基于多幅同目标图像和HMM的SAR图像目标识别
doi: 10.3724/SP.J.1146.2007.00334
Synthetic Aperture Radar Image Target Recognition Based on Multi-Images of the Same Target and Hidden Markov Models
-
摘要: 该文提出了一种基于多幅同目标图像和隐马尔可夫模型的合成孔径雷达图像目标识别方法。该方法通过小波域主成分分析提取目标图像特征向量，结合多幅不同方位角下的同目标图像的特征向量生成单幅图像的特征序列，用隐马尔可夫模型对特征序列进行识别。实验结果表明，该方法可明显提高目标的正确识别率，是一种有效的合成孔径雷达图像目标识别方法。Abstract: This paper presents a method for synthetic aperture radar images target recognition based on multi images of the same target and Hidden Markov Models (HMM). Feature vectors of target images are extracted with principal component analysis in wavelet domain. Feature sequences of an image are obtained from the feature vectors of multi images of the same target in different azimuths. Target recognition is carried out for feature sequences with the HMM. The experiments results show that the correctness of recognition is enhanced obviously with the proposed method, and it is an effective method for SAR images target recognition.
-
[1] Ross T D, Worrell S W, and Velten V J, et al.. Standard SARATR evaluation experiments using the MSTAR public releasedata set[J].Proc. SPIE.1998, Vol. 3370:566-573 [2] Zhao Q and Principe J C. Support vector machines for SARautomatic target recognition[J].IEEE Trans. on Aerospace andElectronic Systems.2001, 37(2):643-654 [3] Kottke D P and Fiore P D. A design for HMM-based SARATR[J].Proc. SPIE.1998, Vol. 3370:541-551 [4] Nilubol C and Pham Q H. Translational and rotationalinvariant hidden Markov model for automatic targetrecognition[J].Proc. SPIE.1998, Vol. 3374:179-185 [5] Nilubol C and Mersereau R M. An improved hidden Markovmodel classifier for SAR imaged[J].Proc. SPIE.1999, Vol.3720:113-122 [6] Albrecht T W and Gustafson S C. Hidden Markov models forclassifying SAR target images. Proc.[J]. SPIE.2004,Vol. 5427:302- [7] Rabiner L. A tutorial on hidden Markov models and selectedapplications in speech recognition[J].Proc. IEEE.1989, 77:257-286 [8] Sandirasegaram N and Englisth R. Comparative analysis offeature extraction (2D FFT and wavelet) and classification(Lp metric distances, MLP NN, and HNeT) algorithms forSAR imagery[J].Proc. SPIE.2005, Vol. 5808:314-325 -
计量
- 文章访问数: 3473
- HTML全文浏览量: 136
- PDF下载量: 1092
- 被引次数: 0
下载:
