July 20-21th, 2017. Mosaicking and geo-registration were performed on the collected multispectral imagery. Support Vector Machine (SVM) was used for scene classification, and a transferred Convolutional Neural Network (CNN) was applied for mite-infestation identification. Experimental results showed that our method outperformed others in terms of accuracy, which demonstrated that our approach has potential in mite-infestation detection using UAV multispectral imagery.

[1]  Larry D. Godfrey,et al.  Remote Sensing for Detection of Cotton Aphid– (Homoptera: Aphididae) and Spider Mite– (Acari: Tetranychidae) Infested Cotton in the San Joaquin Valley , 2006 .

[2]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[3]  Zhe Xu,et al.  Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a UAV , 2014, Remote. Sens..

[4]  Lloyd T. Wilson,et al.  Within-Plant Distribution of Spider Mites (Acari: Tetranychidae) on Cotton: A Developing Implementable Monitoring Program , 1983 .

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Gérard Dedieu,et al.  Detection of Flavescence dorée Grapevine Disease Using Unmanned Aerial Vehicle (UAV) Multispectral Imagery , 2017, Remote. Sens..

[7]  Stephan J. Maas,et al.  Spider Mite Detection and Canopy Component Mapping in Cotton Using Hyperspectral Imagery and Spectral Mixture Analysis , 2004, Precision Agriculture.

[8]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[9]  Spectral response of spider mite infested cotton: Mite density and miticide rate study , 2013 .

[10]  Arnon Karnieli,et al.  Spectral monitoring of two-spotted spider mite damage to pepper leaves , 2012 .

[11]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton , 2017, Journal of visualized experiments : JoVE.

[14]  B. K. Julsing,et al.  Face Recognition with Local Binary Patterns , 2012 .

[15]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[16]  Heng Zhang,et al.  Building extraction from high-resolution SAR imagery based on deep neural networks , 2017 .