引用本文: | 王玉明,施云飞,王建,等.基于方位特征序列的地雷鉴别算法[J].国防科技大学学报,2013,35(6):88-95.[点击复制] |
WANG Yuming,SHI Yunfei,WANG Jian,et al.A new landmine discrimination approach based on sequential aspect features [J].Journal of National University of Defense Technology,2013,35(6):88-95[点击复制] |
|
|
|
本文已被:浏览 6677次 下载 6345次 |
基于方位特征序列的地雷鉴别算法 |
王玉明, 施云飞, 王建, 宋千, 黄晓涛 |
(国防科技大学 电子科学与工程学院, 湖南 长沙 410073)
|
摘要: |
在使用低频超宽带合成孔径雷达(UWB SAR)对地雷进行探测的过程中,根据目标电磁散射随方位角和入射角的变化特性,提出一种利用双峰间距和频率凹点特征沿方位向变化的隐马尔科夫模型(HMM)鉴别算法。该算法首先针对目标感兴趣区域(ROI)图像估计其各方位回波响应,然后利用时频原子提取时域双峰间距和频率凹点,进而得到随方位角变化的特征序列,再通过SAR工作时方位角和入射角的变化特点以及训练样本确定HMM参数,并在此基础上计算疑似目标新的特征矢量,采用马氏距离进行判别。实验结果表明了本文所提方法在目标鉴别方面的有效性。 |
关键词: 方位特征序列 时频原子 地雷鉴别 隐马尔科夫模型 |
DOI: |
投稿日期:2013-04-01 |
基金项目:国家自然科学基金资助项目(61271441);全国优秀博士学位论文作者专项资金资助项目(201046) |
|
A new landmine discrimination approach based on sequential aspect features |
WANG Yuming, SHI Yunfei, WANG Jian, SONG Qian, HUANG Xiaotao |
(College of Electronic Science and Engineering, National University of Defense Technology,Changsha 410073,China)
|
Abstract: |
Low-frequency ultra-wideband synthetic aperture radar (UWB SAR) is a promising technology for landmine detection. According to the scattering characteristics of body-of-revolution (BOR) targets along with azimuth angles and incident angles, a Hidden Markov model (HMM) discrimination algorithm is proposed, using such sequential features as double-hump distance and notch frequency. First, the algorithm estimated the target scatterings in all azimuths based on regions of interest (ROI). Second, sequential aspect features were extracted by sparse time-frequency representation. Then the HMM parameters were trained with the labeled samples and the probability of occurrence was computed to discriminate suspicions targets. The experimental results indicate that the proposed algorithm is effective in BOR target discrimination. |
Keywords: sequential aspect features time-frequency atom landmine discrimination hidden Markov model |
|
|
|
|
|