Feature Refinement Method Based on the Two-Stage Detection Framework for Similar Pest Detection in the Field
Author:
Chen Hongbo12ORCID, Wang Rujing123, Du Jianming2, Chen Tianjiao12, Liu Haiyun12, Zhang Jie12, Li Rui2, Zhou Guotao4
Affiliation:
1. Science Island Branch of Graduate School, University of Science and Technology of China, Hefei 230026, China 2. Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China 3. Institutes of Physical Science and Information Technology, Anhui University, Hefei 230039, China 4. Henan Yunfei Technology Development Co., Ltd., Zhengzhou 450003, China
Abstract
Efficient pest identification and control is critical for ensuring food safety. Therefore, automatic detection of pests has high practical value for Integrated Pest Management (IPM). However, complex field environments and the similarity in appearance among pests can pose a significant challenge to the accurate identification of pests. In this paper, a feature refinement method designed for similar pest detection in the field based on the two-stage detection framework is proposed. Firstly, we designed a context feature enhancement module to enhance the feature expression ability of the network for different pests. Secondly, the adaptive feature fusion network was proposed to avoid the suboptimal problem of feature selection on a single scale. Finally, we designed a novel task separation network with different fusion features constructed for the classification task and the localization task. Our method was evaluated on the proposed dataset of similar pests named SimilarPest5 and achieved a mean average precision (mAP) of 72.7%, which was better than other advanced object detection methods.
Funder
National Natural Science Foundation of China Anhui Province Science and Technology Natural Science Foundation of Anhui Province
Reference48 articles.
1. Oberemok, V.V., Gal’chinsky, N.V., Useinov, R.Z., Novikov, I.A., Puzanova, Y.V., Filatov, R.I., Kouakou, N.J., Kouame, K.F., Kra, K.D., and Laikova, K.V. (2023). Four Most Pathogenic Superfamilies of Insect Pests of Suborder Sternorrhyncha: Invisible Superplunderers of Plant Vitality. Insects, 14. 2. A new pest, Spodoptera frugiperda (JE Smith), in tropical Africa: Its seasonal dynamics and damage in maize fields in northern Ghana;Nboyine;Crop Prot.,2020 3. Babendreier, D., Koku Agboyi, L., Beseh, P., Osae, M., Nboyine, J., Ofori, S.E.K., Frimpong, J.O., Attuquaye Clottey, V., and Kenis, M. (2020). The Efficacy of Alternative, Environmentally Friendly Plant Protection Measures for Control of Fall Armyworm, Spodoptera Frugiperda, in Maize. Insects, 11. 4. Larval Identification of Spodoptera frugiperda and Other Common Species Occurring at Seedling Stage Maize in Henan Province;Li;Chin. J. Biol. Control,2019 5. Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review;Rieder;Comput. Electron. Agric.,2018
|
|