BUILDING EXTRACTION FROM MULTI-SOURCE REMOTE SENSING IMAGES VIA DEEP DECONVOLUTION NEURAL NETWORKS

被引:111
作者
Huang, Zuming [1 ]
Cheng, Guangliang [1 ]
Wang, Hongzhen [1 ]
Li, Haichang [1 ]
Shi, Limin [1 ]
Pan, Chunhong [1 ]
机构
[1] Chinese Acad Sci CASIA, Inst Automat, NLPR, Beijing, Peoples R China
来源
2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | 2016年
关键词
Building extraction; DeconvNet; multi-source; remote sensing; band combination;
D O I
10.1109/IGARSS.2016.7729471
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Building extraction from remote sensing images is of great importance in urban planning. Yet it is a longstanding problem for many complicate factors such as various scales and complex backgrounds. This paper proposes a novel supervised building extraction method via deep deconvolution neural networks (DeconvNet). Our method consists of three steps. First, we preprocess the multi-source remote sensing images provided by the IEEE GRSS Data Fusion Contest. A high-quality Vancouver building dataset is created on pansharpened images whose ground-truth are obtained from the OpenStreetMap project. Then, we pretrain a deep deconvolution network on a public large-scale Massachusetts building dataset, which is further fine-tuned by two band combinations (RGB and NRG) of our dataset, respectively. Moreover, the output saliency maps of the fine-tuned models are fused to produce the final building extraction result. Extensive experiments on our Vancouver building dataset demonstrate the effectiveness and efficiency of the proposed method. To the best of our knowledge, it is the first work to use deconvolution networks for building extraction from remote sensing images.
引用
收藏
页码:1835 / 1838
页数:4
相关论文
共 11 条
[1]  
[Anonymous], COMPUTER SCI
[2]  
Badrinarayanan V., 2015, SEGNET DEEP CONVOLUT, DOI DOI 10.1109/TPAMI.2016.2644615
[3]   COLOR ENHANCEMENT OF HIGHLY CORRELATED IMAGES .2. CHANNEL RATIO AND CHROMATICITY TRANSFORMATION TECHNIQUES [J].
GILLESPIE, AR ;
KAHLE, AB ;
WALKER, RE .
REMOTE SENSING OF ENVIRONMENT, 1987, 22 (03) :343-365
[4]   Caffe: Convolutional Architecture for Fast Feature Embedding [J].
Jia, Yangqing ;
Shelhamer, Evan ;
Donahue, Jeff ;
Karayev, Sergey ;
Long, Jonathan ;
Girshick, Ross ;
Guadarrama, Sergio ;
Darrell, Trevor .
PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14), 2014, :675-678
[5]   Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1026-1034
[6]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[7]  
Lefvre S., 2007, P URBAN REMOTE SENSI, P1, DOI DOI 10.1109/URS.2007.371825
[8]  
Mnih V, 2013, Machine learning for aerial image labeling, DOI DOI 10.1109/ICCV.2015.178
[9]   THRESHOLD SELECTION METHOD FROM GRAY-LEVEL HISTOGRAMS [J].
OTSU, N .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1979, 9 (01) :62-66
[10]  
Vakalopoulou M, 2015, INT GEOSCI REMOTE SE, P1873, DOI 10.1109/IGARSS.2015.7326158