CASIA OpenIR  > 综合信息系统研究中心
Cost-Effective Class-Imbalance Aware CNN for Vehicle Localization and Categorization in High Resolution Aerial Images
Li, Feimo1,2; Li, Shuxiao1,2; Zhu, Chengfei1,2; Lan, Xiaosong1,2; Chang, Hongxing1,2; 李非墨,李书晓
Source PublicationREMOTE SENSING
2017-05-01
Volume9Issue:5Pages:494
SubtypeArticle
AbstractJoint vehicle localization and categorization in high resolution aerial images can provide useful information for applications such as traffic flow structure analysis. To maintain sufficient features to recognize small-scaled vehicles, a regions with convolutional neural network features (R-CNN) -like detection structure is employed. In this setting, cascaded localization error can be averted by equally treating the negatives and differently typed positives as a multi-class classification task, but the problem of class-imbalance remains. To address this issue, a cost-effective network extension scheme is proposed. In it, the correlated convolution and connection costs during extension are reduced by feature map selection and bi-partite main-side network construction, which are realized with the assistance of a novel feature map class-importance measurement and a new class-imbalance sensitive main-side loss function. By using an image classification dataset established from a set of traditional real-colored aerial images with 0.13 m ground sampling distance which are taken from the height of 1000 m by an imaging system composed of non-metric cameras, the effectiveness of the proposed network extension is verified by comparing with its similarly shaped strong counter-parts. Experiments show an equivalent or better performance, while requiring the least parameter and memory overheads are required.
KeywordVehicle Localization Vehicle Classification High Resolution Aerial Image Convolutional Neural Network (Cnn) Class Imbalance
WOS HeadingsScience & Technology ; Technology
DOI10.3390/rs9050494
WOS KeywordSCENE CLASSIFICATION ; FEATURES
Indexed BySCI
Language英语
Funding OrganizationNational Science Foundation of China (NSFC)(61302154 ; 61573350)
WOS Research AreaRemote Sensing
WOS SubjectRemote Sensing
WOS IDWOS:000402573700097
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/14579
Collection综合信息系统研究中心
Corresponding Author李非墨,李书晓
Affiliation1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Li, Feimo,Li, Shuxiao,Zhu, Chengfei,et al. Cost-Effective Class-Imbalance Aware CNN for Vehicle Localization and Categorization in High Resolution Aerial Images[J]. REMOTE SENSING,2017,9(5):494.
APA Li, Feimo,Li, Shuxiao,Zhu, Chengfei,Lan, Xiaosong,Chang, Hongxing,&李非墨,李书晓.(2017).Cost-Effective Class-Imbalance Aware CNN for Vehicle Localization and Categorization in High Resolution Aerial Images.REMOTE SENSING,9(5),494.
MLA Li, Feimo,et al."Cost-Effective Class-Imbalance Aware CNN for Vehicle Localization and Categorization in High Resolution Aerial Images".REMOTE SENSING 9.5(2017):494.
Files in This Item: Download All
File Name/Size DocType Version Access License
remotesensing-09-004(4065KB)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
[Li, Feimo]'s Articles
[Li, Shuxiao]'s Articles
[Zhu, Chengfei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Feimo]'s Articles
[Li, Shuxiao]'s Articles
[Zhu, Chengfei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Feimo]'s Articles
[Li, Shuxiao]'s Articles
[Zhu, Chengfei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: remotesensing-09-00494.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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