SIA OpenIR  > 光电信息技术研究室
基于双模全卷积网络的行人检测算法
Alternative TitlePedestrian detection algorithm based on dual-model fused fully convolutional networks
罗海波; 何淼; 惠斌; 常铮
Department光电信息技术研究室
Source Publication红外与激光工程
ISSN1007-2276
2018
Volume47Issue:2Pages:10-17
Indexed ByEI ; CSCD
EI Accession number20182105214034
CSCD IDCSCD:6207493
Contribution Rank1
Keyword深度学习 弱监督训练 行人检测 语义分割
Abstract

在近距离行人检测任务中,平衡算法的检测精度与检测速度对于检测算法的实际应用有着重要意义。为了快速并准确地检测出近景行人目标,提出了一种基于模型融合全卷积网络的行人检测算法。首先,通过全卷积检测网络对图像中的目标进行检测,得到一系列候选框;其次,通过弱监督训练的语义分割网络得到图像的像素级分类结果;最后,将候选框与像素级分类结果融合,完成检测。实验结果表明:算法在检测速度与精度方面都具有较高的性能。

Other Abstract

In the task of close range pedestrian detection, the balance of the precision and speed were of great significance to the practical application of the detection algorithm. In order to detect the close range target quickly and accurately, a pedestrian detection algorithm based on fused fully convolutional network was proposed. Firstly, a fully convolutional detection network was used to detect the target in the image, and a series of candidate bounding boxes were obtained. Secondly, pixel level classification results of the image were obtained by using a semantic segmentation network with weakly supervised training. Finally, the candidate bounding boxes and the pixel level classification results were fused to complete the detection. The experimental results show that the algorithm has good performance in both the speed and the precision of detection.

Language中文
Citation statistics
Cited Times:3[CSCD]   [CSCD Record]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/21620
Collection光电信息技术研究室
Corresponding Author何淼
Affiliation1.中国科学院沈阳自动化研究所
2.中国科学院大学
3.中国科学院光电信息处理重点实验室
4.辽宁省图像理解与视觉计算重点实验室
Recommended Citation
GB/T 7714
罗海波,何淼,惠斌,等. 基于双模全卷积网络的行人检测算法[J]. 红外与激光工程,2018,47(2):10-17.
APA 罗海波,何淼,惠斌,&常铮.(2018).基于双模全卷积网络的行人检测算法.红外与激光工程,47(2),10-17.
MLA 罗海波,et al."基于双模全卷积网络的行人检测算法".红外与激光工程 47.2(2018):10-17.
Files in This Item: Download All
File Name/Size DocType Version Access License
基于双模全卷积网络的行人检测算法.pdf(800KB)期刊论文作者接受稿开放获取ODC PDDLView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[罗海波]'s Articles
[何淼]'s Articles
[惠斌]'s Articles
Baidu academic
Similar articles in Baidu academic
[罗海波]'s Articles
[何淼]'s Articles
[惠斌]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[罗海波]'s Articles
[何淼]'s Articles
[惠斌]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于双模全卷积网络的行人检测算法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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