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. 多模态人工智能系统全国重点实验室
  5. 遥感图像处理团队
Dynamic camera configuration learning for high-confidence active object detection

文献类型：期刊论文

作者Xu, Nuo1,2; Huo, Chunlei1,2; Zhang, Xin1,2; Cao, Yong1,2; Meng, Gaofeng1,2,3; Pan, Chunhong2
刊名NEUROCOMPUTING
出版日期2021-11-27
卷号466页码:113-127
关键词Object detection Active object detection Deep reinforcement learning Camera control
ISSN号0925-2312
DOI10.1016/j.neucom.2021.09.037
通讯作者Xu, Nuo(nuo.xu@nlpr.ia.ac.cn)
英文摘要The performance of object detection is closely related to the quality of input images. However, the current image acquisition is purely guided by human visual perception, and such camera imaging process ignores the subsequent application. In this context, detection performance is impacted by imaging configuration and dynamic camera motion. To address the above problems, an active object detection framework is proposed in this paper, which aims to build the bridge between imaging configuration and object detec-tion task. Within the proposed framework, a dynamic camera configuration learning approach is pre-sented based on deep reinforcement learning, where the camera is actively controlled to maximize the detection performance. Through iterated interactions between imaging, control and object detection, the deep gap between perception and cognition in the object detection system is eliminated, and the transformation from physical imaging to purposeful imaging is realized. The effectiveness and advan-tages of the proposed framework are demonstrated in three dynamic environments. (c) 2021 Elsevier B.V. All rights reserved.
资助项目Natural Science Foundation of China[62071466] ; Natural Science Foundation of China[91438105] ; Natural Science Foundation of China[62076242] ; Natural Science Foundation of China[61976208] ; National Key Research and Development Program of China[2018AAA0100400]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000710154200002
出版者ELSEVIER
资助机构Natural Science Foundation of China ; National Key Research and Development Program of China
源URL[http://ir.ia.ac.cn/handle/173211/46282]  
专题自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者Xu, Nuo
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, HK Inst Sci & Innovat, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Xu, Nuo,Huo, Chunlei,Zhang, Xin,et al. Dynamic camera configuration learning for high-confidence active object detection[J]. NEUROCOMPUTING,2021,466:113-127.
APA Xu, Nuo,Huo, Chunlei,Zhang, Xin,Cao, Yong,Meng, Gaofeng,&Pan, Chunhong.(2021).Dynamic camera configuration learning for high-confidence active object detection.NEUROCOMPUTING,466,113-127.
MLA Xu, Nuo,et al."Dynamic camera configuration learning for high-confidence active object detection".NEUROCOMPUTING 466(2021):113-127.

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。