基于U型卷积神经网络的航空影像建筑物检测

doi:10.11947/j.AGCS.2018.20170651

测绘学报 ›› 2018, Vol. 47 ›› Issue (6): 864-872.doi: 10.11947/j.AGCS.2018.20170651

• 数字摄影测量与深度学习方法 • 上一篇下一篇

基于U型卷积神经网络的航空影像建筑物检测

伍广明¹, 陈奇^1,2, Ryosuke SHIBASAKI¹, 郭直灵¹, 邵肖伟¹, 许永伟¹

1. 东京大学空间信息科学研究中心, 日本东京 113-8657;
2. 中国地质大学(武汉)信息工程学院, 湖北武汉 430074

收稿日期:2017-12-12 修回日期:2018-03-25 出版日期:2018-06-20 发布日期:2018-06-21
通讯作者: 邵肖伟 E-mail:shaoxw@iis.u-tokyo.ac.jp
作者简介:伍广明(1991-),男,博士生,研究方向为计算机视觉和人流模式分析。E-mail:huster-wgm@csis.u-tokyo.ac.jp
基金资助:
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）

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

WU Guangming¹, CHEN Qi^1,2, Ryosuke SHIBASAKI¹, GUO Zhiling¹, SHAO Xiaowei¹, XU Yongwei¹

1. Center for Spatial Information Science, University of Tokyo, Tokyo 113-8657, Japan;
2. Faculty of Information Engineering, China University of Geosciences, Wuhan 430074, China

Received:2017-12-12 Revised:2018-03-25 Online:2018-06-20 Published:2018-06-21
Supported by:
The GRENE-ei (Green Network of Excellence,Environmental Information) Program;The National Natural Science Foundation of China (No.41601506);The China Postdoctoral Science Foundation (No.2016M590730)

摘要/Abstract

摘要： 经典的卷积神经网络结构在前向传播过程中分辨率不断下降，导致仅采用末层特征时难以实现建筑物边缘的精确分割，进而限制目标检测精度。针对该问题，提出一种基于U型卷积网络的建筑物检测方法。首先借鉴在图像分割领域中性能出色的神经网络模型U-Net的建模思想，采用对称式的网络结构融合深度网络中的高维和低维特征以恢复高保真边界；其次考虑到经典U-Net对位于特征金字塔顶层的模型参数优化程度相对不足，通过在顶层和底层两个不同尺度输出预测结果进行双重约束，进一步提升了建筑物检测精度。在覆盖范围达30 km²、建筑物目标28 000余个的航空影像数据集上的试验结果表明，本文方法的检测结果在IoU和Kappa两项关键评价指标的均值上分别达到83.7%和89.5%，优于经典U-Net模型，显著优于经典全卷积网络模型和基于人工设计特征的AdaBoost模型。

关键词: 航空影像, 建筑物检测, 卷积神经网络, U型卷积网络, 特征金字塔

Abstract: 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.In recent years,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 building contour.In order to tackle this problem,an improved fully convolutional network based on U-Net 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.

Key words: aerial imagery, building detection, convolutional neural network, U-Net, feature pyramid

中图分类号:

P237

伍广明, 陈奇, Ryosuke SHIBASAKI, 郭直灵, 邵肖伟, 许永伟. 基于U型卷积神经网络的航空影像建筑物检测[J]. 测绘学报, 2018, 47(6): 864-872.

WU Guangming, CHEN Qi, Ryosuke SHIBASAKI, GUO Zhiling, SHAO Xiaowei, XU Yongwei. High Precision Building Detection from Aerial Imagery Using a U-Net Like Convolutional Architecture[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6): 864-872.

参考文献

[1] HUERTAS A, NEVATIA R. Detecting Buildings in Aerial Images[J]. Computer Vision, Graphics, and Image Processing, 1988, 41(2):131-152.
[2] MCGLONE C, SHUFELT J A. Projective and Object Space Geometry for Monocular Building Extraction[C]//IEEE Computer Society Conference Computer Vision and Pattern Recognition. Seattle, WA:IEEE, 1994.
[3] PESARESI M, GERHARDINGER A, KAYITAKIRE F. A Robust Built-up Area Presence Index by Anisotropic Rotation-invariant Textural Measure[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2008, 1(3):180-192.
[4] 林祥国, 张继贤. 面向对象的形态学建筑物指数及其高分辨率遥感影像建筑物提取应用[J]. 测绘学报, 2017, 46(6):724-733. DOI:10.11947/j.AGCS.2017.20170068. LIN Xiangguo, ZHANG Jixian. Object-based Morphological Building Index for Building Extraction from High Resolution Remote Sensing Imagery[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(6):724-733. DOI:10.11947/j.AGCS.2017.20170068.
[5] PENG J, LIU Y C. Model and Context-driven Building Extraction in Dense Urban Aerial Images[J]. International Journal of Remote Sensing, 2005, 26(7):1289-1307.
[6] LHOMME S, HE Dongchen, WEBER C, et al. A New Approach to Building Identification from Very-high-spatial-resolution Images[J]. International Journal of Remote Sensing, 2009, 30(5):1341-1354.
[7] INGLADA J. Automatic Recognition of Man-made Objects in High Resolution Optical Remote Sensing Images by SVM Classification of Geometric Image Features[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2007, 62(3):236-248.
[8] AYTEKIN Ö, ZÖNGVR U, HALICI U. Texture-based Airport Runway Detection[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(3):471-475.
[9] DONG Yanni, DU Bo, ZHANG Liangpei. Target Detection Based on Random Forest Metric Learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(4):1830-1838.
[10] LI Er, FEMIANI J, XU Shibiao, et al. Robust Rooftop Extraction from Visible Band Images Using Higher Order CRF[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(8):4483-4495.
[11] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-Based Learning Applied to Document Recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[12] RUSSAKOVSKY O, DENG Jia, SU Hao, et al. Imagenet Large Scale Visual Recognition Challenge[J]. International Journal of Computer Vision, 2015, 115(3):211-252.
[13] VAKALOPOULOU M, KARANTZALOS K, KOMODAKIS N, et al. Building Detection in very High Resolution Multispectral Data with Deep Learning Features[C]//IEEE International Geoscience and Remote Sensing Symposium. Milan, Italy:IEEE, 2015:1873-1876.
[14] GUO Zhiling, SHAO Xiaowei, XU Yongwei, et al. Identification of Village Building via Google Earth Images and Supervised Machine Learning Methods[J]. Remote Sensing, 2016, 8(4):271.
[15] LONG J, SHELHAMER E, DARRELL T. Fully Convolutional Networks for Semantic Segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA:IEEE, 2015:3431-3440.
[16] PIRAMANAYAGAM S, SCHWARTZKOPF W, KOEHLER F W, et al. Classification of Remote Sensed Images Using Random Forests and Deep Learning Framework[C]//Proceedings Volume 10004, Image and Signal Processing for Remote Sensing XXⅡ. Edinburgh, United Kingdom:SPIE, 2016, 10004:100040L.
[17] MARMANIS D, WEGNER J D, GALLIANI S, et al. Semantic Segmentation of Aerial Images with an Ensemble of CNNS[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, Ⅲ-3:473-480.
[18] MAGGIORI E, TARABALKA Y, CHARPIAT G, et al. Convolutional Neural Networks for Large-scale Remote-Sensing Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(2):645-657.
[19] BADRINARAYANAN V, KENDALL A, CIPOLLA R. Segnet:A Deep Convolutional Encoder-decoder Architecture for Image Segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(12):2481-2495.
[20] NOH H, HONG S, HAN B. Learning Deconvolution Network for Semantic Segmentation[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile:IEEE, 2015:1520-1528.
[21] RONNEBERGER O, FISCHER P, BROX T. U-net:Convolutional Networks for Biomedical Image Segmentation[M]//NAVAB N, HORNEGGER J, WELLS W, et al. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Cham:Springer, 2015:234-241.
[22] DALAL N, TRIGGS B. Histograms of Oriented Gradients for Human Detection[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA:IEEE, 2005:886-893.
[23] FREUND Y, SCHAPIRE R E. A Desicion-theoretic Generalization of On-line Learning and an Application to Boosting[C]//VITÁNYI P. Computational Learning Theory. Berlin:Springer, 1995:23-37.
[24] CARLETTA J. Assessing Agreement on Classification Tasks:The Kappa Statistic[J]. Computational Linguistics, 1996, 22(2):249-254.

基于U型卷积神经网络的航空影像建筑物检测

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

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	梁哲恒, 黎宵, 邓鹏, 盛森, 姜福泉. 融合多尺度特征注意力的遥感影像变化检测方法[J]. 测绘学报, 2022, 51(5): 668-676.
[2]	金飞, 官恺, 刘智, 韩佳容, 芮杰, 李庆高. 无监督密集匹配特征提取网络性能分析[J]. 测绘学报, 2022, 51(3): 426-436.
[3]	葛小三, 陈曦, 赵文智, 李瑞祥. 基于生成对抗网络的建筑物损毁检测[J]. 测绘学报, 2022, 51(2): 238-247.
[4]	张玉鑫, 颜青松, 邓非. 高分辨率遥感影像建筑物提取多路径RSU网络法[J]. 测绘学报, 2022, 51(1): 135-144.
[5]	杨秋莲, 刘艳飞, 丁乐乐, 孟凡效. 高分影像场景分类的半监督深度卷积神经网络学习方法[J]. 测绘学报, 2021, 50(7): 930-938.
[6]	叶发茂, 孟祥龙, 董萌, 聂运菊, 葛芸, 陈晓勇. 遥感图像蚁群算法和加权图像到类距离检索法[J]. 测绘学报, 2021, 50(5): 612-620.
[7]	张传辉, 姚国标, 张力, 艾海滨, 满孝成, 黄鹏飞. 多分支网络联合的倾斜影像仿射不变特征匹配[J]. 测绘学报, 2021, 50(5): 641-651.
[8]	施慧慧, 徐雁南, 滕文秀, 王妮. 高分辨率遥感影像深度迁移可变形卷积的场景分类法[J]. 测绘学报, 2021, 50(5): 652-663.
[9]	蓝朝桢, 卢万杰, 于君明, 徐青. 异源遥感影像特征匹配的深度学习算法[J]. 测绘学报, 2021, 50(2): 189-202.
[10]	汤寓麟, 金绍华, 边刚, 张永厚, 李凡. 侧扫声呐识别沉船影像的迁移学习卷积神经网络法[J]. 测绘学报, 2021, 50(2): 260-269.
[11]	阳凡林, 朱正任, 李家彪, 冯成凯, 邢喆, 吴自银. 利用深层卷积神经网络实现地形辅助的多波束海底底质分类[J]. 测绘学报, 2021, 50(1): 71-84.
[12]	李道纪, 郭海涛, 卢俊, 赵传, 林雨准, 余东行. 遥感影像地物分类多注意力融和U型网络法[J]. 测绘学报, 2020, 49(8): 1051-1064.
[13]	杨必胜, 宗泽亮, 陈驰, 孙文鹿, 米晓新, 吴唯同, 黄荣刚. 车载探地雷达地下目标实时探测法[J]. 测绘学报, 2020, 49(7): 874-882.
[14]	邓睿哲, 陈启浩, 陈奇, 刘修国. 遥感影像船舶检测的特征金字塔网络建模方法[J]. 测绘学报, 2020, 49(6): 787-797.
[15]	刘嗣超, 武鹏达, 赵占杰, 李成名. 交通监控视频图像语义分割及其拼接方法[J]. 测绘学报, 2020, 49(4): 522-532.