SIA OpenIR  > 空间自动化技术研究室
Active Object Detection Using Double DQN and Prioritized Experience Replay
Han XN(韩小宁)1; Liu H(刘华平)2; Sun FC(孙富春)2; Yang, Dongfang3
Department空间自动化技术研究室
Conference Name2018 International Joint Conference on Neural Networks, IJCNN 2018
Conference DateJuly 8-13, 2018
Conference PlaceRio de Janeiro, Brazil
Source PublicationProceedings of the International Joint Conference on Neural Networks
PublisherIEEE
Publication PlaceNew York
2018
Pages1-7
Indexed ByEI
EI Accession number20184706086233
Contribution Rank1
ISBN978-1-5090-6014-6
AbstractVisual object detection is one of the fundamental tasks in computer vision and robotics. Small scale, partial capture and occlusion often occur in robotic applications, most existing object detection algorithms perform poorly in such situations. While a robot can look at one object from different views and plan its trajectory in the next few steps, which can lead to better observations. We formulate it as a sequential action-decision process, and develop a deep reinforcement learning architecture to solve the active object detection problem. A double deep Q-learning network (DQN) is applied to predict an action at each step. Experimental validation on the Active Vision Dataset shows the efficiency of the proposed method.
Language英语
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/23592
Collection空间自动化技术研究室
Corresponding AuthorHan XN(韩小宁)
Affiliation1.Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang, China
2.Department of Computer Science and Technology, Tsinghua University, Beijing, China
3.Xi'An High Tech Research Institution, China
Recommended Citation
GB/T 7714
Han XN,Liu H,Sun FC,et al. Active Object Detection Using Double DQN and Prioritized Experience Replay[C]. New York:IEEE,2018:1-7.
Files in This Item: Download All
File Name/Size DocType Version Access License
Active Object Detect(9517KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Han XN(韩小宁)]'s Articles
[Liu H(刘华平)]'s Articles
[Sun FC(孙富春)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Han XN(韩小宁)]'s Articles
[Liu H(刘华平)]'s Articles
[Sun FC(孙富春)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Han XN(韩小宁)]'s Articles
[Liu H(刘华平)]'s Articles
[Sun FC(孙富春)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Active Object Detection Using Double DQN and Prioritized Experience Replay.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.