Candidate box fusion based approach to adjust position of the candidate box for object detection

doi:10.1049/ipr2.12264

	Candidate box fusion based approach to adjust position of the candidate box for object detection
	Cao, Jie 1,2,3; Ren, Wei 2; Zhang, Hong 1,3; Chen, Zuohan 1,3
刊名	IET IMAGE PROCESSING
	2021-10
卷号	15 期号:12 页码:2799-2809
关键词	Deep learning Object recognition CNN models Detection accuracy Detection framework Fusion methods Generalization ability Object detection method Selection methods Selection stages
ISSN号	1751-9659
DOI	10.1049/ipr2.12264
英文摘要	The method of object detection has been applied to all aspects in our lives. Although object detection methods based on deep learning have been widely used in various fields, there are still some overlooked problems in the candidate box selection stage. The detection results of traditional candidate box selection methods can only select a relatively optimal maximum candidate box. If the maximum candidate box is still not accurate enough, this type of methods will not be able to do adjust it. To solve this problem, an object detection method based on the multiple candidate box fusion is proposed. The method can not only retain the maximum candidate box and delete the non-maximum candidate box, but also adjust the position of the maximum candidate box again. Thereby a more accurate maximum candidate box can be obtained. In order to verify the generalization ability of the method, the candidate box fusion method is combined with the two object detection frameworks: faster R-CNN model and YOLOv3 model. The results of these experiments prove that the proposed method can achieve higher detection accuracy and complete the object detection task more effectively.
WOS研究方向	Computer Science ; Engineering ; Imaging Science & Photographic Technology
语种	英语
出版者	WILEY
WOS记录号	WOS:000664989600001
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/148735]
专题	计算机与通信学院兰州理工大学
作者单位	1.Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou 730050, Peoples R China; 2.Lanzhou Univ Technol, Sch Elect & Informat Engn, Lanzhou 730050, Peoples R China; 3.Engn Res Ctr Urban Railway Transportat Gansu Prov, Urban Railway Transportat, Lanzhou 730050, Peoples R China
推荐引用方式 GB/T 7714	Cao, Jie,Ren, Wei,Zhang, Hong,et al. Candidate box fusion based approach to adjust position of the candidate box for object detection[J]. IET IMAGE PROCESSING,2021,15(12):2799-2809.
APA	Cao, Jie,Ren, Wei,Zhang, Hong,&Chen, Zuohan.(2021).Candidate box fusion based approach to adjust position of the candidate box for object detection.IET IMAGE PROCESSING,15(12),2799-2809.
MLA	Cao, Jie,et al."Candidate box fusion based approach to adjust position of the candidate box for object detection".IET IMAGE PROCESSING 15.12(2021):2799-2809.