全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

结合边缘和区域的活动轮廓模型SAR图像目标轮廓提取

DOI: 10.11834/jig.20140714

Keywords: 合成孔径雷达,轮廓提取,活动轮廓模型,似然比,向量场卷积,G0分布

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的目标轮廓表征了目标形状,可用于目标方位角估计、自动目标识别等,因此提取合成孔径雷达(SAR)图像中的目标轮廓受到了人们的广泛关注。受SAR图像乘性噪声的影响,传统的目标轮廓提取方法应用在SAR图像时失效。针对这一问题,提出一种将基于边缘的活动轮廓模型和基于区域的活动轮廓模型相结合的活动轮廓模型。方法以真实SAR图像为基础,分析了向量场卷积(VFC)活动轮廓模型以及区域竞争(RC)活动轮廓模型各自的特点和优势,发现这两个模型存在一定的互补性,因此将这两个模型进行了结合,得到了一种新的SAR图像目标轮廓提取方法。结果基于真实SAR图像的实验结果表明,本文方法能较好地应对SAR图像信噪比较低、目标边缘模糊等特点,能准确地获得SAR图像目标轮廓。结论本文方法可用于执行实际的SAR图像轮廓提取任务,为后续的SAR图像自动识别和特征级图像融合等任务提供了较为优良的输入信息。

References

[1]  Kuang G Y, Gao G, Jiang Y M, et al. Synthetic Aperture Radar Target Detection Theory Algorithms and Applications[M]. Changsha: National University of Defense Press, 2007: 3-9.[匡纲要,高贵,蒋咏梅,等. 合成孔径雷达:目标检测理论、算法及应用[M]. 长沙: 国防科技大学出版社,2007: 3-9.]
[2]  Novak L M, Halversen S D. Effects of polarization and resolution on SAR ATR[J]. IEEE Transactions on Aerospace and Electronic System, 1997, 33(1): 102-115.
[3]  Gerrnain O, Refregier P. Edge location in SAR images: performance of the likelihood ratio filter and accuracy improvement with an active contour approach[J]. IEEE Transactions on Image Processing, 2001, 1(10): 72-78.
[4]  Fiortoft R, Delignon Y, Pieczynski W, et a1. Unsupervised classification of radar images using hidden Markov chains and hidden Markov random fields[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 3(41): 675-686.
[5]  Kass M, Witkin A, Terzopoulos D. Snakes-active contour models[J]. International Journal of Computer Vision, 1987, 1: 321-331.
[6]  Cohen L D. On active contour models and balloons[J]. CVGIP: Image Understanding, 1991, 53(2): 211-218.
[7]  Xu C, Prince J L. Snakes, shapes, and gradient vector flow[J]. IEEE Transactions on Image Processing, 1998, 7(3): 359-369.
[8]  Deng X P, He C, Sun H. An improved GVF snake model and its application to linear feature extraction from SAR images[C]//Proceedings of the 10th IEEE International Conference on Signal Processing. Beijing, China: IEEE, 2010: 2063-2066.
[9]  Liu C C, Tsai C Y, Tsui T S, et al. An improved GVF snake based breast region extrapolation scheme for digital mammograms[J]. IEEE Transactions on Image Processing, 2012, 39(4): 4505-4510.
[10]  Ray N, Acton S T. Motion gradient vector flow: an external force for tracking rolling leukocytes with shape and size constrained active contours[J]. IEEE Transactions on Medical Imaging, 2004, 23(12): 1466-1478.
[11]  Li B, Acton S T.Active contour external force using vector field convolution for image segmentation[J].IEEE Transactions on Image Processing, 2007, 16(8): 2096-2106.
[12]  Zhou Y N, Cheng X, Luo J C, et al. Automatic snakes based on modified GVF[J]. Journal of Image and Graphics, 2012, 17(2): 256-262.[周亚男,程熙,骆剑承,等. 改进GVF的自动Snakes模型[J]. 中国图象图形学报. 2012, 17(2): 256-262.][DOI: 10.11834/jig.20120215]
[13]  Ronfard R. Region-based strategies for active contour models[J]. International Journal of Computer Vision, 1994, 13(2): 229-251.
[14]  Zhu S C, Yuille A. Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(9): 884-900.
[15]  Chan T, Vese L. Active contours without edges[J]. IEEE Transactions on Image Processing, 2001, 10(2):266-277.
[16]  Gao G. Review on the statistical modeling of SAR images[J]. Signal Processing, 2009, 25(8): 1270-1278.[高贵. SAR图像统计建模研究综述[J]. 信号处理, 2009, 25(8): 1270-1278.]
[17]  Frery A C, Muller H, Freitas C C, et al. A model for extremely feterogeneous Clutter[J]. IEEE Transactions on Geoscience and Remote Sensing, 1997, 35(3): 648-659.
[18]  Fjortoft R, Lopes A, Marthon P,et al.An optimal multiedge detector for SAR image segment[J]. IEEE Transactions on Geoscience and Remote Sensing, 1988,36(3): 793-802.
[19]  Xie K. Research on target detection in synthetic aperture radar image[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2011.[谢?. 合成孔径雷达目标检测方法研究[D]. 南京:南京航空航天大学, 2011.]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133