结合空间约束的卷积神经网络多模型多尺度船企场景识别

doi:10.6046/zrzyyg.2021020

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(9885 KB)

HTML
输出: BibTeX | EndNote (RIS)

摘要

船企场景识别对修复沿岸生态环境、保护水域环境以及促进船舶产业的协调发展具有现实意义,但传统方法基于中、低层次的特征难以实现卫星遥感图像中船企的自动识别。为此,提出了结合空间约束的卷积神经网络多模型多尺度船企场景识别方法。首先分别采用全局尺度的船企场景和局部尺度船坞(台)、厂房和船只样本训练多个卷积神经网络模型,并进行多模型多尺度检测; 进而对局部对象进行像素级定位并计算对象空间距离; 最终结合多尺度检测结果、对象标签组合方式、对象空间距离进行船企场景综合判别与提取。将此方法分别应用于中国江苏省、日本长崎县和爱媛县周边以及韩国木浦市和巨济市周边5个典型造船密集区。结果表明,江苏省整体识别精确度为87%,召回率为85%; 日本研究区整体识别精确度为91%,召回率为87%; 韩国研究区整体识别精确度为85%,召回率为92%。实验结果表明,此方法可以较好地实现遥感船企复杂场景的识别。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	于新莉
	宋妍
	杨淼
	黄磊
	张艳杰

关键词 ：卫星遥感, 造船企业, 卷积神经网络, 多尺度, 空间距离约束

Abstract：

The scene recognition of shipbuilding enterprises is of practical significance for the restoration of the coastal ecological environment, the protection of water environment, and the promotion of the coordinated development of shipbuilding enterprises. However, it is difficult to realize the automatic recognition of shipbuilding enterprises from satellite remote sensing images based on traditional medium- and low-level features. Therefore, this paper proposes a multi-model multi-scale scene recognition method of shipbuilding enterprises based on a convolutional neural network with spatial constraints and the steps are as follows. Firstly, train multiple convolutional neural network models using the samples of global-scale shipbuilding enterprise scenes and local-scale docks (slipways), workshops, and ships individually, and conduct multi-model multi-scale detection. Then, locate local-scale objects at a pixel level and calculate the spatial distance of the objects. Finally, conduct comprehensive judgment and extraction of the shipbuilding enterprise scenes according to the multi-scale detection results, the combination method of object tags, and the spatial distance of objects. The method was applied to five typical shipbuilding intensive areas in Jiangsu Province, China, the surrounding areas of Nagasaki and Ehime prefectures, Japan, and Mokpo and Geoje cities, South Korea. As a result, the overall recognition accuracy and recall rate were 87% and 85%, respectively in Jiangsu Province, were 91% and 87%, respectively in the study area in Japanese, and were 85% and 92%, respectively in the study area in South Korean. The experimental results show that this method can realize the effective recognition of the complex scenes of shipbuilding enterprises based on remote sensing images.

Key words： satellite remote sensing shipbuilding enterprises convolutional neural networks multi-scale spatial distance constraint

收稿日期: 2021-01-15 出版日期: 2021-12-23

ZTFLH:

TP79

基金资助:海洋领域融合应用示范项目(2020010004);国防科工局民用“十三五”航天预先研究项目“星载高分辨率红外高光谱相机及应用技术”(D040104)

通讯作者: 宋妍

作者简介: 于新莉(1997-),女,硕士,主要研究方向为深度学习、海岸带多源遥感监测等。Email: yu_xinli@cug.edu.cn。

引用本文:

于新莉, 宋妍, 杨淼, 黄磊, 张艳杰. 结合空间约束的卷积神经网络多模型多尺度船企场景识别[J]. 自然资源遥感, 2021, 33(4): 72-81.
YU Xinli, SONG Yan, YANG Miao, HUANG Lei, ZHANG Yanjie. Multi-model and multi-scale scene recognition of shipbuilding enterprises based on convolutional neural network with spatial constraints. Remote Sensing for Natural Resources, 2021, 33(4): 72-81.

链接本文:

https://www.gtzyyg.com/CN/10.6046/zrzyyg.2021020 或 https://www.gtzyyg.com/CN/Y2021/V33/I4/72

Fig.1 船企内部结构图

Tab.1 船企内部解译标志

Fig.2 残差学习单元

Fig.3 多模型检测流程

Fig.4 多模型多尺度船企识别流程

Fig.5 局部对象空间关系约束

Fig.6 船企场景识别流程

Tab.2 样本数量

Tab.3 网络训练结果

Fig.7 江苏省研究区域结果展示

Fig.8 日本研究区域结果展示

Fig.9 韩国研究区域结果展示

Tab.4 基于不同基础网络模型的江苏省船企识别结果

Fig.10 江苏省船企分布的最终识别结果

Tab.5 江苏省船企识别结果细节展示

Fig.11 日本研究区域的船企识别结果

Tab.6 日本研究区船企识别结果细节展示

Tab.7 韩国研究区船企识别结果细节展示

Fig.12 韩国研究区域的船企识别结果

[1]	杨青. 长三角船舶产业集群研究[D]. 上海:上海海事大学, 2007.
	Yang Q. Research on the shipbuilding industry cluster in the Yangtze River delta[D]. Shanghai:Shanghai Maritime University, 2007.
[2]	刘辉, 史雅娟, 曾春水. 中国船舶产业空间布局与发展策略[J]. 经济地理, 2017,37(8):99-107.
	Liu H, Shi Y J, Zeng C S. Spatial layout and development strategy of the ship-related industry in China[J]. Economic Geography, 2017,37(8):99-107.
[3]	Zhou Z H, Zhang M L, Huang S J, et al. Multi-instance and multi-label learning[J]. Artificial Intelligence, 2012,176(1):2291-2320. doi: 10.1016/j.artint.2011.10.002
[4]	Li Z L, Xu K, Xie J F, et al. Deep multiple instance convolutional neural networks for learning robust scene representations[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020,58(5):3685-3702. doi: 10.1109/TGRS.36
[5]	Liu W H, Li Y D, Wu Q. An attribute-based high-level image representation for scene classification[J]. IEEE Access, 2019,7:4629-4640. doi: 10.1109/ACCESS.2018.2886597
[6]	Khan N, Chaudhuri U, Banerjee B, et al. Graph convolutional network for multi-label VHR remote sensing scene recognition[J]. Neurocomputing, 2019,357:36-46. doi: 10.1016/j.neucom.2019.05.024
[7]	Chen Z M, Wei X S, Wang P, et al. Multi-Label Image Recognition with Graph Convolutional Networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE, 2019.
[8]	Clement M, Kurtz C, Wendling L. Learning spatial relations and shapes for structural object description and scene recognition[J]. Pattern Recognition, 2018,84:197-210. doi: 10.1016/j.patcog.2018.06.017
[9]	Lazebnik S, Schmid C, Ponce J. Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories[C]//Computer Vision and Pattern Recognition,2006 IEEE Computer Society Conference, 2006.
[10]	Jiang Y, Yuan J, Gang Y. Randomized spatial partition for scene recognition[M]. Berlin:Springer Berlin Heidelberg, 2012:730-743.
[11]	Weng C Q, Wang H X, Yuan J S, et al. Discovering Class-Specific Spatial Layouts for Scene Recognition[J]. IEEE Signal Processing Letters, 2017,24(8):1143-1147. doi: 10.1109/LSP.2016.2641020
[12]	He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015,37(9):1904-1916. doi: 10.1109/TPAMI.2015.2389824
[13]	Xie L, Lee F F, Liu L, et al. Scene recognition:A comprehensive survey[J]. Pattern Recognition, 2020,102:107205. doi: 10.1016/j.patcog.2020.107205
[14]	船舶工业年鉴编委会. 中国船舶工业年鉴2018[Z].[s.l]:船舶工业年鉴编委会, 2018.
	Editorial Committee of Yearbook of Shipbuilding Industry. Yearbook of China shipbuilding industry 2018[Z].[s.l]:Editorial Committee of Yearbook of Shipbuilding Industry, 2018.
[15]	He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas:2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2016:770-778.
[16]	颜荔. 基于卷积神经网络的遥感图像飞机目标识别研究[D]. 合肥:中国科学技术大学, 2018.
	Yan L. Research on airplane target recognition in remote sensing images based on convolutional neural network[D]. Hefei:University of Science and Technology of China, 2018.
[17]	Zhou Z H. A brief introduction to weakly supervised learning[J]. National Science Review, 2018,5(1):44-53. doi: 10.1093/nsr/nwx106
[18]	Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM:Visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020,128(2):336-359. doi: 10.1007/s11263-019-01228-7
[19]	Xia G S, Hu J W, Hu F, et al. AID:A benchmark data set for performance evaluation of aerial scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017,55(7):3965-3981. doi: 10.1109/TGRS.2017.2685945
[20]	Cheng G, Han J W, Lu X Q. Remote sensing image scene classification:Benchmark and state of the art[J]. Proceedings of the IEEE, 2017,105(10):1865-1883. doi: 10.1109/JPROC.2017.2675998
[21]	Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017,60(6):84-90. doi: 10.1145/3065386
[22]	Karen S, Andrew Z. Very deep convolutional networks for large-scale image recognition[J]. arXiv, 2014.

[1]	郑宗生, 刘海霞, 王振华, 卢鹏, 沈绪坤, 唐鹏飞. 改进3D-CNN的高光谱图像地物分类方法[J]. 自然资源遥感, 2023, 35(2): 105-111.
[2]	胡建文, 汪泽平, 胡佩. 基于深度学习的空谱遥感图像融合综述[J]. 自然资源遥感, 2023, 35(1): 1-14.
[3]	李恺霖, 廖廓, 党皓飞. 内陆与近岸水体的色度学遥感研究进展[J]. 自然资源遥感, 2023, 35(1): 15-26.
[4]	孙盛, 蒙芝敏, 胡忠文, 余旭. 多尺度轻量化CNN在SAR图像地物分类中的应用[J]. 自然资源遥感, 2023, 35(1): 27-34.
[5]	苏腾飞. 基于边界信息的多尺度遥感影像分割质量非监督评价方法[J]. 自然资源遥感, 2023, 35(1): 35-40.
[6]	沈骏翱, 马梦婷, 宋致远, 柳汀洲, 张微. 基于深度学习语义分割模型的高分辨率遥感图像水体提取[J]. 自然资源遥感, 2022, 34(4): 129-135.
[7]	杨昭颖, 韩灵怡, 郑向向, 李文吉, 冯磊, 王轶, 杨永鹏. 基于卷积神经网络的遥感影像及DEM滑坡识别——以黄土滑坡为例[J]. 自然资源遥感, 2022, 34(2): 224-230.
[8]	孔爱玲, 张承明, 李峰, 韩颖娟, 孙焕英, 杜漫飞. 基于知识引导的遥感影像融合方法[J]. 自然资源遥感, 2022, 34(2): 47-55.
[9]	廖廓, 聂磊, 杨泽宇, 张红艳, 王艳杰, 彭继达, 党皓飞, 冷伟. 基于多维卷积神经网络的多源高分辨率卫星影像茶园分类[J]. 自然资源遥感, 2022, 34(2): 152-161.
[10]	吴琳琳, 李晓燕, 毛德华, 王宗明. 基于遥感和多源地理数据的城市土地利用分类[J]. 自然资源遥感, 2022, 34(1): 127-134.
[11]	高琪, 王玉珍, 冯春晖, 马自强, 柳维扬, 彭杰, 季彦桢. 基于改进型光谱指数的荒漠土壤水分遥感反演[J]. 自然资源遥感, 2022, 34(1): 142-150.
[12]	温银堂, 王铁柱, 王书涛, 王贵川, 刘诗瑜, 崔凯. 基于多尺度分割的高分辨率遥感影像镶嵌线自动提取[J]. 自然资源遥感, 2021, 33(4): 64-71.
[13]	姜亚楠, 张欣, 张春雷, 仲诚诚, 赵俊芳. 基于多尺度LBP特征融合的遥感图像分类[J]. 自然资源遥感, 2021, 33(3): 36-44.
[14]	王华, 李卫卫, 李志刚, 陈学业, 孙乐. 基于多尺度超像素的高光谱图像分类研究[J]. 自然资源遥感, 2021, 33(3): 63-71.
[15]	刘万军, 高健康, 曲海成, 姜文涛. 多尺度特征增强的遥感图像舰船目标检测[J]. 自然资源遥感, 2021, 33(3): 97-106.

Viewed

Full text

Abstract

Cited

Shared

Discussed