CASIA OpenIR  > 模式识别国家重点实验室  > 先进数据分析与学习
Context-Aware Cascade Network for Semantic Labeling in VHR Image
Yongcheng Liu1,2; Bin Fan1; Jun Bai3; Lingfeng Wang1; Shiming Xiang1; Chunhong Pan1
2017
Conference NameIEEE International Conference on Image Processing
Conference Date2017-9-17
Conference PlaceBeijing, CHINA
AbstractSemantic labeling for the very high resolution (VHR) image of urban areas is challenging, because of many complex manmade objects with different materials and fine-structured objects located together. Under the framework of convolutional neural networks (CNNs), this paper proposes a novel end-toend network for semantic labeling. Specifically, our network not only improves the labeling accuracy of complex manmade objects by aggregating multiple context semantics with a cascaded architecture, but also refines fine-structured objects by utilizing the low-level detail in shallow layers of CNNs with a hierarchical pyramid structure. Throughout the network, a dedicated residual correction scheme is employed to amend the latent fitting residual. As a result of these specific components, the whole model works in a global-to-local and coarseto-fine manner. Experimental results show that our network outperforms the state-of-the-art methods on the large-scale ISPRS Vaihingen 2D Semantic Labeling Challenge dataset.
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20352
Collection模式识别国家重点实验室_先进数据分析与学习
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.School of Computer and Control Engineering, University of Chinese Academy of Sciences
3.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yongcheng Liu,Bin Fan,Jun Bai,et al. Context-Aware Cascade Network for Semantic Labeling in VHR Image[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
16_0000575_ICIP_Liuy(2989KB)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
[Yongcheng Liu]'s Articles
[Bin Fan]'s Articles
[Jun Bai]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yongcheng Liu]'s Articles
[Bin Fan]'s Articles
[Jun Bai]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yongcheng Liu]'s Articles
[Bin Fan]'s Articles
[Jun Bai]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 16_0000575_ICIP_Liuyongcheng_2017.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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