基于似圆阴影的光学遥感图像油罐检测

李轩; 刘云清

doi:10.11999/JEIT151334

基于似圆阴影的光学遥感图像油罐检测

doi: 10.11999/JEIT151334

李轩¹,
刘云清²

2.
(长春理工大学电子信息工程学院长春 130022) ②(中国科学院国家空间科学中心复杂航天系统电子信息技术重点实验室北京 100190)

基金项目:

国家973计划(613192)

计量
- 文章访问数: 1650
- HTML全文浏览量: 216
- PDF下载量: 606
- 被引次数: 0
出版历程
- 收稿日期: 2015-11-26
- 修回日期: 2016-03-23
- 刊出日期: 2016-06-19

Oil Tank Detection in Optical Remote Sensing Imagery Based on Quasi-circular Shadow

LI Xuan¹,
LIU Yunqing²

2.
(School of Electronics and Information Engineering, Changchun University of Science and Technology, Changchun 130022, China)

Funds:

The National 973 Program of China (613192)

摘要

摘要: 针对光学遥感图像中受阴影干扰的油罐目标识别率低的问题，该文提出一种将改进的视觉显著模型与似圆阴影区域特征检测相结合的由粗到精的油罐目标检测方法。首先建立改进的视觉显著模型，将油罐从复杂背景中粗分离。然后对分离结果中由油罐产生的似圆阴影区域进行精检测，得到疑似油罐目标。再去除阴影，获得油罐目标的初步检测结果。最后基于图搜索策略及先验知识，确定油罐目标并定位油库区域。实验结果表明，该方法对检测光学遥感图像中存在似圆阴影的油罐目标具有较高的鲁棒性和准确率。同时，在不同环境的光学遥感图像中使用该方法可快速准确地定位油库区域。
- 光学遥感图像 /
- 似圆阴影区域 /
- 视觉显著模型 /
- 特征检测 /
- 油罐
Abstract: To deal with the issue of low oil tanks recognition rate in optical remote sensing image, an improved oil tanks detection method is proposed, which is based on the improved visual saliency model and quasi-circular shadow region. Firstly, the oil tanks are separated from the complex background by using the improved visual saliency model. Secondly, the circular shadow regions are finely detected, and the suspected oil tanks are obtained. Then, the shadow region and the preliminary detection result of oil tanks are obtained. Finally, the false oil tank targets are removed and oil depots are determined based on graph search strategy and prior knowledge. The proposed method is robust to the oil tanks in the optical remote sensing images, and can effectively detect the oil tanks in high recognition rate. The experimental results indicate that the proposed algorithm are fast and accurate to detect the oil tanks, which is suitable for optical remote sensing images of different spatial resolutions.
- Optical remote sensing images /
- Quasi-circular shadow region /
- Visual saliency model /
- Feature detection /
- Oil tanks

HTML全文

参考文献(21)

XU Huaping, CHEN Wei, SUN Bing, et al. Oil tank detection in synthetic aperture radar images based on quasi-circular shadow and highlighting arcs[J]. Journal of Applied Remote Sensing, 2014, 8(1): 083689.

陈爱军, 李金宗. 卫星遥感图像中类圆形油库的自动识别方法[J]. 光电工程, 2006, 33(9): 96-100.

CHEN Aijun and LI Jinzong. Automatic recognition method for quasi-circular oil depots in satellite remote sensing images[J]. Opto-Electronic Engineering, 2006, 33(9): 96-100.

李斌, 尹东, 袁勋, 等. 改进的Hough变换对油库目标识别[J]. 光电工程, 2008, 35(3): 31-33.

LI Bin, YIN Dong, YUAN Xun, et al. Oilcan recognition method based on improved gough transform[J]. Opto- Electronic Engineering, 2008, 35(3): 31-33.

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

HAN Xianwei, FU Yili, and LI Gang. Oil depots recognition based on improved Hough transform and graph search[J]. Journal of Electronics Information Technology, 2011, 33(1): 66-72. doi: 10.3724/SP.J.1146.2010.00112.

HAN Xianwei and FU Yili. Circular array targets detection from remote sensing images based on saliency detection[J]. Optical Engineering, 2012, 51(2): 026201.

YAO Yuan, JIANG Zhiguo, and ZHANG Haopeng. Oil tank detection based on salient region and geometric features[J]. Proceedings of the SPIE, 2014, 9273. doi: 10.1117/12.2072839.

CAI Xiaoyu, SUI Haigang, LV Ruipeng, et al. Automatic circular oil tank detection in high-resolution optical image based on visual saliency and Hough transform[C]. IEEE Workshop on Electronics, Computer and Applications, Ottawa, Canada, 2014: 408-411.

ZHU Chenxian, LIU Bin, ZHOU Yuhao, et al. Framework design and implementation for oil tank detection in optical satellite imagery[C]. IEEE International Geography and Remote Sensing (IGARSS), Munich, Germany, 2012: 6016-6019.

KUSHWAHA N K, CHAUDHURI D, and SINGH M P. Automatic bright circular type oil tank detection using remote sensing images[J]. Defence Science Journal, 2013, 63(3): 298-304.

ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency- tuned salient region detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009: 1597-1604.

CHENG Mingming, MITRA N J, HUANG Xiaolei, et al. Global contrast based salient region detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 569-582.

DUDA R O and HART P E. Use of the Hough transformation to detect lines and curves in pictures[J]. Graphics and Image Processing, 1972, 15(1): 11-15.

VIORICA P, GURDJOS P, and GIOI R G V. A parameterless line segment and elliptical arc detector with enhanced ellipse fitting[C]. Springer-Verlag, European Conference on Computer Vision (ECCV 2012), Berlin, Heidelberg, Part II, 2012: 572-585.

DESOLNEUX A, MOISAN L, and MOREL J M. From Gestalt Theory to Image Analysis: A Probabilistic Approach [M]. New York: Springer Science, USA, 2008: 33-40.

GIOI R G V, JAKUBOWICZ J, MOREL J M, et al. LSD: A fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 722-732.

Ok A O. A new approach for the extraction of aboveground circular structures from near-nadir VHR satellite imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(6): 3125-3140.

Ok A O and EMRE B. Automated detection of oil depots from high resolution images: A new perspective[C]. Remote Sensing and Spatial Information Sciences, Munich, Germany, 2015: 149-156.

KAPUR J N, PRASANNA S, and WONG A K C. A new method for gray-level picture thresholding using the entropy of the histogram[J]. Computer Vision Graphics and Image Processing, 1985, 29(3): 273-285.

施引文献

资源附件(0)

访问统计