Journal of Integrative Agriculture ›› 2012, Vol. 12 ›› Issue (6): 978-985.DOI: 10.1016/S1671-2927(00)8621

• 论文 • 上一篇    下一篇

An Insect Imaging System to Automate Rice Light-Trap Pest Identification

 YAO Qing, LIU Qing-jie, YANG Bao-jun, CHEN Hong-ming, TANG Jian   

  1. 1.College of Informatics and Electronics, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.China
    2.State Key Laboratory of Rice Biology, China National Rice Research Institute, Hangzhou 310006, P.R.China
    3.Xiangshan Agriculture and Forestry Bureau, Ningbo 315700, P.R.China
  • 收稿日期:2011-12-23 出版日期:2012-06-01 发布日期:2012-07-20
  • 通讯作者: TANG Jian, Tel: +86-571-63370331, Fax: +86-571-63370359, E-mail:tangjian@mail.hz.zj.cn
  • 作者简介:YAO Qing, Tel: +86-571-86843324, E-mail: qingyaozstu@gmail.com
  • 基金资助:

    National Natural Science Foundation of China (31071678), the Major Scientific and Technological Special of Zhejiang Province, China (2010C12026), the Ningbo Science and Technology Project, China (201002C1011001) and Xiangshan Science and Technology Project, China (2010C0001).

An Insect Imaging System to Automate Rice Light-Trap Pest Identification

 YAO Qing, LIU Qing-jie, YANG Bao-jun, CHEN Hong-ming, TANG Jian   

  1. 1.College of Informatics and Electronics, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.China
    2.State Key Laboratory of Rice Biology, China National Rice Research Institute, Hangzhou 310006, P.R.China
    3.Xiangshan Agriculture and Forestry Bureau, Ningbo 315700, P.R.China
  • Received:2011-12-23 Online:2012-06-01 Published:2012-07-20
  • Contact: TANG Jian, Tel: +86-571-63370331, Fax: +86-571-63370359, E-mail:tangjian@mail.hz.zj.cn
  • About author:YAO Qing, Tel: +86-571-86843324, E-mail: qingyaozstu@gmail.com
  • Supported by:

    National Natural Science Foundation of China (31071678), the Major Scientific and Technological Special of Zhejiang Province, China (2010C12026), the Ningbo Science and Technology Project, China (201002C1011001) and Xiangshan Science and Technology Project, China (2010C0001).

摘要: Identification and counting of rice light-trap pests are important to monitor rice pest population dynamics and make pest forecast. Identification and counting of rice light-trap pests manually is time-consuming, and leads to fatigue and an increase in the error rate. A rice light-trap insect imaging system is developed to automate rice pest identification. This system can capture the top and bottom images of each insect by two cameras to obtain more image features. A method is proposed for removing the background by color difference of two images with pests and non-pests. 156 features including color, shape and texture features of each pest are extracted into an support vector machine (SVM) classifier with radial basis kernel function. The seven-fold cross-validation is used to improve the accurate rate of pest identification. Four species of Lepidoptera rice pests are tested and achieved 97.5% average accurate rate.

关键词: automatic identification, imaging system, rice light-trap pests, SVM, cross-validate

Abstract: Identification and counting of rice light-trap pests are important to monitor rice pest population dynamics and make pest forecast. Identification and counting of rice light-trap pests manually is time-consuming, and leads to fatigue and an increase in the error rate. A rice light-trap insect imaging system is developed to automate rice pest identification. This system can capture the top and bottom images of each insect by two cameras to obtain more image features. A method is proposed for removing the background by color difference of two images with pests and non-pests. 156 features including color, shape and texture features of each pest are extracted into an support vector machine (SVM) classifier with radial basis kernel function. The seven-fold cross-validation is used to improve the accurate rate of pest identification. Four species of Lepidoptera rice pests are tested and achieved 97.5% average accurate rate.

Key words: automatic identification, imaging system, rice light-trap pests, SVM, cross-validate