High-Resolution Image Building Extraction Based on Multi-level Feature Fusion Network

被引：0
|
作者：
Li X. [1 ]
Bai X. [1 ]
Li Z. [2 ]
Zuo Z. [3 ]
机构：
[1] School of Remote Sensing and Information Engineering, Wuhan University, Wuhan
[2] CCCC Second Highway Consultants Co. Ltd, Wuhan
[3] Norla Institute of Technical Physics, Chengdu
来源：
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | 2022年 / 47卷 / 08期
基金：
中国国家自然科学基金;
关键词：
building extraction; deep learning; high-resolution image; multi-scale characteristics; remote sensing;
D O I：
10.13203/j.whugis20210506
中图分类号：
学科分类号：
摘要：
Objectives The scale of buildings and their distribution is key indicators to measure the economic and social development of a region. Therefore, it is significant to study the extraction of buildings based on remote sensing images. Existing neural network methods still have shortcomings in the completeness of building extraction and the accuracy of building edges. To solve the above problems, this paper proposes a multi-level feature fusion network (MFFNet) based on high-resolution images. Methods Firstly, we use edge detection operators to improve the ability of the network to recognize the boundaries of buildings. Secondly, we use a multi-path convolution fusion module to extract building features from multiple dimensions, and introduce a large receptive field convolution module to break through feature extraction. The process is limited by the size of the receptive field. After fusing the extracted features, the convolutional attention module is used to compress them, and the global features are further mined by pyramid pooling, so as to achieve high-precision extraction of buildings. Results The current mainstream UNet, pyramid scene parsing network (PSPNet), multi attending path neural network (MAPNet) and multiscale-feature fusion deep neural networks with dilated convolution (MDNNet)are used as the comparison methods, and we use Wuhan University Aerial Image Dataset, Satellite Dataset II (East Asia) and Inria Aerial Image Dataset as experimental data for testing. Compared with the other four methods, MFFNet improves intersection over union, precision, recall, F1-score and mean average precision by 1.53%, 2.65%, 2.41%, 3.32% and 1.19% on average, achieves a better effect. Conclusions MFFNet not only accurately captures the detail features of buildings, but also strengthens the extraction and utilization of global features. It has better extraction effect on large buildings and buildings in complex environment. © 2022 Wuhan University. All rights reserved.
引用
下载
收藏
页码：1236 / 1244
页数：8
相关论文
共 21 条
  • [1] Min Ye, Bin Wang, Siyuan Wang, Et al., Extracting Floor Area Ratio of the Classified Buildings from Very High Resolution Satellite Image Using Multi⁃ ple Features［J］, Geomatics and Information Science of Wuhan University, 44, 11, pp. 1674-1684, (2019)
  • [2] Fenghua Lu, Ning Shu, Yan Gong, Et al., Regular Building Extraction from High Resolution Image Based on Multilevel-Features［J］, Geomatics and In⁃ formation Science of Wuhan University, 42, 5, pp. 656-660, (2017)
  • [3] Xianjun Gao, Xuedong Zheng, Dajiang Shen, Et al., Automatic Building Extraction Based on Shadow Analysis from High Resolution Images in Suburb Areas［J］, Geomatics and Information Science of Wuhan University, 42, 10, pp. 1350-1357, (2017)
  • [4] Xiangguo Lin, Jixian Zhang, Object-Based Morpho⁃ logical Building Index for Building Extraction from High Resolution Remote Sensing Imagery［J］, Acta Geodaetica et Cartographica Sinica, 46, 6, pp. 724-733, (2017)
  • [5] Guodong Shu, Chuanjie Liu, Lu Wang, Extraction Algorithm Study of Urban Flat-Topped Buildings Based on Airborne LiDAR Point Cloud［J］, Modern Surveying and Mapping, 42, 1, pp. 21-23, (2019)
  • [6] Qihong Zeng, Jianhua Mao, Xianhua Li, Et al., Building Roof Boundary Extraction from LiDAR Point Cloud［J］, Geomatics and Information Science of Wuhan University, 34, 4, pp. 383-386, (2009)
  • [7] Hinton G., Machine Learning for Aerial Image Labeling［D］, (2013)
  • [8] He K M, Zhang X Y，, Ren S Q，, Et al., Deep Residual Learning for Image Recognition［C］, IEEE Conference on Computer Vision and Pattern Recognition, (2016)
  • [9] Paisitkriangkrai S, Et al., Effec⁃ tive Semantic Pixel Labelling with Convolutional Networks and Conditional Random Fields［C］, IEEE Conference on Computer Vision and Pattern Recognition Workshops, (2015)
  • [10] Maggiori E，, Tarabalka Y，, Charpiat G，, Et al., High-Resolution Aerial Image Labeling with Convolutional Neural Networks ［J］, IEEE Transactions on Geoscience and Remote Sensing, 55, 12, pp. 7092-7103, (2017)
123