光学学报, 2007, 27 (4): 638, 网络出版: 2007-04-25   

背景高斯化的遥感图像目标检测

Target Detection for Remote Sensing Image Based on Gaussian Transformation of Background
作者单位
西安电子科技大学技术物理学院, 西安 710071
摘要
在假设单一地表遥感图像灰度起伏符合马尔可夫模型的条件下,得到了理想单一地表灰度起伏符合高斯分布的结果。将这一结果应用于遥感图像的目标检测,提出了一种新的基于背景高斯化的遥感图像目标检测方法。该方法首先将遥感图像进行高斯化处理,将其作为近似理想背景,然后将原图像与高斯化背景做差得到残差图,进而对残差图进行目标检测。由于目标本身的信息远离背景高斯化模型,因此在背景消减的过程中,目标信息得到了很好的保持,比在原图上进行目标检测性能得到了很大的提高。实验结果进一步验证了算法具有很好的检测性能。
Abstract
A new target detection algorithm is presented which deals with the problem of detecting target in remote sensing image. Based on the assumption that the distribution of the homogenous land surface is a Markov random field, we analyzed that the distribution of the homogenous land surface background is Gaussian. This model leads to an efficient and effective detector for discriminating man-made objects in real remote sensing imagery. First, the original image is transformed into Gaussian space as the ideal background. And then, the residual image is obtained by subtracting the ideal background from the original images. Finally, a conventional detector is applied to the residual image to complement the further target detection. Because the targets have values deviating significantly from the distribution of the background, the background can be severely decreased during the subtraction. Therefore, the new algorithm has better performance. Some experiments of real remote sensing images proved the validity of the new algorithm.
参考文献

[1] Phil Clare, Mak Bernhardt, William Oxford et al.. A new approach to anomaly detection in hyperspectral images[C]. Proc. SPIE, 2003, 5093: 17~28

[2] D. Manolakis, D. Marden, J. Kerekes et al.. On the statistics of hyperspectral imaging data[C]. Proc. SPIE, 2001, 4381: 308~316

[3] B. A. Bastami, H. Amindavar. A new method for detectability of signals in K-distributed clutter[J]. IEEE, Signal Processing and Its Applications, 2003, 1(1~4): 345~348

[4] M. Bernhardt, W. J. Oxford, P. E. Clare et al.. Statistical detection algorithms in fat-tailed hyperspectral background clutter[C]. Proc. SPIE, 2004, 5573: 215~225

[5] Huang Yinbo, Wang Yingjian. The effect of tracking jitter on the beam spreading induced by atmospheric turbulence[J]. Acta Optica Sinica, 2005, 25(2): 152~156 (in Chinese)
黄印博,王英俭. 跟踪抖动对激光湍流大气传输光束扩展的影响[J]. 光学学报, 2005, 25(2): 152~156

[6] Sun Gang, Weng Ningquan, Xiao Liming et al.. Profile and character of atmospheric temperature[J]. Acta Optica Sinica, 2004, 24(5): 592~596 (in Chinese)
孙刚,翁宁泉,肖黎明 等. 大气温度分布特性及对折射率结构常数的影响[J]. 光学学报, 2004, 24(5): 592~596

[7] Jiaqi Wang, Ping Yu, Changxiang Yan et al.. Space optical remote sensor image motion velocity vector computational modeling, error budget and synthesis[J]. Chin. Opt. Lett., 2005, 3(7): 414~417

[8] Zhou Qingcai, Wang Zhijian, Wang Chunyan.The application of the theory about image stabilization in calculating image motion on space remote sensor[J]. Acta Optica Sinica, 2004, 24(3): 413~417 (in Chinese)
周庆才,王志坚,王春艳. 基于稳像理论的空间光学遥感像移补偿的分析与计算[J]. 光学学报, 2004, 24(3): 413~417

[9] . B. Chapple, D. C. Bertilone, R. S. Caprari et al.. Stochastic model-based processing for detection of small targets in non-Gaussian natural imagery[J]. IEEE Transactions on Image Processing, 2001, 10(4): 554-564.

[10] . Rellier, X. Descombes, F. Falzon et al.. Texture feature analysis using a Gauss-Markov model in hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(7): 1543-1551.

[11] . N. Tran, R. Wehrens, D. H. Hoekman et al.. Initialization of Markov random field clustering of large remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(8): 1912-1919.

[12] . H. S. Solberg, T. Taxt, A. K. Jain. A Markov random field model for classification of multisource satellite imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 1996, 34(1): 100-113.

[13] . Geman, D. Geman. Stochastic relaxation, Gibbs distribution, and bayesian restoration of images[J]. IEEE Transactions Pattern Analysis Machine. Intelligence, 1984, 6(6): 721-741.

[14] . W. J. Stein, S. G. Beaven, L. E. Hoff et al.. Anomaly detection from hyperspectral imageryp[J]. IEEE Signal Process. Mag., 2002, 19(1): 58-69.

[15] . Nasrabadi. Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery[J]. IEEE Transactions Geosci. Remote Sensing, 2005, 43(2): 388-397.

刘德连, 张建奇, 何国经. 背景高斯化的遥感图像目标检测[J]. 光学学报, 2007, 27(4): 638. 刘德连, 张建奇, 何国经. Target Detection for Remote Sensing Image Based on Gaussian Transformation of Background[J]. Acta Optica Sinica, 2007, 27(4): 638.

本文已被 7 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!