Context-Aware Cascade Network for Semantic Labeling in VHR Image
Yongcheng Liu1,2; Bin Fan1; Jun Bai3; Lingfeng Wang1; Shiming Xiang1; Chunhong Pan1
2017
会议名称IEEE International Conference on Image Processing
会议日期2017-9-17
会议地点Beijing, CHINA
摘要Semantic 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.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/20352
专题模式识别国家重点实验室_先进数据分析与学习
作者单位1.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
推荐引用方式
GB/T 7714
Yongcheng Liu,Bin Fan,Jun Bai,et al. Context-Aware Cascade Network for Semantic Labeling in VHR Image[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
16_0000575_ICIP_Liuy(2989KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yongcheng Liu]的文章
[Bin Fan]的文章
[Jun Bai]的文章
百度学术
百度学术中相似的文章
[Yongcheng Liu]的文章
[Bin Fan]的文章
[Jun Bai]的文章
必应学术
必应学术中相似的文章
[Yongcheng Liu]的文章
[Bin Fan]的文章
[Jun Bai]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 16_0000575_ICIP_Liuyongcheng_2017.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。