S-RPN: Sampling-balanced region proposal network for small crop pest detection

doi:10.1016/j.compag.2021.106290

	S-RPN: Sampling-balanced region proposal network for small crop pest detection
	Wang, Rujing 1; Jiao, Lin 1,3; Xie, Chengjun 1; Chen, Peng 2; Du, Jianming 1; Li, Rui 1,3
刊名	COMPUTERS AND ELECTRONICS IN AGRICULTURE
	2021-08-01
卷号	187
关键词	Deep learning Object detection Small pests Attention mechanism Region proposals
ISSN号	0168-1699
DOI	10.1016/j.compag.2021.106290
通讯作者	Jiao, Lin(linj93@mail.ustc.edu.cn) ; Xie, Chengjun(cjxie@iim.ac.cn)
英文摘要	Effective pest management and control are the key factors in the agricultural food safety field. Therefore, the automatic monitoring and precise recognition of crop pests have a high practical value in the process of agricultural planting. Over the years, pest recognition and detection results have been rapidly improved with the development of deep learning-based methods. Although promising, these methods still have limited efficiency and precision to detect crop pests with very small scales, deteriorating their effectiveness. The main reason is that current deep learning-based methods may not be able to extract sufficient detailed appearance features for small pest objects in an image, making it difficult to train a classifier to detect and distinguish small pests from the backgrounds or similar objects. To address the small pest recognition and detection problem, in this paper, we instead seek to recast the current region proposal network and perform more details in different scales for easier small pest detection. Inspired by the visual attention system, we first introduce attention mechanism into the Residual network for obtaining richer pest feature appearance, especially the detailed features of small object pests; Then, to make the region proposal network (RPN) obtain more high-quality object proposals for easier detection, a sampling-balanced region proposal generation network is proposed for improving pest detection accuracy. Furthermore, we devise a novel adaptive region of interest (RoI) selection method to learn features from different levels of the feature pyramid. Several experiments were conducted on the proposed AgriPest21 dataset, and our method can achieve an average recall of 89.0% and mAP of 78.7%, outperforming other state-ofthe-art methods, including SSD, RetinaNet, Free-Anchor, PISA, Grid RCNN, and Cascade RCNN detectors.
资助项目	national natural science foundation of China[31671586] ; 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:000696624000004
资助机构	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/334002/124859]
专题	中国科学院合肥物质科学研究院
通讯作者	Jiao, Lin; Xie, Chengjun
作者单位	1.Chinese Acad Sci, Hefei Inst Phys Sci, Inst Intelligent Machines, Hefei, Peoples R China 2.Anhui Univ, Hefei, Peoples R China 3.Univ Sci & Technol China, Hefei, Peoples R China
推荐引用方式 GB/T 7714	Wang, Rujing,Jiao, Lin,Xie, Chengjun,et al. S-RPN: Sampling-balanced region proposal network for small crop pest detection[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2021,187.
APA	Wang, Rujing,Jiao, Lin,Xie, Chengjun,Chen, Peng,Du, Jianming,&Li, Rui.(2021).S-RPN: Sampling-balanced region proposal network for small crop pest detection.COMPUTERS AND ELECTRONICS IN AGRICULTURE,187.
MLA	Wang, Rujing,et al."S-RPN: Sampling-balanced region proposal network for small crop pest detection".COMPUTERS AND ELECTRONICS IN AGRICULTURE 187(2021).