Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Acta Geodaetica et Cartographica Sinica》 2018-06
Add to Favorite Get Latest Update

High Precision Building Detection from Aerial Imagery Using a U-Net Like Convolutional Architecture

WU Guangming;CHEN Qi;Ryosuke SHIBASAKI;GUO Zhiling;SHAO Xiaowei;XU Yongwei;Center for Spatial Information Science,University of Tokyo;Faculty of Information Engineering,China University of Geosciences,Wuhan;  
Automatic identification of the building target and precise acquisition of its vector contour has been an urgent task which is at the same time facing huge challenges.Inrecentyears,due to its ability of automatically extracting high-dimensional abstract features with extremely high complexity,convolutional neural network(CNN)have made considerable improvement in this research area,and strongly enhanced the classification accuracy and generalization capability of the state-of-art building detection methods.However,the pooling layers in a classic CNN model actually considerably reduce the spatial resolution of the input image,the building detection results generated from the top layer of CNN often have coarse edges,which poses big challenges for extracting accurate buildingcontour.Inordertotacklethisproblem,an improved fully convolutional network based on UNet is proposed.First,the structure of U-Net is adopted to detect accurate building edge by using a bottom-up refinement process.Then,by predicting results in both top and bottom layers with the feature pyramid,a twofold constraint strategy is proposed to further improve the detection accuracy.Experiments on aerial imagery datasets covering 30 square kilometers and over 28 000 buildings demonstrate that proposed method performs well for different areas.The accuracy values in the form of average IoU and Kappa are 83.7% and 89.5%,respectively;which are higher than the classic U-Net model,and significantly outperforms the classic full convolutional network model and the AdaBoost model trained with low-level features.
【Fund】: 日本文部科学省GRENE-ei项目;; 国家自然科学基金(41601506);; 中国博士后科学基金(2016M590730)~~
【CateGory Index】: P237;TP183
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved