SIA OpenIR  > 光电信息技术研究室
基于改进SSD的轻量化小目标检测算法
Alternative TitleA lightweight small object detection algorithm based on improved SSD
吴天舒1,2; 张志佳1; 刘云鹏2; 裴文慧1; 陈红叶1
Department光电信息技术研究室
Source Publication红外与激光工程
ISSN1007-2276
2018
Volume47Issue:7Pages:1-7
Indexed ByEI ; CSCD
EI Accession number20183805818141
CSCD IDCSCD:6373938
Contribution Rank1
Funding Organization国家自然科学基金(61540069) ; 装发部共用技术课题项目(Y6k4250401)
Keyword目标检测 转置卷积 深度可分离卷积 嵌入式 Pascal Voc数据集 Kitti数据集
Abstract

为提高SSD目标检测算法的小目标检测能力,提出在SSD算法中引入转置卷积结构,采用转置卷积将低分辨率高语义信息特征图与高分辨率低语义信息特征图相融合,增加低层特征提取能力,提高SSD算法的平均精准度。同时针对SSD算法存在模型过大,运行内存占用量过高,无法在嵌入式ARM设备上运行的问题,以DenseNet为基础,结合深度可分离卷积,逐点分组卷积与通道重排提出轻量化特征提取最小单元,将SSD算法特征提取部分替换为轻量化特征提取最小单元的组合后,可在嵌入式ARM设备上运行。在PASCAL VOC数据集和KITTI自动驾驶数据集上进行对比实验,结果表明改进后的网络结构在平均精准度上得到明显提升,模型参数数量得到有效降低。

Other Abstract

In order to improve the small object detection ability of SSD object detection algorithm, the transposed convolution structure in SSD algorithm was proposed, the low resolution high semantic information feature map was integrated with high resolution low semantic information feature map using transposed convolution, which increased the ability of low level feature extraction and improved the average accuracy of SSD algorithm. At the same time for the problem that SSD algorithm model being large, running memory consumption high, without running on the embedded equipment ARM, a lightweight feature extraction minimum unit was proposed based on DenseNet, combining depthwise separable convolutions, pointwise group convolution and channel shuffle, running on the embedded equipment ARM cloud be realized. The comparative experiments on PASCAL VOC data set and KITTI autopilot data set show that the mean average is significantly improved by improved network structure, and the number of model parameters is effectively reduced.

Language中文
Citation statistics
Cited Times:6[CSCD]   [CSCD Record]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/22321
Collection光电信息技术研究室
Corresponding Author张志佳
Affiliation1.沈阳工业大学软件学院
2.中国科学院沈阳自动化研究所
Recommended Citation
GB/T 7714
吴天舒,张志佳,刘云鹏,等. 基于改进SSD的轻量化小目标检测算法[J]. 红外与激光工程,2018,47(7):1-7.
APA 吴天舒,张志佳,刘云鹏,裴文慧,&陈红叶.(2018).基于改进SSD的轻量化小目标检测算法.红外与激光工程,47(7),1-7.
MLA 吴天舒,et al."基于改进SSD的轻量化小目标检测算法".红外与激光工程 47.7(2018):1-7.
Files in This Item:
File Name/Size DocType Version Access License
基于改进SSD的轻量化小目标检测算法.p(556KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[吴天舒]'s Articles
[张志佳]'s Articles
[刘云鹏]'s Articles
Baidu academic
Similar articles in Baidu academic
[吴天舒]'s Articles
[张志佳]'s Articles
[刘云鹏]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[吴天舒]'s Articles
[张志佳]'s Articles
[刘云鹏]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于改进SSD的轻量化小目标检测算法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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