Cross stage partial connections based weighted Bi-directional feature pyramid and enhanced spatial transformation network for robust object detection

doi:10.1016/j.neucom.2022.09.117

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 机器人应用与理论组

	Cross stage partial connections based weighted Bi-directional feature pyramid and enhanced spatial transformation network for robust object detection
	Lu, Yan-Feng 3,4,5; Yu, Qian 3,4,5; Gao, Jing-Wen 3,4,5; Li, Yi 2; Zou, Jun-Cheng 1; Qiao, Hong 3,4,5
刊名	NEUROCOMPUTING
	2022-11-07
卷号	513 页码:70-82
关键词	Robust object detection Structural deformation Image detection Spatial transformation
ISSN号	0925-2312
DOI	10.1016/j.neucom.2022.09.117
通讯作者	Lu, Yan-Feng(yanfeng.lv@ia.ac.cn)
英文摘要	Structural information is an essential component for efficient object detection. In many visual detection tasks, the objects with large structural deformation usually make up a large proportion. The shape, con-tour, and internal structure of the objects tend toward dramatic change, which easily causes troubles for efficient object detection. Therefore, how to detect these objects robustly and accurately is one of the sig-nificant challenges. To address this issue, we introduce a Cross Stage Partial connections-based weighted Bi-directional Feature Pyramid Network (CSP-BiFPN), which allows easy and efficient multi-scale feature fusion by cross-stage partial connections. Second, to enhance the model's spatial transformation capacity, the multi-scale feature maps extracted from the YOLO backbone network are processed by an enhanced spatial transformation network (ESTN) for spatial deformations. Based on these architectural modifica-tions and optimizations, we further develop a novel real-time robust object detection model called Bi-STN-YOLO. We evaluate the performance of the proposed method on four image datasets. The experi-mental results demonstrate that the proposed approach achieves significant improvements compared with the typical YOLO families and competitive performance compared to the state-of-the-arts in detec-tion tasks. (c) 2022 Elsevier B.V. All rights reserved.
资助项目	Beijing Natural Science Foundation ; National Key Research and Development Plan of China ; National Natural Science Foundation of China ; [L211023] ; [2020AAA0105900] ; [91948303]
WOS关键词	ALIGNMENT
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000866415400007
资助机构	Beijing Natural Science Foundation ; National Key Research and Development Plan of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50278]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组
通讯作者	Lu, Yan-Feng
作者单位	1.Huizhou Univ, Sch Elect Informat & Elect Engn, Huizhou 516007, Peoples R China 2.Nanchang Univ, Sch Informat Engn, Nanchang 330031, Peoples R China 3.Chinese Acad Sci, Inst Automation, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 5.Chinese Acad Sci, Inst Automation, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Lu, Yan-Feng,Yu, Qian,Gao, Jing-Wen,et al. Cross stage partial connections based weighted Bi-directional feature pyramid and enhanced spatial transformation network for robust object detection[J]. NEUROCOMPUTING,2022,513:70-82.
APA	Lu, Yan-Feng,Yu, Qian,Gao, Jing-Wen,Li, Yi,Zou, Jun-Cheng,&Qiao, Hong.(2022).Cross stage partial connections based weighted Bi-directional feature pyramid and enhanced spatial transformation network for robust object detection.NEUROCOMPUTING,513,70-82.
MLA	Lu, Yan-Feng,et al."Cross stage partial connections based weighted Bi-directional feature pyramid and enhanced spatial transformation network for robust object detection".NEUROCOMPUTING 513(2022):70-82.