共查询到19条相似文献,搜索用时 640 毫秒
1.
2.
3.
针对空谱信息中普遍存在的异常干扰现象,提出了基于空谱联合聚类的自适应核协同表示高光谱异常目标探测算法.算法充分发挥了基于密度的聚类算子(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)对于异常点的筛选特性,在DBSCAN聚类去除异常波谱的基础上,采用分波段子集随机投影变换对数据降维处理,以减少谱噪声和谱冗余,并采用DBSCAN聚类消除了局部背景像元中的杂乱点对协同探测算法结果的干扰.研究了背景离散度对核参选择的影响,比较了不同的核估计方法,并提出基于平均差的自适应核协同算法.采用该方法对AVIRIS和ROSIS的三组数据进行仿真实验并与现有算法进行了对比,结果表明该算法表现出较好的探测性能. 相似文献
4.
提出了结合稀疏编码和空间约束的红外图像聚类分割新算法, 在稀疏编码的基础上融合聚类算法, 扩展了传统的基于K-means聚类的图像分割方法. 结合稀疏编码的聚类分割算法能有效融合图像的局部信息, 便于利用像素之间的内在相关性, 但是对于分割会出现过分割和像素难以归类的问题.为此, 在字典的学习过程中, 将原子的聚类算法引入其中, 有助于缩减字典中原子所属类别的数目, 防止出现过分割; 考虑到像素及其邻域像素具有类别属性一致性的特点, 引入了空间类别属性约束信息, 并给出了一种交替优化算法. 联合学习字典、稀疏系数、聚类中心和隶属度, 将稀疏编码系数同原子对聚类中心的隶属程度相结合, 构造像素归属度来判断像素所属的类别. 实验结果表明, 该方法能够有效提高红外图像重要区域的分割效果, 具有较好的鲁棒性.
关键词:
图像分割
稀疏编码
聚类
空间约束 相似文献
5.
将人工智能算法引入目标检测,空间红外弱小目标的检测也可归为模糊检测的二分类问题。依据空中红外弱小目标的探测模型,建立了信号电压比光谱模型,仿真分析表明电压比变化趋势与目标的速度、姿态和两机态势有关,可用以检测目标。采用动态特征构建理论,构建了红外弱小目标的双色比特征空间,基于该特征空间,优化最小二乘分类算法,用于从光谱信号层级检测目标。该方法不仅缩小了样本数据量,而且防止了高斯核函数参数选择引起的“过拟合”现象,既保证了分类精度,又使分类速率提高近1倍,为人工智能算法用于红外弱小目标检测提供了参考依据。 相似文献
6.
基于分类的红外云层背景弱小目标检测方法 总被引:3,自引:2,他引:1
提出了一种新的基于模糊分类的红外云层背景弱小目标检测方法.根据红外成像的特点,将红外云层背景弱小目标图像分为三类:边缘类、净空及云中类、弱小目标类;对不同类别图像进行分析,建立了分类模型,并定义了方向特征矢量,将其作为类别的特征矢量;根据模糊分类的理论,定义了类相似系数来判别图像中每一个像素的类别属性,保留弱小目标类的像素点完成检测.实验结果表明,该方法能够对红外弱小目标图像中不同类型的区域进行准确的分类,从而较好的实现了对低信杂比的复杂云层背景图像中的弱小目标检测. 相似文献
7.
8.
在小数据量计算最大Lyapunov指数的过程中,为了减少人为因素识别线性区域带来的误差,提出一种基于模糊C均值聚类的新方法.该方法根据平均发散程度指数曲线的变化特征,利用分类算法进行识别.首先,利用小数据量算法对混沌时间序列进行计算得到平均发散程度指数集合;其次,利用模糊C均值聚类算法对平均发散程度指数集合进行分类,得到不饱和数据;然后,对不饱和的二阶差分数据进行分类,得到零附近波动数据并剔除粗大误差,再对保留的有效数据利用统计方法识别出线性区域;最后,对线性区域进行最小二乘法拟合得到最大Lyapunov指数.为了验证该算法的有效性,对著名Logistic和Hénon混沌系统进行了仿真,所得结果接近理论值.实验表明,所提出的新方法与主观识别方法比较,计算结果更加准确. 相似文献
9.
基于伪彩色融合图像聚类的夜视图像上色算法 总被引:6,自引:0,他引:6
提出一种将小波融合和基于伪彩色融合图像的C均值聚类用于图像色彩传递算法中的彩色夜视方法.在色彩传递前将可见光和红外图像进行小波融合得到灰度融合图像作为目标图像,保持了较好的纹理信息和目标信息;再对彩色源网像进行基于连接相对熵的彩色阈值分割;然后针对灰度融合图像的特点,根据一种基于伪彩色融合图像的C均值聚类方法,将伪彩色融合图像的彩色信息作为特征向量应用在夜视图像的分类当中,得到较好的分类效果,并基于此分类结果再进行色彩传递,得到更为自然的彩色夜视图像.实现了对夜视图像的自动色彩传递,得到的罔像色彩较真实.纹理清晰,将有利于人眼的目标识别. 相似文献
10.
茶叶的品种不同,其有机化学成分含量往往不同,其功效也是不尽相同的,因此,研究出一种简单、高效、识别率高的茶叶品种鉴别技术方法是十分有必要的。中红外光谱技术是一种快速检测技术,在用中红外光谱仪采集得到的茶叶中红外光谱中含有噪声信号。为了对含噪声茶叶中红外光谱的准确分类以实现茶叶品种分类,将可能模糊C-均值聚类(PFCM)思想应用到K调和均值(KHM)聚类,设计出一种可能模糊K调和均值(PFKHM)聚类算法,计算出PFKHM的模糊隶属度、典型值和聚类中心。可能模糊K调和均值聚类能有效解决K调和均值聚类的噪声敏感性问题。用傅里叶红外光谱分析仪(FTIR-7600型)分别对三种茶叶(优质乐山竹叶青、劣质乐山竹叶青和峨眉山毛峰)进行扫描以获取它们的傅里叶中红外光谱。光谱波数区间是4 001.569~401.121 1 cm-1。先采用主成分分析法(PCA)将光谱数据压缩到20维,再采用线性判别分析(LDA)将光谱数据压缩到两维并提取鉴别特征信息。最后分别用K调和均值聚类和可能模糊K调和均值聚类实现茶叶品种分类。实验结果:当权重指数m=2,q=2和p=2时,KHM具有91.67%的聚类准确率,PFKHM聚类准确率达到94.44%;KHM迭代12次达到收敛,而PFKHM迭代11次就可以达到收敛。采用傅里叶红外光谱技术检测茶叶,用主成分分析和线性判别分析压缩光谱数据,再用可能模糊K调和均值聚类进行品种分类可快速、准确地实现茶叶品种的鉴别。 相似文献
11.
Delian Liu Jianqi Zhang Weike Dong 《International Journal of Infrared and Millimeter Waves》2007,28(5):373-381
A new algorithm is presented which deals with the problem of detecting small moving targets in infrared image sequences that
also contain drifting and evolving clutter. Through development of models of the temporal behavior of the static background,
target and cloud edge on a single pixel basis, the new algorithm employing the connecting line of the stagnation points (CLSP)
of the temporal profile as the baseline is created and tested. The deviation of the temporal profile and its CLSP is analyzed
and it is determined that the distribution of the residual temporal profile obtained by subtracting the baseline from the
temporal profile can be modeled by a Gaussian distribution. The occurrences of the targets have intensity values significantly
different to the distribution of the residual temporal profile. Unlike the conventional 3-D method, this new algorithm operates
on the temporal profile in 1-D space, not in 3-D space, thus having a higher computational efficiency. Experiments with real
IR image sequences have proved the validity of the new approach.
This work was supported by National Natural Science Fund of China (No. 60277005). 相似文献
12.
为进行强目标相关旁瓣干扰下的相邻弱目标检测,采用稀疏重建理论进行多目标方位估计。高信噪比情况下,由方位估计结果即可完成目标检测;对于低信噪比弱目标回波,为提高系统检测能力,结合方位估计结果,提出了两种检测算法,前者类似于传统CLEAN算法,从能量角度进行目标检测;后者则利用相关函数能量集中于主瓣的特点,通过计算将目标方位估计结果中非零元素置零前后匹配滤波峰值的差值,采用Page-test序贯检测器进行多目标检测。仿真和试验数据处理结果表明,相同检测概率下,第二种方法具有更加优良的弱目标检测性能。 相似文献
13.
14.
15.
Infrared (IR) image fusion is designed to fuse several IR images into a comprehensive image to boost imaging quality and reduce redundancy information, and image matching is an indispensable step. However, Conventional matching techniques are susceptible to the noise and fuzzy edges in IR images and it is therefore very desirable to have a matching algorithm that is tolerant to them. This paper presents a method for infrared image matching based on the SUSAN corner detection. To solve the problems of the traditional SUSAN algorithm including the fixed threshold of gray value difference and the failed detection of symmetry corners, an adaptive threshold extraction method is raised in this study. Furthermore, an attached double ring mask is used to improve the complex corner detection capability. A constraint condition and a principle of gravity are adopted to filtrate the candidate corners. The proposed method is qualitatively and quantitatively evaluated on IR images in the experiments. In comparison with other methods, better performance has been achieved. 相似文献
16.
The rock near-infrared spectrum contains information of its composition and structure. The interpretation of rock near-infrared spectrum is one of the important approaches in the qualitative and quantitative analyses of the alteration minerals in rock. The rock near-infrared spectra are classified using optimized fuzzy C-means clustering algorithm, and the main mineral composition is obtained for different rock samples through the analysis of cluster centers. The minimum Spectral Correlation Coefficient is used as the objective function to classify the simulation data. In this study, the classification method was first tested for parameter setting using simulation data, which was the mixture of several standard mineral spectra quantified in terms of reflectivity in the near-infrared band. Classification accuracies under different fuzzy index values are compared. When the fuzzy index value is 1.5, the classification accuracy of the simulation samples is 83%. The initial values of different cluster centers were shown to affect the classification result. In the practical application, the initial values of cluster centers need to be rationally chosen based on the knowledge of mineral spectroscopy. This method is applied in the clustering analysis of the rock near-infrared spectra, which were also quantified in terms of reflectivity in the near-infrared band. These actual rock near-infrared spectra were measured by a spectrometer, while the classification results were compared with X-ray diffraction analysis to show the effectiveness of our algorithm. Our study has shown that, with the optimized fuzzy C-means clustering algorithm, the interpretation of rock near-infrared spectra can help us obtain information of the mineral composition and structure more effectively in terms of accuracy and speed. This method is suitable for the rapid processing of massive rock near-infrared spectra and may become an important technology in geological survey and geological prospecting. 相似文献
17.
18.
针对单机红外搜索跟踪(IRST)系统探测距离和精度有限,得到的红外图像在杂乱背景和强噪声环境中弱小目标难以检测的问题,采用双机IRST对同时刻同目标区域探测后的图像进行配准融合,融合过程中采用高频基于区域、低频基于像素的多规则算法,提出一种基于小波变换与边缘信息表征的目标检测方法。仿真实验表明,多规则融合算法使图像质量评价指标提高了30%~50%,该目标检测方法可有效剔除虚假目标及滤除杂波干扰,从融合滤波前的7个减少到3个,虚警率降低,有助于弱小目标更为精确的检测识别。 相似文献