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.

Author Contributions

Prof. Yubin Lan, Jizhong Deng and Sheng Wen designed the experiments; Huasheng Huang, Yan Jiang, Gaoyu Suo and Pengchao Chen conducted the data collection; Jizhong Deng, Huasheng Huang and Aqing Yang performed the data analyzing, code programming and wrote the manuscript; Yubin Lan, Xiaoling Deng and Lei Zhang revised the manuscript.

Additional information

Funding

This work was supported by the Science and Technology Planning Project of Guangdong Province, China (Grant No.2017A020208046), the National Key Research and Development Plan, China (Grant No. 2016YFD0200700), the National Natural Science Fund, China (Grant No. 61675003), the Science and Technology Planning Project of Guangdong Province, China (Grant No. 2017B010117010), and the Science and Technology Planning Project of Guangzhou city, China (Grant No.201707010047).