基于可变类FCM算法的多光谱遥感影像分割

为了自动确定多光谱遥感影像中地物目标类别数,该文提出一种基于可变类模糊C均值(Fuzzy C-Means, FCM)的多光谱遥感影像分割方法。首先定义像素与聚类的非相似性测度并据此构建目标函数,而后通过求解目标函数得到最优模糊隶属度和聚类中心。其次,研究模糊因子与影像地物目标类别数的关系,并通过定义划分熵(Partition Entropy, PE)指数优选模糊因子,选择PE指数值稳定收敛后所对应的最小模糊因子值为最优模糊因子,根据模糊因子与类别数的关系得到最优类别数,从而实现了影像的可变类分割。最后,利用提出算法分别对合成和真实多光谱遥感影像进行分割实验,实验结果表明,提出算法不仅能自动确定影像的最优类别数,还能获得较好的分割结果,为实现自动确定遥感影像中地物目标类别数提供新方法。     

利用地物波谱学习的遥感影像波段模拟方法

针对已有遥感影像模拟方法难以在影像光谱维上扩展的不足,提出了一种基于地物波谱学习的遥感影像波段模拟方法.以地物波谱库作为先验知识,通过支持向量机拟合地物在不同观测波段范围内反射率之间的复杂非线性关系,进而在多光谱遥感影像已有波段的基础上模拟一个新的波段影像.通过模拟TM红波段影像的实验,证明本方法能较为准确地模拟出真实的光谱影像,其模拟结果可靠.进一步将该方法应用于模拟IRS真彩色影像,验证了本方法的实用性.本方法能够有效地解决多光谱影像波段缺损的问题,并在一定程度上可解决较高空间分辨率遥感影像光谱维的不足,为建立地物波谱与遥感像元波谱的定量联系提出了新的思路.     

基于多特征的遥感影像决策树分类

构建了一种基于多特征的遥感影像决策树分类方法。通过对遥感影像进行波段代数运算、主成分分析和图像分割等处理,提取出影像上地物的光谱维特征、纹理特征和形状特征。在此基础上,结合试验区主要地物类型提纯后的训练样本集,采用C5.0决策树分类法进行影像分类,实现主要地物的空间分布专题信息提取,并利用该方法对Landsat-5TM影像进行了分类实验。结果表明,所提出的方法能够有效地提高分类精度。     

基于光谱加权低秩矩阵分解的高光谱影像去噪方法

高光谱遥感影像在获取和传输过程中会受到各种类型噪声的污染,不仅降低影像质量,也限制了其后续应用的精度。高光谱影像噪声类型复杂多样,且噪声在不同波段上的强度也并不相同。通过引入光谱域上的权重矩阵,文中提出了一种基于光谱加权低秩矩阵分解的高光谱遥感影像混合噪声去除方法,利用光谱权重矩阵均衡不同波段的噪声强度差异性。为进一步将噪声与纯净影像分离,利用加权核范数最小化来约束纯净高光谱影像的局部低秩结构,并利用交替方向乘子法对所提出的模型进行优化求解。通过对模拟与真实高光谱遥感数据的实验,验证了所提方法的有效性与优越性。     

基于多光谱的空间点目标特征提取与识别

基于实际测量的空间目标多光谱数据,提出了新的多光谱特征分析方法,即把目标红外辐射分为长、中、短三个波段,分析提取了三个波段内的辐照度,以及长波段、中波段辐照度与短波段辐照度的比值,估算出目标温度和有效辐射面积,并利用BP神经网络对四类目标进行识别试验,取得了好的识别效果。     

基于空谱联合和波段分类的高光谱压缩感知重构

卫星在获取地面信息时会受到大气、电磁波的干扰,导致高光谱影像本身产生坏线和噪声。针对这一问题,本文结合高光谱遥感影像的特性提出了一种基于空谱联合和波段分类的影像重构方法。首先,根据噪声影响程度将影像波段分为坏线强干扰波段和非干扰低噪声波段;其次,对波段进行分组,确定每组参考波段,并对参考波段进行独立重构;然后,根据参考波段构建双模式空谱联合预测模型,利用正则化交叉投影得到非参考波段重构影像;最后,对坏线强干扰波段,先进行独立重构,然后对重构影像进行小波分解,通过高频校正得到了干扰波段最终重构影像。实验表明,本文方法对重构高光谱影像的平均信噪比较传统方法提高了1~2dB。     

基于GA优化的地物红外光谱组合识别

为了从TM影像中提取不同地物红外光谱信息特征，构造了地物光谱组合的函数关系式，提出了从地物TM影像中分辨出某类地物的一般原则，并采用遗传算法优化确定地物光谱组合关系式中的系数。根据不同地物与函数值分布范围的对应关系。可以较容易地由TM影像作出多种不同地物的识别。实例分析表明这种地物光谱识别模型具有简单性、实用性和可分辨性等特点。     

一种基于BP网络的星图识别算法

为了提高星图识别算法的抗噪性能,提出一种基于逆向传播(Back Propagation,BP)网络的识别算法。该算法通过将星图转换成“0”、“1”和“2”的网格矩阵,提取行列数值和星数形成匹配向量,利用多个BP识别子网进行训练完成匹配识别。通过仿真试验得出以下结论:对星等位置和星等添加噪声,当位置噪声标准偏差为2像素时,BP网络算法的识别率和识别时间相对传统栅格算法分别提高2%和60ms,对噪声有较强抗干扰能力,表明BP网络算法具有更快的识别速度。     

一种基于改进子空间划分的波段选择方法

高光谱图像具有光谱分辨率高、波段连续、数据量大、图谱合一等特点。然而较高的光谱分辨率会造成波段间相关性强,信息冗余多。所以如何从数百个高光谱波段中选出有利于识别或分类的波段组合成为了高光谱应用需要解决的问题。文章针对相邻波段间相关性较大的特点,提出一种改进的对波段相关矩阵进行全局搜索的子空间划分的波段选择方法。该方法克服了传统只利用相关向量对波段进行划分的缺陷,利用整个相关矩阵进行全局搜索划分,再在划分后的子空间内进行波段选择,从而降低了波段之间的相关性。文章最后使用上述方法对AVIRIS数据进行波段选择,并通过SVM方法对其进行地物分类,结果表明该方法较不进行子空间划分的波段选择方法有较高的分类精度。     

端元匹配的遥感影像地物自适应光谱表征

光谱信息是遥感识别地物的依据,而目前已发展的典型地类的光谱指数模型有限,波谱库中的标准地物类型及其普适性也是有限的.鉴于此,提出一种端元匹配的地物自适应光谱表征方法,通过选取贴合影像本身的端元,并综合光谱角和距离度量对影像和端元光谱进行综合匹配.通过ETM+(Enhanced Thematic Mapper)影像上对植被、水体与美国地质调查局(United States Geological Survey,USGS)波谱库及归一化植被/水体指数的对比实验,及阴影、裸地等的验证实验,证实了该方法的有效性和普适性.     

基于神经网络的图像识别

神经网络图像识别技术是随着当代计算机技术、图像处理、人工智能、模式识别理论等发展起来的一种新型图像识别技术。在进行图像识别之前需要利用数字图像处理技术进行图像预处理以及特征提取。本文选取字符图像0~9作为识别目标,对图像预处理过程进行了叙述,并在此基础上选取字符图像矩阵每行的与每列的黑色像素点之和以及图像欧拉数这两个特征作为BP神经网络的输入样本。经实验仿真表明图像的平均识别率为89%,这表明图像预处理的结果和提取的特征是合适的、有效的,设计的BP网络也较好的完成了模式分类识别工作。     

Consistent landmark and intensity-based image registration

Two new consistent image registration algorithms are presented: one is based on matching corresponding landmarks and the other is based on matching both landmark and intensity information. The consistent landmark and intensity registration algorithm produces good correspondences between images near landmark locations by matching corresponding landmarks and away from landmark locations by matching the image intensities. In contrast to similar unidirectional algorithms, these new consistent algorithms jointly estimate the forward and reverse transformation between two images while minimizing the inverse consistency error-the error between the forward (reverse) transformation and the inverse of the the reverse (forward) transformation. This reduces the ambiguous correspondence between the forward and reverse transformations associated with large inverse consistency errors. In both algorithms a thin-plate spline (TPS) model is used to regularize the estimated transformations. Two-dimensional (2-D) examples are presented that show the inverse consistency error produced by the traditional unidirectional landmark TPS algorithm can be relatively large and that this error is minimized using the consistent landmark algorithm. Results using 2-D magnetic resonance imaging data are presented that demonstrate that using landmark and intensity information together produce better correspondence between medical images than using either landmarks or intensity information alone.     

A model-based, semi-global segmentation approach for automatic 3-D point landmark localization in neuroimages

The existing differential approaches for localization of 3-D anatomic point landmarks in 3-D images are sensitive to noise and usually extract numerous spurious landmarks. The parametric model-based approaches are not practically usable for localization of landmarks that can not be modeled by simple parametric forms. Some dedicated methods using anatomic knowledge to identify particular landmarks are not general enough to cope with other landmarks. In this paper, we propose a model-based, semi-global segmentation approach to automatically localize 3-D point landmarks in neuroimages. To localize a landmark, the semi-global segmentation (meaning the segmentation of a part of the studied structure in a certain neighborhood of the landmark) is first achieved by an active surface model, and then the landmark is localized by analyzing the segmented part only. The joint use of global model-to-image registration, semi-global structure registration, active surface-based segmentation, and point-anchored surface registration makes our method robust to noise and shape variation. To evaluate the method, we apply it to the localization of ventricular landmarks including curvature extrema, centerline intersections, and terminal points. Experiments with 48 clinical and 18 simulated magnetic resonance (MR) volumetric images show that the proposed approach is able to localize these landmarks with an average accuracy of 1 mm (i.e., at the level of image resolution). We also illustrate the use of the proposed approach to cortical landmark identification and discuss its potential applications ranging from computer-aided radiology and surgery to atlas registration with scans.      

Measurement of Torsion from Multitemporal Images of the Eye Using Digital Signal Processing Techniques

Two methods of measuring ocular torsion from digital images of the eyes were developed and tested. One method measures torsion from the translation of two landmarks using a rectilinear coordinate system. The second method measures torsion from the translation of two landmarks using a polar coordinate system. The center for the polar sampling is the center of the pupil. After thresholding and filtering the images, landmark translation is measured from the interpolated peak in the normalized cross correlation of the reference landmark with the image.     

A behavior-based mobile robot with a visual landmark-recognition system

In this paper, based on behavior-based artificial intelligence we have built a fully autonomous mobile robot. Several modules are developed for the mobile robot to implement different levels of competences and behaviors, where each module itself generates behaviors. New modules can be easily added to the robot system to improve in the competence without changing any existing modules. A vision-based landmark recognition system for robot navigation is developed as the highest layer in the subsumption architecture. A genetic-algorithm-based search method for pattern recognition of digital images is proposed and implemented to recognize artificial landmarks by searching all the predefined patterns. The vision layer is capable of generating the desired behaviors corresponding to various landmarks. A combination of eight ultrasonic sensors is designed to implement obstacle-avoidance behaviors through a set of fuzzy rules. The effectiveness of this behavior-based mobile robot is demonstrated by experimental studies.     

Efficient facial landmark localization using spatial–contextual AdaBoost algorithm

Facial landmark detectors can be categorized into global and local detectors. Global facial landmark detectors rely on global statistical relations between landmarks, but do not sufficiently utilize local appearance information, whereas local detectors mainly focus on local appearance attributes of landmarks. Although the AdaBoost algorithm has been successfully employed in object localization, it cannot take advantage of geometric facial feature distribution very well. We propose an AdaBoost algorithm called SC-AdaBoost, which efficiently combines the global knowledge of landmark distribution, the regional shape model, and the local landmark attributes based on a coarse-to-fine strategy. The global prior distribution of landmarks is estimated using a face image set with landmark annotations. First, the face region is detected as a rectangular bounding box using a Haar-like feature-based boosting method, and the global distribution of landmarks is used to determine the facial component regions. Facial landmark localization is roughly performed by regional shape modeling. Posteriors of individual weak classifiers are determined by Gabor wavelet analysis at landmark candidate positions constrained by the regional shape model. SC-AdaBoost is established by empirical risk minimization, which decides the weights for the weak classifiers, and is used for the precise localization. The strength of the proposed approach is shown by extensive experiments using standard face datasets.     

Landmark-based elastic registration using approximating thin-platesplines

We consider elastic image registration based on a set of corresponding anatomical point landmarks and approximating thin-plate splines. This approach is an extension of the original interpolating thin-plate spline approach and allows to take into account landmark localization errors. The extension is important for clinical applications since landmark extraction is always prone to error. Our approach is based on a minimizing functional and can cope with isotropic as well as anisotropic landmark errors. In particular, in the latter case it is possible to include different types of landmarks, e.g., unique point landmarks as well as arbitrary edge points. Also, the scheme is general with respect to the image dimension and the order of smoothness of the underlying functional. Optimal affine transformations as well as interpolating thin-plate splines are special cases of this scheme. To localize landmarks we use a semi-automatic approach which is based on three-dimensional (3-D) differential operators. Experimental results are presented for two-dimensional as well as 3-D tomographic images of the human brain.     

基于主成分分析与BP神经网络的识别方法研究

利用BP神经网络对红外目标进行识别之前,若不对原始样本数据进行预处理与特征提取,一方面使识别结果准确性降低,另一方面使BP神经网络的结构复杂化,采用主成分分析法可解决这些问题。主成分分析法能较好地提取表征样本的少数几个主分量,由该方法的特点可知,这几个主分量彼此不相关,非常符合特征优化的要求。研究结果表明,用该方法处理后的结果数据输入BP神经网络．提高了识别正确率,减少了训练时间,同时也简化了网络结构。将两种常见的模式识别方法结合用于红外目标识别：先由主成分分析法对原始样本数据进行精简处理,然后再由BP神经网络法进行分类识别,与传统的单一识别方法相比,准确度得到提高,计算量大为减少。     

基于BP神经网络的地震动信号识别

通过数据采集得到三种不同类型车辆的地震动信号,采用小波消噪和特征提取,得到样本数据对神经网络进行训练,训练完成的神经网络就能实现车辆类型的识别。试验结果表明,BP神经网络对车辆目标具有较高的识别率,证明对地震动信号的特征提取方法是正确的,人工神经网络是有效的目标识别方法。     

基于神经网络和圆谐展开对战斗机俯视图位移、旋转和缩放的识别

神经网络进行畸变不变性模式识别具有普适性、适应性、最优并行性及其在硬件上实现的优点,它可以有效地弥补光学相关模式识别在存在性上的局限性。两者的有效结合对模式识别的发展将起到很大的作用。神经网络和圆谐展开相结合的方式构造复合滤波器可以有效地实现对同一位移、平面旋转和缩放了的图像的畸变不变识别,并给出了该方法用于战斗机俯视图识别的计算机模拟结果。