Accurate localization and parameter extraction of oil tank in remote sensing images

Han Jiang; Yueting Zhang; Jiayi Guo; Xin Zhao; Fangfang Li; Lijia Huang; Yuxin Hu; Bin Lei; Chibiao Ding

doi:10.11834/jig.200604

Remote Sensing Image Processing | Views : 0 下载量: 646 CSCD: 0

PDF
Export
Share
Collection
Album

Accurate localization and parameter extraction of oil tank in remote sensing images
Vol. 26, Issue 12, Pages: 2953-2963(2021)
Received：21 October 2020，

Revised：2020-12-15，

Accepted：22 December 2020，

Published：16 December 2021
DOI： 10.11834/jig.200604
稿件说明：

移动端阅览

DOI：

Han Jiang, Yueting Zhang, Jiayi Guo, Xin Zhao, Fangfang Li, Lijia Huang, Yuxin Hu, Bin Lei, Chibiao Ding. Accurate localization and parameter extraction of oil tank in remote sensing images[J]. Journal of Image and Graphics, 2021, 26(12): 2953-2963. DOI： 10.11834/jig.200604.

摘要

目的

浮动顶油罐是遥感图像中具有圆形特征的典型人造目标，其高精度定位与参数提取问题是一类代表性的应用问题，针对该问题，传统的基于圆形特征的变换域提取方法鲁棒性差，参数选择需要不断手动调整；基于深度学习的方法利用对已有标注图像的训练求解网络参数，提高了自动化程度，但对于圆形目标而言，覆盖圆周需要较大的感受野，这对应较大的网络结构，随之带来细节信息缺失或参数量、运算量增大的问题。本文针对油罐的定位与参数提取问题，将传统特征提取与深度学习结合，提出了一种计算量小、精度高的方法。

方法

基于快速径向对称变换（fast radial symmetry transform，FRST）后的变换域数据及原始数据构建了卷积神经网络（convolutional neural networks，CNN），给出了训练过程及参数选择，有效地将圆形特征的先验引入深度学习过程，计算复杂度低，用较少层的网络实现了高精度的定位。

结果

基于SkySat数据的实验表明，该方法比单纯基于深度学习的方法在相同网络量级上精度得到了有效提高，预测误差平均降低了17.42%，且随着网络深度的增加，精度仍有明显提高，在较浅层次网络中，预测误差平均降低了19.19%，在较深层次网络中，预测误差平均降低了15.66%。

结论

本文针对油罐遥感图像定位与参数提取问题，提出了一种基于变换域特征结合深度学习的方法，有效降低了计算量，提升了精度和稳定性。本文方法适用于油罐等圆形或类圆形目标的精确定位和参数提取。

Abstract

Objective

Object localization and parameter extraction have been one of the vital applications for remote sensing image interpretation and the basis of information extraction nowadays. The acquired accuracy is the key factor to improve the accuracy of information inversion. As a typical man-made object with circle shape in remote sensing image

the high-precision localization and parameter extraction of floating roof oil tank have been the representative application issues. The elevation of the top cover of the floating roof oil tank has been fluctuated up and down with the change of oil storage volume. The remote sensing image of the oil tank has presented different circle shadows and multiple circle areas in terms of the elevation change. The localization and parameter extraction analysis of the oil tank has referred to the measurement of the center position of the tank roof

the center position of the circular-arc-shaped shadow cast has projected by the sunshine on the floating roof and the radius of the oil tank image

which is of great significance for the inversion of the oil tank structure and the oil storage information. However

the distribution and overlapping characteristics of circles in oil tank images have related to many factors

such as illumination

cloud cover

satellite observation and imaging conditions

background environment

side wall occlusion and so on. Therefore

for localization and parameter extraction of floating roof oil tank

it is necessary to develop a localization and parameter extraction method to adapt with circle shaped objects. The traditional parameterized feature extraction method has included Hough transform and template matching. The emerging deep learning method has been developed recently. Traditional parameterized feature extraction method can make effective use of the circumference feature with the non-learnable and the poor applicability of parameters. The lower automation has relied on priori knowledge to adjust parameters manually. The method based on deep learning has its advantages to use the training of the existing labeled images to solve the parameters of the network

which improves the degree of automation. For objects with circular structure

convolutional neural networks (CNNs) can predict the radius and get accurate location of the circle center. The disadvantages have been described as follows: First

the main feature of an object with circular structure such as oil tank is on the circumference

but not in the circle. The neural networks need to traverse all the pixels

which leads to redundant computation and a low processing efficiency. Next

CNN has increased the receptive field and aggregated the spatial features via cascading networks subject to the receptive field. At last

abundant training samples requirement has not existed in traditional parameterized feature extraction method. This research has proposed a method of low calculation and high precision by combining the traditional feature extraction method with deep learning to resolve the problem of localization and parameter extraction of oil tank in remote sensing images

which no longer needs to sacrifice resolution or increase the network.

Method

A CNN has been constructed via fast radial symmetry transform (FRST). The training process and parameter has been sorted out. The image is processed by FRST and the original image and the processed image are superimposed as two channels of the image into a new dual channel image

which is input into the designed CNN for processing. The result has been compared with the result of the single channel original image into the same CNN for processing. The experiment is based on a self-made dataset of SkySat satellite data

compared under two CNN architectures

and ran once under two fixed random seeds. This method has illustrated the priori knowledge of circular feature into the deep learning process effectively. Low-computational complexity has been presented. High-precision localization based on relatively few layers of network has been realized.

Result

The experimental results have shown that the accuracy of the proposed method is effectively improved at the same network level and the average prediction error is reduced by 17.42%. Moreover

the prediction error has been decreased by 19.19% on average in the shallower network. In the deeper network

the prediction error has been deducted by 15.66% on average.

Conclusion

This research has demonstrated the transform domain features combined with deep learning to improve the accuracy of the localization and parameter extraction of oil tank in remote sensing images effectively.

关键词

Keywords

references

Cai X Y and Sui H G. 2015. A saliency map segmentation oil tank detection method in remote sensing image. Electronic Science and Technology, 28(11): 154-156, 160

蔡肖芋, 眭海刚. 2015. 一种显著图分割的遥感油库检测方法. 电子科技, 28(11): 154-156, 160 [DOI:10.16180/j.cnki.issn1007-7820.2015.11.041]

Duda R O and Hart P E. 1972. Use of the Hough transformationto detect lines and curves in pictures. Communications of the ACM, 15(1): 11-15[DOI:10.1145/361237.361242]

Gong R. 2016. "Sky Sat". Satellite Application, (7): 82

龚燃. 2016. "天空卫星". 卫星应用, (7): #82

Han X W, Fu Y L and Li G. 2011. Oil depots recognition based on improved Hough transform and graph search. Journal of Electronics and Information Technology, 33(1): 66-72

韩现伟, 付宜利, 李刚. 2011. 基于改进Hough变换和图搜索的油库目标识别. 电子与信息学报, 33(1): 66-72)[DOI:10.3724/SP.J.1146.2010.00112]

He K M, Zhang X Y, Ren S Q and Sun J. 2015. Deep residual learning for image recognition[EB/OL]. [2020-10-01] . https://arxiv.org/pdf/1512.03385.pdf https://arxiv.org/pdf/1512.03385.pdf

Hinton G E, Osindero S and Teh Y W. 2006. A fast learning algorithm for deep belief nets. Neural Computation, 18(7): 1527-1554[DOI:10.1162/neco.2006.18.7.1527]

Kimme C, Ballard D and Sklansky J. 1975. Finding circles by an array of accumulators. Communications of the ACM, 18(2): 120-122[DOI:10.1145/360666.360677]

Krizhevsky A, Sutskever I and Hinton G E. 2012. ImageNet classification with deep convolutional neural networks//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, USA: Curran Associates Inc. : 1097-1105

LeCun Y, Boser B, Denker J S, Henderson D, Howard R E, Hubbard W and Jackel L D. 1989. Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4): 541-551[DOI:10.1162/neco.1989.1.4.541]

LeCun Y, Bengio Y and Hinton G. 2015. Deep learning. Nature, 521(7553): 436-444[DOI:10.1038/nature14539]

Loy G and Zelinsky A. 2003. Fast radial symmetry for detecting points of interest. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(8): 959-973[DOI:10.1109/TPAMI.2003.1217601]

Meng F S. 2012. Review of change detection methods based on remote sensing images. Technology Innovation and Application, (24): 57, 58

孟繁烁. 2012. 基于遥感影像的变化检测方法综述. 科技创新与应用, (24): 57, 58

Ok A O and Başeski E. 2015. Circular oil tank detection from panchromatic satellite images: a new automated approach. IEEE Geoscience and Remote Sensing Letters, 12(6): 1347-1351[DOI:10.1109/LGRS.2015.2401600]

Reisfeld D, Wolfson H and Yeshurun Y. 1995. Context-free attentional operators: the generalized symmetry transform. International Journal of Computer Vision, 14(2): 119-130[DOI:10.1007/BF01418978]

Sela G and Levine M D. 1997. Real-time attention for robotic vision. Real-Time Imaging, 3(3): 173-194[DOI:10.1006/rtim.1996.0057]

Shin B G, Park S Y and Lee J J. 2007. Fast and robust template matching algorithm in noisy image//Proceedings of 2007 International Conference on Control, Automation and Systems. Seoul, Korea (South): IEEE: 6-9[ DOI: 10.1109/iccas.2007.4406869 http://dx.doi.org/10.1109/iccas.2007.4406869 ]

Sui X L, Zhang T and Qu Q X. 2019. Application of deep learning in target recognition and position in remote sensing images. Technology Innovation and Application, (34): 180-181

隋雪莲, 张涛, 曲乔新. 2019. 深度学习在遥感影像目标识别与定位中的应用研究. 科技创新与应用, (34): 180-181

Sun Z J, Xue L, Xu Y M and Wang Z. 2012. Overview of deep learning. Application Research of Computers, 29(8): 2806-2810

孙志军, 薛磊, 许阳明, 王正. 2012. 深度学习研究综述. 计算机应用研究, 29(8): 2806-2810[DOI:10.3969/j.issn.1001-3695.2012.08.002]

Wang Y J, Zhang Q, Zhang Y M, Meng Y and Guo W. 2019. Oil tank detection from remote sensing images based on deep convolutional neural network. Remote Sensing Technology and Application, 34(4): 727-735

王颖洁, 张荞, 张艳梅, 蒙印, 郭文. 2019. 基于深度卷积神经网络的油罐目标检测研究. 遥感技术与应用, 34(4): 727-735[DOI:10.11873/j.issn.1004-0323.2019.4.0727]

Wu X D, Feng W F, Feng Q Q, Li R S and Zhao S. 2015. Oil tank extraction from remote sensing images based on visual attention mechanism and Hough transform. Journal of Information Engineering University, 16(4): 503-506

吴晓东, 冯伍法, 冯倩倩, 李润生, 赵爽. 2015. 基于视觉注意机制和Hough变换融合的遥感影像油罐提取. 信息工程大学学报, 16(4): 503-506[DOI:10.3969/j.issn.1671-0673.2015.04.021]

Xu H P, Chen W, Sun B, Chen Y F and Li C S. 2014. Oil tank detection in synthetic aperture radar images based on quasi-circular shadow and highlighting arcs. Journal of Applied Remote Sensing, 8(1): #083689[DOI:10.1117/1.JRS.8.083689]

Yu S T. 2019. Research on Oil Tank Volume Extraction Based on High Resolution Remote Sensing Image. Dalian: Dalian Maritime University

于圣涛. 2019. 基于高分辨率遥感影像的油罐体积求取研究. 大连: 大连海事大学

Zhang J F, Wang Q Q, Wang S Y, Zhang H, Hu X H and Wang R. 2017. Oil tank detection and reserve analysis method based on high-resolution optical remote sensing image. China, 201710727161.4

张金芳, 王庆全, 王思雨, 张慧, 胡晓惠, 王瑞. 2017. 基于高分辨率光学遥感图像的油罐检测和储量分析方法. 中国, 201710727161.4

Zhang W S, Wang C, Zhang H, Wu F, Tang Y X and Mu X P. 2006. An automatic oil tank detection algorithm based on remote sensing image. Journal of Astronautics, 27(6): 1298-1301

张维胜, 王超, 张红, 吴樊, 汤益先, 穆湘萍. 2006. 基于遥感影像的油罐自动检测算法. 宇航学报, 27(6): 1298-1301[DOI:10.3321/j.issn:1000-1328.2006.06.035]