A Deep Learning Based Method for Remote Sensing Image Parcel Segmentation

doi:10.11871/jfdc.issn.2096-742X.2021.02.015

Abstract

Abstract:

[Objective] Remote sensing image parcel segmentation is a specific task of remote sensing image interpretation. Good results of remote sensing image parcel segmentation can provide guidance for environmental protection, agricultural production and town construction. [Methods] In this paper, DeepLabV3+ network is built using Pytorch framework. The encoder uses ResNet101 and atrous spatial pyramid pooling module for feature extraction, and the decoder uses the bilinear interpolation method for feature map resizing. During the training process, a data augmentation strategy is specifically designed for the remote sensing image parcel segmentation task, so as to enhance the generalization ability of the model. A loss function with joint Lovasz loss and Softmax loss is used to solve the problem of unbalanced distribution of sample categories. [Results] The mean Intersection over Union is chosen as the evaluation index for the experimental results. The mean Intersection over Union of the final model can reach 70.3%, which is 7.6% higher than the UNet, a commonly used method for remote sensing image segmentation. [Limitations] The region of some segmented images is not complete, and the connectivity of segmented images needs to be further improved. [Conclusions] The remote sensing image parcel segmentation method proposed in this paper can achieve fine segmentation results of high-resolution remote sensing images and provide a reference for the research of remote sensing image segmentation.

Key words: remote sensing image, image segmentation, deep learning

ZHAO Weiyu,ZHANG Honghai,ZHONG Bo. A Deep Learning Based Method for Remote Sensing Image Parcel Segmentation[J]. Frontiers of Data and Computing, 2021, 3(2): 133-141.

Figures/Tables 7

Fig.1

Fig.2

Table1

Fig.3

Fig.4

Table 2

Table 3

References 19

[1]	于东方, 殷建平, 张国敏. 一种基于灰度直方图的遥感影像阴影自动检测方法[J]. 计算机工程与科学, 2008,30(12):43-44+93.
[2]	陈波, 张友静, 陈亮. 标记分水岭算法及区域合并的遥感图像分割[J]. 国土资源遥感, 2007(02):35-38.
[3]	刘永学, 李满春, 毛亮. 基于边缘的多光谱遥感图像分割方法[J]. 遥感学报, 2006(03):350-356.
[4]	郑玮, 康戈文, 陈武凡, 李小文. 基于模糊马尔可夫随机场的无监督遥感图像分割算法[J]. 遥感学报, 2008(02):246-252.
[5]	王民, 张鑫, 贠卫国, 卫铭斐, 王静. 基于核模糊C-均值和EM混合聚类算法的遥感图像分割[J]. 液晶与显示, 2017,32(12):999-1005.
[6]	李树深. 数据与计算是科技创新的巨大驱动力[J]. 数据与计算发展前沿, 2019,1(1):1-1.
[7]	廖方宇, 洪学海, 汪洋, 褚大伟. 数据与计算平台是驱动当代科学研究发展的重要基础设施[J]. 数据与计算发展前沿, 2019,1(1):2-10.
[8]	Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks[J]. Neural Information Processing Systems, 2012: 1097-1105.
[9]	K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition[C]. In ICLR, 2015: 1-14.
[10]	K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition[C]. In CVP, 2016: 770-778.
[11]	孙哲南, 张兆翔, 王威, 刘菲, 谭铁牛. 2019 年人工智能新态势与新进展[J]. 数据与计算发展前沿, 2019,1(2):1-16.
[12]	Shelhamer E, Long J, Darrell T. Fully Convolutional Networks for Semantic Segmentation[J]. IEEE Trans Pattern Anal Mach Intell, 2017 Apr;39(4):640-651. doi: 10.1109/TPAMI.2016.2572683
[13]	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. Springer, Cham, 2015: 234-241.
[14]	Zhao H, Shi J, Qi X, et al. Pyramid Scene Parsing Network[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017: 6230-6239.
[15]	Chen L C, Zhu Y, Papandreou G, et al. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[C]// European Conference on Computer Vision. Springer, Cham, 2018: 833-851.
[16]	Chen LC, Papandreou G, Kokkinos I, et al. Semantic image segmentation with deep convolutional nets and fully connected crfs[C]// arXiv preprint arXiv:1412.7062, 2014.
[17]	Chen L C, Papandreou G, Kokkinos I, et al. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018,40(4):834-848. doi: 10.1109/TPAMI.2017.2699184
[18]	Berman M, Triki A R, Blaschko MB. The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2018: 4413-4421.
[19]	Sun K, Xiao B, Liu D, et al. Deep HighResolution Re-presentation Learning for Human Pose Estimation[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2019: 5693-5703.

类别	像素值
建筑	0
耕地	1
林地	2
水体	3
道路	4
草地	5
其他	6
未标注区域	255

方法	平均交并比
本文方法	70.3%
UNet	62.7%
未修改的DeeplabV3+	66.8%
HRNet	64.7%

预训练数据集	平均交并比
MS-COCO（本文方法）	70.3%
Imagenet	67.9%
Cityscapes	68.5%