深度卷积神经网络支持下的遥感影像语义分割

doi:10.13474/j.cnki.11-2246.2020.0141

测绘通报 ›› 2020, Vol. 0 ›› Issue (5): 36-42.doi: 10.13474/j.cnki.11-2246.2020.0141

深度卷积神经网络支持下的遥感影像语义分割

谢梦¹, 刘伟^1,2, 李二珠¹, 杨梦圆¹, 王晓檀³

1. 江苏师范大学地理测绘与城乡规划学院, 江苏徐州 221116;
2. 资源与环境信息系统国家重点实验室, 北京 100101;
3. 河海大学地球科学与工程学院, 江苏南京 210098

收稿日期:2019-08-16 出版日期:2020-05-25 发布日期:2020-06-02
通讯作者: 刘伟。E-mail:grid_gis@126.com E-mail:grid_gis@126.com
作者简介:谢梦(1994-),女,硕士生,研究方向为遥感图像处理与目标检测、图像特征识别。E-mail:15262036926@163.com
基金资助:
江苏省国土资源科技项目（2018044）；徐州市科技项目（KC18139）；资源与环境信息系统国家重点实验室开放基金；徐州市国土资源科技项目（XZGTKJ2018001）

Remote sensing image semantic segmentation supported by deep convolutional neural networks

XIE Meng¹, LIU Wei^1,2, LI Erzhu¹, YANG Mengyuan¹, WANG Xiaotan³

1. School of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou 221116, China;
2. State Key Laboratory of Resources and Environmental Information System, Beijing 100101, China;
3. College of Earth Sciences and Engineering, Hohai University, Nanjing 210098, China

Received:2019-08-16 Online:2020-05-25 Published:2020-06-02

摘要/Abstract

摘要： 针对高分遥感影像语义分割面临的类别不平衡和上下文信息利用不充分问题，本文提出了一种优化的DeeplabV3+算法。首先通过修改交叉熵损失函数，解决数据不平衡问题；其次使用Vortex Pooling取代ASPP模块提高上下文信息；然后采用多尺度输入充分利用图像的多尺度信息，并用投票策略进行特征融合提高图像分割准确性；最后使用形态学作后处理消除拼接痕迹和噪声。在CCF大赛的数据集上进行训练，并与其他经典语义分割算法进行比较。试验结果表明，该算法充分利用上下文信息，有效减少了错误分类，且使分割边界更精确，尤其对于线状目标的捕捉能力更强；在整幅测试影像上的MIoU可达85.21%，明显优于SegNet、U-Net算法。

关键词: 语义分割, DeeplabV3+, 高分辨率遥感影像, Vortex Pooling, 多尺度信息

Abstract: Aiming at the problem of category imbalance and insufficient utilization of context information in high-score remote sensing image semantic segmentation, this paper proposes an optimized DeeplabV3 + algorithm. Firstly, the data imbalance problem is solved by modifying the cross-entropy loss function. Secondly, it replace the ASPP module with Vortex Pooling to improve the context information. Then it use multi-scale input to make full use of the multi-scale information of the image. And then it use the voting strategy for feature fusion to improve the accuracy of image segmentation. Finally, morphology is used for post-processing to eliminate stitching marks and noise. Train on the CCF contest dataset and compare it with other classic semantic segmentation algorithms. The experimental results show that the algorithm in this paper makes full use of contextual information, effectively reduces misclassification, makes segmentation boundaries more accurate, and captures linear targets more effectively. The MIoU on the entire test image can reach 85.21%, which is significantly better than the SegNet and U-Net algorithms.

Key words: semantic segmentation, DeeplabV3+, high-resolution remote sensing image, Vortex Pooling, multi-scale information

中图分类号:

P237

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.

XIE Meng, LIU Wei, LI Erzhu, YANG Mengyuan, WANG Xiaotan. Remote sensing image semantic segmentation supported by deep convolutional neural networks[J]. Bulletin of Surveying and Mapping, 2020, 0(5): 36-42.

参考文献

[1] PANBOONYUEN T, JITKAJORNWANICH K, LAWAWI-ROJWONG S. Semantic segmentation on remotely sensed images using an enhanced global convolutional network with channel attention and domain specific transfer learning[J]. Remote Sensing, 2019, 11(1):83.
[2] ALSHEHHI R, MARPU P R, WOON W L, et al. Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130(8):139-149.
[3] MARMANIS D, SCHINDLER K, WEGNER J D, et al. Classification with an edge:improving semantic image segmentation with boundary detection[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 135(1):158-172.
[4] AUDEBERT N, LE SAUX B, LEFÈVRE S, et al. Beyond RGB:very high resolution urban remote sensing with multimodal deep networks[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 140(1):20-32.
[5] MARCOS D, VOLPI M, KELLENBERGER B, et al. Land cover mapping at very high resolution with rotation equivariant CNNs:towards small yet accurate models[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 145(2):96-107.
[6] MAGGIORI E, TARABALKA Y, CHARPIAT G, et al. High-resolution aerial image labeling with convolutional neural networks[J]. IEEE Transactions on Geoscience & Remote Sensing, 2017, 55(12):7092-7103.
[7] 张新明, 祝晓斌, 蔡强, 等. 图像语义分割深度学习模型综述[J]. 高技术通讯, 2017, 27(S1):808-815.
[8] HU F, XIA G S, HU J,et al. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery[J]. Remote Sensing, 2015, 7(11):14680-14707.
[9] CASTELLUCCIO M, POGGI G, SANSONE C, et al. Land use classification in remote sensing images by convolutional neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE, 2015.
[10] BECK R A. Remote sensing and GIS as counterterrorism tools in the Afghanistan war:a case study of the Zhawar Kili region[J]. The Professional Geographer, 2003, 55(2):170-179.
[11] LONG J, SHELHAMER E, DARRELL T. Fully convolu-tional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 39(4):640-651.
[12] BADRINARAYANAN V, KENDALL A, Cipolla R. SegNet:a deep convolutional encoder-decoder architecture for scene segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(12):2481-2495.
[13] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE, 2015.
[14] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[J]. Computer Science, 2014(4):357-361.
[15] 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 & Machine Intelligence, 2018, 40(4):834-848.
[16] ZHAO H, SHI J, QI X, et al. Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii:IEEE, 2017.
[17] PENG C, ZHANG X, YU G, et al. Large kernel matters-improve semantic segmentation by global convolutional network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii:IEEE, 2017.
[18] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii:IEEE, 2017.
[19] 吴止锾, 高永明, 李磊, 等. 类别非均衡遥感图像语义分割的全卷积网络方法[J]. 光学学报, 2019, 39(4):401-412.
[20] 陈天华, 郑司群, 于峻川. 采用改进DeepLab网络的遥感图像分割[J]. 测控技术, 2018, 37(11):34-39.
[21] 苏健民, 杨岚心, 景维鹏. 基于U-Net的高分辨率遥感图像语义分割方法[J]. 计算机工程与应用, 2019, 55(7):207-213.
[22] LIU Y, REN Q, GENG J, et al. Efficient patch-wise semantic segmentation for large-scale remote sensing images[J]. Sensors, 2018, 18(10):3232.
[23] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE, 2018.
[24] CHOLLET F. Xception:deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii:IEEE, 2017.
[25] XIE C W, ZHOU H Y, WU J, et al. Vortex Pooling:improving context representation in semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE, 2018.
[26] GARCIA-GARCIA A, ORTS-ESCOLANO S, OPREA S, et al. A review on deep learning techniques applied to semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii:IEEE, 2017.
[27] ZHANG H, DANA K, SHI J, et al. Context encoding for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE, 2018.
[28] 刘懿兰, 黄晓霞, 李红旮, 等.基于卷积神经网络与条件随机场方法提取乡镇非正规固体废弃物[J]. 地球信息科学学报, 2019, 21(2):259-268.

深度卷积神经网络支持下的遥感影像语义分割

Remote sensing image semantic segmentation supported by deep convolutional neural networks

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]	任月娟, 葛小三. 改进DeepLabV3+网络的遥感影像道路综合提取方法[J]. 测绘通报, 2022, 0(6): 55-61.
[2]	潘建平, 付占宝, 程卫华, 陆世安, 李鑫, 孙博文, 黄桂萍. 基于地表类型的山地海绵城市生态建设评估[J]. 测绘通报, 2022, 0(5): 84-88.
[3]	陈智朗, 付振华, 朱紫阳, 王慧慧, 刘沁雯, 杨钰灵, 许耿然. 基于HRNet的高分辨率遥感影像建筑物变化信息提取[J]. 测绘通报, 2022, 0(5): 126-132.
[4]	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.
[5]	杨素妨, 杜林. 多特征流形鉴别嵌入的高分辨率遥感影像分类[J]. 测绘通报, 2021, 0(9): 37-42.
[6]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.
[7]	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.
[8]	聂倩, 七珂珂, 赵艳福. 融入超像素分割的高分辨率影像面向对象分类[J]. 测绘通报, 2021, 0(6): 44-49.
[9]	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.
[10]	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.
[11]	王媛, 杜明义, 杨柳忠, 蔡国印, 张宁. 多源遥感数据支持下的城市生态状况评价[J]. 测绘通报, 2021, 0(11): 16-20.
[12]	迪里胡玛尔·阿汗木江, 玉素甫江·如素力. 新疆焉耆盆地土壤湿度时空分布特征[J]. 测绘通报, 2021, 0(11): 36-41.
[13]	常京新, 高贤君, 杨元维, 王双喜. 融合多时相高分影像的建筑物轮廓优化方法[J]. 测绘通报, 2020, 0(7): 112-115.
[14]	乔婷婷, 李鲁群. 结合数据增广和迁移学习的高分辨率遥感影像场景分类[J]. 测绘通报, 2020, 0(2): 37-42.
[15]	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.