CASIA OpenIR  > 智能感知与计算研究中心
Fast Object Detection at Constrained Energy
Jingyu Liu1; Yongzhen Huang1; Junran Peng1; Jun Yao2; Liang Wang1
Source PublicationIEEE Trans. on Emerging Topics in Computing
2016
Issue1-1Pages:99
Abstract
Visual computing, e.g., automatic object detection, in mobile
devices attracts more and more attention recently, in which fast models
at constrained energy cost is a critical problem. In this paper, we
introduce our work on designing models based on deep learning for
200 classes object detection in mobile devices, as well as exploring
trade-off between accuracy and energy cost. In particular, we investigate
several methods of extracting object proposals and integrate them into
the fast-RCNN framework for object detection. Extensive experiments
are conducted using the Jetson TK1 SOC platform and the Alienware-15 laptop, including detailed parameters evaluation with respect to
accuracy, energy cost and speed. From these experiments, we conclude
how to obtain good balance between accuracy and energy cost, which
might provide guidance to design effective and efficient object detection
models on mobile devices.
KeywordObject Detection Constrained Energy Fast-rcnn
WOS IDWOS:000443894400010
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19701
Collection智能感知与计算研究中心
Affiliation1.中科院自动化所
2.华为有限公司
Recommended Citation
GB/T 7714
Jingyu Liu,Yongzhen Huang,Junran Peng,et al. Fast Object Detection at Constrained Energy[J]. IEEE Trans. on Emerging Topics in Computing,2016(1-1):99.
APA Jingyu Liu,Yongzhen Huang,Junran Peng,Jun Yao,&Liang Wang.(2016).Fast Object Detection at Constrained Energy.IEEE Trans. on Emerging Topics in Computing(1-1),99.
MLA Jingyu Liu,et al."Fast Object Detection at Constrained Energy".IEEE Trans. on Emerging Topics in Computing .1-1(2016):99.
Files in This Item: Download All
File Name/Size DocType Version Access License
paper-v3.pdf(2002KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jingyu Liu]'s Articles
[Yongzhen Huang]'s Articles
[Junran Peng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jingyu Liu]'s Articles
[Yongzhen Huang]'s Articles
[Junran Peng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jingyu Liu]'s Articles
[Yongzhen Huang]'s Articles
[Junran Peng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: paper-v3.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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