Towards densely clustered tiny pest detection in the wild environment

doi:10.1016/j.neucom.2021.12.012

HFCAS OpenIR

	Towards densely clustered tiny pest detection in the wild environment
	Du, Jianming 1; Liu, Liu 2; Li, Rui 1; Jiao, Lin 3; Xie, Chengjun1 ; Wang, Rujing1,4
	2022-06-14
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
通讯作者	Liu, Liu(liuliu1993@sjtu.edu.cn)
摘要	Our life is populated with many small-size objects, such as human in aerial images and tiny pests in agriculture. Current generic and small object detection methods are only focus on tackling their sizes rather than distribution. Considering this limitation, we state a Densely Clustered Tiny (DCT) object detection problem using a novel metric Object Density Level (ODL) to measure the object distribution in an image. The DCT problem allows varied densely distributed objects in the real-world captured images. In dealing with the DCT problem, we select two kinds of aphids that usually gather into cliques in the real-world agricultural environment, and build an aphid dataset APHID-4K in our task. Accompanying the DCT task, we propose a novel DCT detection network (DCTDet) to address this challenge. Specifically, a Cluster Region Proposal Network (ClusRPN) is trained to select appropriate densely distributed object cluster regions from images. These candidates are classified into different groups according to their density. A Density Merging and Partition module (DMP) merges and partitions them respectively and finally outputs cluster regions with uniform size and density to a subsequent Local Detector Group (LDG). In addition, we also use Composited Cluster data Generation (CCG) to present a large-scale dataset for ClusRPN optimization for robust training procedure and theoretically analyze their effects in detail. Experiments on APHID-4K and another clustered small object detection dataset VisDrone show that our DCTDet achieves state-of-the-art performance.
关键词	Pest detection Clustered tiny object Small object detection Image dataset
DOI	10.1016/j.neucom.2021.12.012
关键词[WOS]	CLASSIFICATION
收录类别	SCI
语种	英语
资助项目	National Natural Science Foun-dation of China[32171888] ; National Natural Science Foun-dation of China[31671586] ; Youth Foundation of Natural Science Foundation of Anhui Province[1908085QE202]
项目资助者	National Natural Science Foun-dation of China ; Youth Foundation of Natural Science Foundation of Anhui Province
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000796255500005
出版者	ELSEVIER
引用统计	被引频次：14[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.hfcas.ac.cn:8080/handle/334002/130880
专题	中国科学院合肥物质科学研究院
通讯作者	Liu, Liu
作者单位	1.Chinese Acad Sci, Hefei Inst Intelligent Machines, Beijing, Peoples R China 2.Shanghai Jiao Tong Univ, Shanghai, Peoples R China 3.Anhui Univ, Hefei, Peoples R China 4.Univ Sci & Technol China, Hefei, Peoples R China
推荐引用方式 GB/T 7714	Du, Jianming,Liu, Liu,Li, Rui,et al. Towards densely clustered tiny pest detection in the wild environment[J]. NEUROCOMPUTING,2022,490.
APA	Du, Jianming,Liu, Liu,Li, Rui,Jiao, Lin,Xie, Chengjun,&Wang, Rujing.(2022).Towards densely clustered tiny pest detection in the wild environment.NEUROCOMPUTING,490.
MLA	Du, Jianming,et al."Towards densely clustered tiny pest detection in the wild environment".NEUROCOMPUTING 490(2022).