Research on oil spill monitoring of multi-source remote sensing image based on deep semantic segmentation

Yan-tong CHEN; Yu-yang LI; Shi-li LÜ; Jun-sheng WANG

doi:10.3788/OPE.20202805.1165

您当前的位置：

首页 >

文章列表页 >

Research on oil spill monitoring of multi-source remote sensing image based on deep semantic segmentation

Information Sciences | 更新时间：2020-07-09

- Research on oil spill monitoring of multi-source remote sensing image based on deep semantic segmentation
- Optics and Precision Engineering Vol. 28, Issue 5, Pages: 1165-1176(2020)
- 作者机构：
  
  1.大连海事大学信息科学技术学院, 辽宁大连 116026
  2.交通运输部搜救中心, 北京 100736
- 作者简介：
  
  WANG Jun-sheng, E-mail:wangjsh＠dlmu.edu.cn
- 基金信息：
- DOI：10.3788/OPE.20202805.1165
  CLC： TP753
- Received：07 November 2019，
  
  Revised：02 December 2019，
  
  Accepted：02 December 2019，
  
  Published：25 May 2020
- 稿件说明：
移动端阅览
Yan-tong CHEN, Yu-yang LI, Shi-li LÜ, et al. Research on oil spill monitoring of multi-source remote sensing image based on deep semantic segmentation[J]. Optics and precision engineering, 2020, 28(5): 1165-1176.
DOI：

Yan-tong CHEN, Yu-yang LI, Shi-li LÜ, et al. Research on oil spill monitoring of multi-source remote sensing image based on deep semantic segmentation[J]. Optics and precision engineering, 2020, 28(5): 1165-1176. DOI： 10.3788/OPE.20202805.1165.

摘要

针对遥感图像海面溢油区域通常受到斑噪声以及强度不均等因素的影响，从而导致溢油区域监测效果较差的问题，本文引入了深度语义分割的方法，将深度卷积神经网络与全连接条件随机场相结合，形成端对端连接。以Resnet结构为基础，首先通过深度卷积神经网络对多源遥感图像粗分割并作为输入，然后经过改进的全连接条件随机场，利用高斯成对势和平均场近似定理，建立条件随机场形成递归神经网络作为输出。通过多源遥感图像对海面溢油区域进行监测，并利用可见光图像估计溢油区域面积。实验在所建立的多源遥感图像数据集上与其它先进模型进行对比，结果表明本文方法提高了溢油区域的分割精度以及精细细节程度，平均交并比为82.1%，监测效果具有明显地改善。

Abstract

In remote sensing images

oil spill areasareusually affected by spot noise and uneven intensity

which leads to poor segmentation. A deep semantic segmentation method was introduced to combine a deep convolution neural network with a full connection conditional random field to form an end-to-end connection.Based on Resnet

first

the multi-source remote sensing image was roughly segmented as input by the deep convolutional neural network.Then

using Gaussian pairwise and mean field approximation

the conditional random field was established as the output of the recurrent neural network. The oil spill area on the sea surface was monitored by amulti-source remote sensing image and estimated by optical images. Experimental results show that the proposed method improves class ification accuracy and captures finer details of oil spill are ascompared with other models using the dataset established by the multi-source remote sensing image. The mean intersection over the union is 82.1%

and the monitoring effect is significantly improved.

关键词

Keywords

references

童丽珏 , 周伯煌 . "桑吉"轮引发的海洋生态环境损害问题探析 . 中国环境管理干部学院学报 , 2018 . 28 ( 2 ): 12 - 14 . http://d.old.wanfangdata.com.cn/Periodical/zghjglgbxyxb201802005 http://d.old.wanfangdata.com.cn/Periodical/zghjglgbxyxb201802005 .

L Y TONG , B H ZHOU . Analysis on damage to the marine ecological environment caused by "Sanchi" oil tanker . Journal of EMCC , 2018 . 28 ( 2 ): 12 - 14 . http://d.old.wanfangdata.com.cn/Periodical/zghjglgbxyxb201802005 http://d.old.wanfangdata.com.cn/Periodical/zghjglgbxyxb201802005 .

蒋兴伟 , 何贤强 , 林明森 , 等 . 中国海洋卫星遥感应用进展 . 海洋学报 , 2019 . 41 ( 10 ): 113 - 124 . http://d.old.wanfangdata.com.cn/Periodical/hyxb201910008 http://d.old.wanfangdata.com.cn/Periodical/hyxb201910008 .

X W JIANG , X Q HE , M S LIN , 等 . Progresses on ocean satellite remote sensing application in China . Acta Oceanologica Sinica , 2019 . 41 ( 10 ): 113 - 124 . http://d.old.wanfangdata.com.cn/Periodical/hyxb201910008 http://d.old.wanfangdata.com.cn/Periodical/hyxb201910008 .

康利军 , 李晓峰 , 宋甜甜 . SAR图像海面溢油检测技术分析 . 江苏科技信息 , 2018 . 35 ( 20 ): 41 - 43 . http://d.old.wanfangdata.com.cn/Periodical/jskjxx201820012 http://d.old.wanfangdata.com.cn/Periodical/jskjxx201820012 .

L J KANG , X F LI , T T SONG . Analysis of oil spill detection techniques for SAR images . Jiangsu Science & Technology Information , 2018 . 35 ( 20 ): 41 - 43 . http://d.old.wanfangdata.com.cn/Periodical/jskjxx201820012 http://d.old.wanfangdata.com.cn/Periodical/jskjxx201820012 .

李宇 , 刘雪莹 , 张洪群 , 等 . 基于卷积神经网络的光学遥感图像检索 . 光学精密工程 , 2018 . 26 ( 1 ): 200 - 207 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201801024 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201801024 .

Y LI , X Y LIU , H Q ZHANG , 等 . Optical remote sensing image retrieval based on convolutional neural networks . Opt. Precision Eng. , 2018 . 26 ( 1 ): 200 - 207 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201801024 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201801024 .

AL-AMRI S S, KALYANKAR N V. Image segmentation by using threshold techniques[J]. ArXiv Preprint ArXiv : 1005.4020, 2010.

赵宏伟 , 陈霄 , 刘萍萍 , 等 . 视觉显著目标的自适应分割 . 光学精密工程 , 2013 . 21 ( 2 ): 531 - 538 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201302038 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201302038 .

H W ZHAO , X CHEN , P P LIU , 等 . Adaptive segmentation for visual salient object . Opt. Precision Eng. , 2013 . 21 ( 2 ): 531 - 538 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201302038 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201302038 .

刘宁波 , 丁昊 , 田永华 , 等 . 基于组合分形特征的海杂波中目标检测方法 . 航空兵器 , 2018 . ( 2 ): 38 - 42 . http://d.old.wanfangdata.com.cn/Periodical/hkbq201802007 http://d.old.wanfangdata.com.cn/Periodical/hkbq201802007 .

N B LIU , H DING , Y H TIAN , 等 . Target detection method in sea clutter based on combined fractal characyeristics . Aero Weaponry , 2018 . ( 2 ): 38 - 42 . http://d.old.wanfangdata.com.cn/Periodical/hkbq201802007 http://d.old.wanfangdata.com.cn/Periodical/hkbq201802007 .

NOH H, HONG S, HAN B. Learning deconvolution network for semantic segmentation[C]. Proceedings of the IEEE international conference on computer vision , 2015: 1520-1528.

CHEN L C, ZHU Y, PAPANDREOU G, et al . Encoder-decoder with atrous separable convolution for semantic image segmentation[C]. Proceedings of the European Conference on Computer Vision (ECCV), 2018: 801-818.

J SHOTTON, M JOHNSON, R CIPOLLA. Semantic texton forests forimage categorization and segmentation[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2008.

M RANALLI , F LAGONA , M PICONE , 等 . Segmentation of sea current fields by cylindrical hidden Markov models: a composite likelihood approach . Journal of the Royal Statistical Society: Series C (Applied Statistics) , 2018 . 67 ( 3 ): 575 - 598 . http://cn.bing.com/academic/profile?id=45e2a441e1b6f9a7dce9b51cb7161b43&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=45e2a441e1b6f9a7dce9b51cb7161b43&encoded=0&v=paper_preview&mkt=zh-cn .

VARMA K I, KRISHNAMOORTHY S, PISIPATI R K. Natural language querying with cascaded conditional random fields[P]. United States Patent Application 20120254143, 280, 535.2016-3-8. http://www.freepatentsonline.com/y2012/0254143.html http://www.freepatentsonline.com/y2012/0254143.html .

汪萍 . 基于多尺度条件随机场的语义图像分割深度卷积网络 . 宿州学院学报 , 2019 . 34 ( 7 ): 69 - 74 . http://d.old.wanfangdata.com.cn/Periodical/szszxb201907017 http://d.old.wanfangdata.com.cn/Periodical/szszxb201907017 .

P WANG . Deep Convolutional network with multi-scale conditional rando field for semantic image segmentation . Journal of Suzhou University , 2019 . 34 ( 7 ): 69 - 74 . http://d.old.wanfangdata.com.cn/Periodical/szszxb201907017 http://d.old.wanfangdata.com.cn/Periodical/szszxb201907017 .

唐聪 , 凌永顺 , 郑科栋 , 等 . 基于深度学习的多视窗SSD目标检测方法 . 红外与激光工程 , 2018 . 47 ( 1 ): 302 - 310 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201801039 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201801039 .

C TANG , Y SH LING , K D ZHENG , 等 . Object detection method of multi-view SSD based on deep learning . Infrare and Laser Engineering , 2018 . 47 ( 1 ): 302 - 310 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201801039 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201801039 .

LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2015: 3431-3440.

L C CHEN , G PAPANDREOU , I KOKKINOS , 等 . Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs . IEEE transactions on pattern analysis and machine intelligence , 2017 . 40 ( 4 ): 834 - 848 . http://d.old.wanfangdata.com.cn/Periodical/mssbyrgzn202003003 http://d.old.wanfangdata.com.cn/Periodical/mssbyrgzn202003003 .

CHEN L C, PAPANDREOU G, KOKKINOS I, et al . Semantic image segmentation with deep convolutional nets and fully connected crfs[J]. arXiv preprint arXiv : 1412.7062, 2014.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]. Advances in neural information processing systems, 2012: 1097-1105.

潘仙张 , 张石清 , 郭文平 . 多模深度卷积神经网络应用于视频表情识别 . 光学精密工程 , 2019 . 27 ( 4 ): 963 - 970 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201904023 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201904023 .

X ZH PAN , SH Q ZHANG , W P GUO . Video-based facial expression recognition using multimodal deep convolutional neural . Opt. Precision Eng. , 2019 . 27 ( 4 ): 963 - 970 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201904023 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201904023 .

SAINATH T N, MOHAMED A, KINGSBURY B, et al . Deep convolutional neural networks for LVCSR[C]. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE , 2013: 8614-8618.

GRAVES A, MOHAMED A, HINTON G. Speech recognition with deep recurrent neural networks[C]. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE , 2013: 6645-6649.

G. LIN, C. SHEN, I. REID, A. van dan Hengel. Efficient piecewise of deep structured models for semantic segmentation[J]. ArXiv Preprint ArXiv: 1504.01013, 2015.

DESMAISON A, BUNEL R, KOHLI P, et al . Efficient continuous relaxations for dense CRF[C]. European Conference on Computer Vision, Springer, Cham , 2016: 818-833.

WANG P, CHEN P, YUAN Y, et al . Understanding convolution for semantic segmentation[C]. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE , 2018: 1451-1460.

XIAN Y, CHOUDHURY S, HE Y, et al . Semantic projection network for zero-and few-label semantic segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 8256-8265.

Z YAN, H ZHANG, Y JIA, et al . Combining the best of convolutional layers and recurrent layers: A hybrid network for semantic segmentation[J]. ArXiv Preprint ArXiv: 1603.04871, 2016.

A ARNAB, S JAYASUMANA, S ZHENG, P. Torr. Higher order potentials in end-to-end trainable conditional random fields[J]. ArXiv Preprint ArXiv : 1511.08119, 2015. http://www.oalib.com/paper/4055092

Views

870

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Spatial adaptation and frequency fusion network for single remote sensing image super-resolution

Multi-scale context-aware network for road extraction in remote sensing images

Improved DeepLabv3+ semantic segmentation incorporating attention mechanisms

Monocular vision transmission line sag measurement method based on local photography

Real-time urban street view semantic segmentation based on cross-layer aggregation network

Related Author

YANG Yichuan

MA Zhongqi

ZHOU Xinyao

ZHENG Fujian

HUANG Hong

LI Zhijie

HUI Aiting

LI Changhua

Related Institution

Beijing Institute of Space Machinery and Electronics

Key Laboratory of Optoelectronic Technology and System， Ministry of Education， Chongqing University

School of Information and Control Engineering， Xi’an University of Architectural Science and Technology

Liangjiang College of Artificial Intelligence， Chongqing University of Technology

School of Mechanical Engineering & Automation， Northeastern University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰