Fusing multi-scale context-aware information representation for automatic in-field pest detection and recognition

doi:10.1016/j.compag.2020.105222

	Fusing multi-scale context-aware information representation for automatic in-field pest detection and recognition
	Wang, Fangyuan 2,3; Wang, Rujing 2; Xie, Chengjun 2; Yang, Po 1; Liu, Liu 2,3
刊名	COMPUTERS AND ELECTRONICS IN AGRICULTURE
	2020-02-01
卷号	169
关键词	Convolutional neural network Context-aware attention network Multi-projection pest detection model In-field pest in food crop
ISSN号	0168-1699
DOI	10.1016/j.compag.2020.105222
通讯作者	Wang, Rujing(rjwang@iim.ac.cn) ; Xie, Chengjun(cjxie@iim.ac.cn) ; Yang, Po(po.yang@sheffield.ac.uk)
英文摘要	Automatic in-field pest detection and recognition using mobile vision technique is a hot topic in modern intelligent agriculture, but suffers from serious challenges including complexity of wild environment, detection of tiny size pest and classification of multiple classes of pests. While recent deep learning based mobile vision techniques have shown some success in overcoming above issues, one key problem is that towards large-scale multiple species of pest data, imbalanced classes significantly reduce their detection and recognition accuracy. In this paper, we propose a novel two-stages mobile vision based cascading pest detection approach (DeepPest) towards large-scale multiple species of pest data. This approach firstly extracts multi-scale contextual information of the images as prior knowledge to build up a context-aware attention network for initial classification of pest images into crop categories. Then, a multi-projection pest detection model (MDM) is proposed and trained by crop-related pest images. The role of MDM can combine pest contextual information from low-level convolutional layers with these in high-level convolutional layers for generating the super-resolved feature. Finally, we utilize the attention mechanism and data augmentation to improve the effectiveness of in-field pest detection. We evaluate our method on our newly established large-scale dataset In-Field Pest in Food Crop (IPFC) and sufficient experimental results show that DeepPest proposed in this paper outperforms state-of-the-art object detection methods in detecting in-field pest.
资助项目	National Key Technology R&D Program of China[2018YFD0200300] ; National Natural Science Foundation of China[31401293] ; National Natural Science Foundation of China[31671586] ; National Natural Science Foundation of China[61773360] ; Major Special Science and Technology Project of Anhui Province[201903a06020006]
WOS研究方向	Agriculture ; Computer Science
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000517665600048
资助机构	National Key Technology R&D Program of China ; National Natural Science Foundation of China ; Major Special Science and Technology Project of Anhui Province
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/103977]
专题	中国科学院合肥物质科学研究院
通讯作者	Wang, Rujing; Xie, Chengjun; Yang, Po
作者单位	1.Univ Sheffield, Sheffield, S Yorkshire, England 2.Chinese Acad Sci, Inst Intelligent Machines, Hefei Inst Phys Sci, Hefei 230031, Peoples R China 3.Univ Sci & Technol China, Hefei 230026, Peoples R China
推荐引用方式 GB/T 7714	Wang, Fangyuan,Wang, Rujing,Xie, Chengjun,et al. Fusing multi-scale context-aware information representation for automatic in-field pest detection and recognition[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2020,169.
APA	Wang, Fangyuan,Wang, Rujing,Xie, Chengjun,Yang, Po,&Liu, Liu.(2020).Fusing multi-scale context-aware information representation for automatic in-field pest detection and recognition.COMPUTERS AND ELECTRONICS IN AGRICULTURE,169.
MLA	Wang, Fangyuan,et al."Fusing multi-scale context-aware information representation for automatic in-field pest detection and recognition".COMPUTERS AND ELECTRONICS IN AGRICULTURE 169(2020).