FII-CenterNet: An Anchor-Free Detector With Foreground Attention for Traffic Object Detection
文献类型：期刊论文
| 作者 | Fan, Siqi2,3,4 ; Zhu, Fenghua3,5; Chen, Shichao3,6; Zhang, Hui2,3; Tian, Bin3; Lv, Yisheng3; Wang, Fei-Yue1,3
|
| 刊名 | IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
 |
| 出版日期 | 2021 |
| 卷号 | 70期号:1页码:121-132 |
| ISSN号 | 0018-9545 |
| 关键词 | Feature extraction Object detection Detectors Proposals Convolution Semantics Estimation Anchor-free detector foreground region proposal object detection |
| DOI | 10.1109/TVT.2021.3049805 |
| 通讯作者 | Zhu, Fenghua(fenghua.zhu@ia.ac.cn) |
| 英文摘要 | Most successful object detectors are anchor-based, which is difficult to adapt to the diversity of traffic objects. In this paper, we propose a novel anchor-free method, called FII-CenterNet, which introduces the foreground information to eliminate the interference of the complex background information in traffic scenes. The foreground region proposal network segments the foreground based on boxes-induced segmentation annotation, and midground is proposed to provide rich edge information of the objects. In addition to foreground location, scale information is also introduced to improve the regression performance. Extensive experimental results on two public datasets verify the benefits of the introduction of the foreground information, and demonstrate that our FII-CenterNet achieves the state-of-the-art performance in both accuracy and efficiency. |
| 资助项目 | National Key R&D Program of China[2018YFB1004803] ; NSFC[U1811463] ; NSFC[U1909204] ; NSFC[61773381] ; NSFC[61876011] ; Guandong Grant[2019B1515120030] ; China Railway[N2019G020] ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles |
| WOS研究方向 | Engineering ; Telecommunications ; Transportation |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:000617762400009 |
| 资助机构 | National Key R&D Program of China ; NSFC ; Guandong Grant ; China Railway ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles |
| 源URL | [http://ir.ia.ac.cn/handle/173211/43171]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
| 通讯作者 | Zhu, Fenghua |
| 作者单位 | 1.Macau Univ Sci & Technol, Inst Syst Engn, Macau 999078, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 4.China Nucl Power Engn Co Ltd, State Key Lab Nucl Power Safety Monitoring Techno, Shenzhen 518172, Peoples R China 5.Qingdao Acad Intelligent Ind, Qingdao 266109, Peoples R China 6.Macau Univ Sci & Technol, Fac Informat Technol, Macau 999078, Peoples R China |
| 推荐引用方式 GB/T 7714 | Fan, Siqi,Zhu, Fenghua,Chen, Shichao,et al. FII-CenterNet: An Anchor-Free Detector With Foreground Attention for Traffic Object Detection[J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY,2021,70(1):121-132. |
| APA | Fan, Siqi.,Zhu, Fenghua.,Chen, Shichao.,Zhang, Hui.,Tian, Bin.,...&Wang, Fei-Yue.(2021).FII-CenterNet: An Anchor-Free Detector With Foreground Attention for Traffic Object Detection.IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY,70(1),121-132. |
| MLA | Fan, Siqi,et al."FII-CenterNet: An Anchor-Free Detector With Foreground Attention for Traffic Object Detection".IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 70.1(2021):121-132. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。