小数据集中的小型建筑物提取方法研究

doi:10.13474/j.cnki.11-2246.2019.0317

测绘通报 ›› 2019, Vol. 0 ›› Issue (10): 51-55.doi: 10.13474/j.cnki.11-2246.2019.0317

小数据集中的小型建筑物提取方法研究

杨旭勃, 田金文

华中科技大学人工智能与自动化学院, 湖北武汉 430074

收稿日期:2019-02-21 出版日期:2019-10-25 发布日期:2019-10-26
作者简介:杨旭勃(1993-),男,硕士生,主要研究方向为计算机视觉。E-mail:yangxubo@hust.edu.cn
基金资助:
国家自然科学基金（61273279）

Research on small building extraction method in small dataset

YANG Xubo, TIAN Jinwen

School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China

Received:2019-02-21 Online:2019-10-25 Published:2019-10-26

摘要/Abstract

摘要： 遥感卫星影像一般尺寸较大，而包含有小型建筑物的区域占比较小，如果采用滑动切块扩增数据样本的方法，大部分切片中没有目标，而构建包含大量小建筑物的大型数据集费工费时。常规的方法在高分辨率卫星影像上提取小型建筑物非常困难，研究适用于小规模数据集的小型建筑物提取任务的提取方法具有重要理论意义和应用价值。本文提出了一种轻量化的全连接分割网络ZF-FCN，使用较小的感受野获取更多局部信息，使用较少的最大池化操作避免剧烈的下采样，使用Lovász-Softmax损失解决样本不平衡问题，使网络训练更稳定也更好地优化交并比。最后构建了一个主要包含小型建筑物的小规模数据集，试验在对不同切块大小进行数据增强后进行。对比试验表明，ZF-FCN在建筑物提取任务上的表现优于FCN和U-Net。

关键词: 建筑物提取, 全连接网络, 感受野, 语义分割, 上采样

Abstract: The remote sensing satellite images are generally large, while the area containing small buildings is relatively small. If sliding cropping is used to augment data, most of the cropped patches have no targets, and a large dataset containing a large number of small buildings is time-consuming and labor intensive to construct. It is very difficult for conventional methods to extract small buildings on high-resolution satellite imagery and of great theoretical significance and application value to study the small building extraction method suitable for small-scale datasets. In this paper, a new lightweight and fully connected network ZF-FCN is proposed. ZF-FCN uses a small receptive field to obtain more local information, uses less max pooling operations to avoid violent down-sampling, and uses Lovász-Softmax loss to solve sample imbalance problem and better optimizes the IoU metric. A dataset consisted of a small number of images containing mainly small buildings is established in this paper, and the experiment is carried out on the augmented dataset with different cropping sizes, which finally proves that ZF-FCN outperforms both FCN and U-Net.

Key words: building extraction, fully connected network, receptive field, semantic segmentation, up-sampling

中图分类号:

P237

杨旭勃, 田金文. 小数据集中的小型建筑物提取方法研究[J]. 测绘通报, 2019, 0(10): 51-55.

YANG Xubo, TIAN Jinwen. Research on small building extraction method in small dataset[J]. 测绘通报, 2019, 0(10): 51-55.

参考文献 15

[1]	安文, 杨俊峰, 赵羲, 等. 高分辨率遥感影像的建筑物自动提取[J]. 测绘科学, 2014, 39(11):80-84.
[2]	侯蕾, 尹东, 尤晓建. 一种遥感图像中建筑物的自动提取方法[J]. 计算机仿真, 2006, 23(4):184-187.
[3]	SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE, 2015:3431-3440.
[4]	RONNEBERGER O, FISCHER P, BROX T. U-net:convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.[S.l.]:Springer, 2015:234-241.
[5]	刘文涛, 李世华, 覃驭楚. 基于全卷积神经网络的建筑物屋顶自动提取[J]. 地球信息科学学报, 2018, 20(11):1562-1570.
[6]	伍广明, 陈奇, SHIBASAKI R, 等. 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, 47(6):864-872.
[7]	ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//European Conference on Computer Vision. Zürich:Springer, 2014:818-833.
[8]	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of International Conference on ICLR.[S.l.]:arXiv, 2014.
[9]	IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning.[S.l.]:arXiv, 2015.
[10]	ODENA A, DUMOULIN V, OLAH C. Deconvolution and checkerboard artifacts[J]. Distill, 2016, 1(10):e3.
[11]	RAKHLIN A, DAVYDOW A, NIKOLENKO S. Land cover classification from satellite imagery with U-Net and Lovász-Softmax loss[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Salt Lake City:IEEE, 2018:257-2574.
[12]	BERMAN M, TRIKI R A, BLASCHKO M B. The Lovász-Softmax loss:a tractable surrogate for the optimization of the intersection-over-union measure in neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE, 2018:4413-4421.
[13]	CONGALTON R G. A comparison of sampling schemes used in generating error matrices for assessing the accuracy of maps generated from remotely sensed data[J]. Photogrammetric Engineering and Remote Sensing, 1988,54(5):593-600.
[14]	QIAN N. On the momentum term in gradient descent learning algorithms[J]. Neural Networks, 1999, 12(1):145-151.
[15]	GLOROT X, BENGIO Y. Understanding the difficulty of training deep feedforward neural networks[C]//Proceedings of the 13th International Conference on Artificial Intelligence And Statistics. Sardinia:[s.n.], 2010:249-256.

小数据集中的小型建筑物提取方法研究

Research on small building extraction method in small dataset

可视化

摘要/Abstract

引用本文

使用本文

参考文献 15

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘小玉, 刘扬, 杜明义, 张敏, 贾竞珏, 杨恒. 基于DeeplabV3+的建筑垃圾堆放点识别[J]. 测绘通报, 2022, 0(4): 16-19,43.
[2]	王雪, 梁珂, 隋立春, 钟棉卿, 朱剑锋. 膨胀卷积与金字塔表达的深度学习模型用于农村建筑物提取[J]. 测绘通报, 2022, 0(4): 61-65.
[3]	李少先. 利用双向布料模拟的机载建筑物点云提取[J]. 测绘通报, 2022, 0(3): 148-151.
[4]	王珍, 张涛, 丁乐乐, 潘宇明, 史芙蓉. 融合高度和光谱信息的倾斜摄影数据建筑物自动提取[J]. 测绘通报, 2022, 0(2): 10-15.
[5]	武花, 张新长, 孙颖, 蔡伟男, 颜军, 邓剑文, 张建国. 融合多特征改进型PSPNet模型应用于复杂场景下的建筑物提取[J]. 测绘通报, 2021, 0(6): 21-27.
[6]	吴永静, 吴锦超, 林超, 窦宝成, 黎珂. 基于深度学习的高分辨率遥感影像光伏用地提取[J]. 测绘通报, 2021, 0(5): 96-101.
[7]	叶沅鑫, 谭鑫, 孙苗苗, 王蒙蒙. 基于增强DeepLabV3网络的高分辨率遥感影像分类[J]. 测绘通报, 2021, 0(4): 40-44.
[8]	陈利燕, 林鸿, 吴健华. 融合随机森林和超像素分割的建筑物自动提取[J]. 测绘通报, 2021, 0(2): 49-53.
[9]	王燕锋, 盛业华, 秦佳睿, 张思阳, 闵祥强. 单体建筑物点云数据的CSF净化处理[J]. 测绘通报, 2020, 0(9): 72-75,84.
[10]	谢梦, 刘伟, 李二珠, 杨梦圆, 王晓檀. 深度卷积神经网络支持下的遥感影像语义分割[J]. 测绘通报, 2020, 0(5): 36-42.
[11]	周继苗, 李必军, 陈世增. 一种多层特征融合的道路场景实时分割方法[J]. 测绘通报, 2020, 0(1): 10-15.
[12]	盛超, 潘树国, 赵涛, 曽攀, 黄砺枭. 基于图像语义分割的动态场景下的单目SLAM算法[J]. 测绘通报, 2020, 0(1): 40-44.
[13]	方鑫, 陈善雄. 密集城区高分辨率遥感影像建筑物提取[J]. 测绘通报, 2019, 0(4): 79-83.
[14]	赵传, 张保明, 陈小卫, 郭海涛, 唐梁珂. 一种基于LiDAR点云的建筑物提取方法[J]. 测绘通报, 2017, 0(2): 35-39.
[15]	林雨准, 张保明, 徐俊峰, 侯凯, 周迅. 多特征多尺度相结合的高分辨率遥感影像建筑物提取[J]. 测绘通报, 2017, 0(12): 53-57.