中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能制造技术与系统研究中心
An Enhanced Feature Pyramid Object Detection Network for Autonomous Driving

文献类型：期刊论文

作者Wu, Yutian2; Tang, Shuming1; Zhang, Shuwei2; Ogai, Harutoshi2
刊名APPLIED SCIENCES-BASEL
出版日期2019-10-01
卷号9期号:20页码:15
关键词object detection feature pyramid network feature recalibration context embedding autonomous driving systems augmented reality
DOI10.3390/app9204363
通讯作者Wu, Yutian(wuyutian@fuji.waseda.jp)
英文摘要Feature Pyramid Network (FPN) builds a high-level semantic feature pyramid and detects objects of different scales in corresponding pyramid levels. Usually, features within the same pyramid levels have the same weight for subsequent object detection, which ignores the feature requirements of different scale objects. As we know, for most detection networks, it is hard to detect small objects and occluded objects because there is little information to exploit. To solve the above problems, we propose an Enhanced Feature Pyramid Object Detection Network (EFPN), which innovatively constructs an enhanced feature extraction subnet and adaptive parallel detection subnet. Enhanced feature extraction subnet introduces Feature Weight Module (FWM) to enhance pyramid features by weighting the fusion feature map. Adaptive parallel detection subnet introduces Adaptive Context Expansion (ACE) and Parallel Detection Branch (PDB). ACE aims to generate the features of adaptively enlarged object context region and original region. PDB predicts classification and regression results separately with the two features. Experiments showed that EFPN outperforms FPN in detection accuracy on Pascal VOC and KITTI datasets. Furthermore, the performance of EFPN meets the real-time requirements of autonomous driving systems.
WOS研究方向Chemistry ; Materials Science ; Physics
语种英语
出版者MDPI
WOS记录号WOS:000496269400166
源URL[http://ir.ia.ac.cn/handle/173211/28902]  
专题自动化研究所_智能制造技术与系统研究中心
通讯作者Wu, Yutian
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Waseda Univ, Grad Sch Informat Prod & Syst, Fukuoka, Fukuoka 8080135, Japan
推荐引用方式
GB/T 7714		 Wu, Yutian,Tang, Shuming,Zhang, Shuwei,et al. An Enhanced Feature Pyramid Object Detection Network for Autonomous Driving[J]. APPLIED SCIENCES-BASEL,2019,9(20):15.
APA Wu, Yutian,Tang, Shuming,Zhang, Shuwei,&Ogai, Harutoshi.(2019).An Enhanced Feature Pyramid Object Detection Network for Autonomous Driving.APPLIED SCIENCES-BASEL,9(20),15.
MLA Wu, Yutian,et al."An Enhanced Feature Pyramid Object Detection Network for Autonomous Driving".APPLIED SCIENCES-BASEL 9.20(2019):15.

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。