Automatic Detection of Geospatial Objects Using Multiple Hierarchical Segmentations

The object-based analysis of remotely sensed imagery provides valuable spatial and structural information that is complementary to pixel-based spectral information in classification. In this paper, we present novel methods for automatic object detection in high-resolution images by combining spectral information with structural information exploited by using image segmentation. The proposed segmentation algorithm uses morphological operations applied to individual spectral bands using structuring elements in increasing sizes. These operations produce a set of connected components forming a hierarchy of segments for each band. A generic algorithm is designed to select meaningful segments that maximize a measure consisting of spectral homogeneity and neighborhood connectivity. Given the observation that different structures appear more clearly at different scales in different spectral bands, we describe a new algorithm for unsupervised grouping of candidate segments belonging to multiple hierarchical segmentations to find coherent sets of segments that correspond to actual objects. The segments are modeled by using their spectral and textural content, and the grouping problem is solved by using the probabilistic latent semantic analysis algorithm that builds object models by learning the object-conditional probability distributions. The automatic labeling of a segment is done by computing the similarity of its feature distribution to the distribution of the learned object models using the Kullback-Leibler divergence. The performances of the unsupervised segmentation and object detection algorithms are evaluated qualitatively and quantitatively using three different data sets with comparative experiments, and the results show that the proposed methods are able to automatically detect, group, and label segments belonging to the same object classes.     

基于SVM混合核的遥感图像变化检测

针对由实际遥感地物类型难以确定导致的多光谱遥感影像变化检测精度较低的问题,提出一种基于SVM混合核的遥感图像变化检测。首先利用CVA算法构造差异影像,其次利用灰度共生矩阵提取差异影像的纹理特征与差异影像的灰度特征组成特征向量,接着利用差异影像的直方图选择置信度高的训练样本,并利用构造的SVM混合核进行训练得到分类超平面,最后利用SVM混合核函数对差异影像进行二分类得到最后的变化检测结果。实际遥感数据验证结果表明,所构造的SVM混合核函数用于多光谱遥感影像变化检测中是可行、有效的。     

受昆虫视觉启发的多光谱遥感影像小目标检测

现有多光谱遥感影像目标检测算法大多依赖于结构化背景模型和先验信息,背景复杂化和先验信息匮乏将导致高虚警率的检测结果。受昆虫视觉系统中小目标检测神经元的启发,跳出传统研究思路,提出多光谱遥感影像小目标仿生检测模型及相应的目标检测方法。该方法利用神经元非线性滤波特性对突变信号的敏感性,在局部区域内通过背景纹理抑制和目标边缘增强实现目标检测。实验结果表明该方法在高复杂度背景条件下获得较为稳定的低虚警率检测效果。同时该算法可以较好地平衡背景复杂度和空间分辨率之间的矛盾关系,相比现有检测算法还具有原理简单、易于实现等特点。     

Adaptive Fuzzy Morphological Filtering of Impulse Noise in Images

In this paper we first introduce a neural network implementationfor fuzzy morphological operators, and by means of a trainingmethod and differentiable equivalent representations for theoperators we then derive efficient adaptation algorithms to optimizethe structuring elements. Thus we are able to design fuzzy morphologicalfilters for processing multi-level or binary images. The convergencebehavior of basic structuring elements and its significance forother structuring elements of different shape is discussed. Besidesthe filter design, the localized structuring elements obtainedfrom the training method give a structural characterization ofthe image which is useful in many applications. The performanceof the fuzzy morphological filters in removing impulse noisein multi-level and binary images is illustrated and comparedwith existing procedures.     

A study of the generalized morphological filter

A new class of morphological filters is proposed for image enhancement. The filter, known as the generalized morphological filter (GMF), uses multiple structuring elements and combines linear and morphological operations. The GMF can be designed to suppress various types of noise yet preserve geometrical structure in an image. A study of several aspects of the performance of the filter is presented. The study includes geometrical feature preservation, noise suppression, structuring element selection, and the root signal structure. For the sake of comparison, averaging and median filters are also used in the experiments and corresponding figures of merit of the performance of the filter. The empirical study shows that the generalized morphological filter possesses effective noise suppression with reduced geometrical feature blurring.This work was supported by the National Science Foundation, under Grant No. CDR-8803017 to the Engineering Research Center for Intelligent Manufacturing Systems.     

Multisource classification of remotely sensed data: fusion ofLandsat TM and SAR images

Proposes a new method for statistical classification of multisource data. The method is suited for land-use classification based on the fusion of remotely sensed images of the same scene captured at different dates from multiple sources. It incorporates a priori information about the likelihood of changes between the acquisition of the different images to be fused. A framework for the fusion of remotely sensed data based on a Bayesian formulation is presented. First, a simple fusion model is given, and then the basic model is extended to take into account the temporal attribute if the different data sources are acquired at different dates. The performance of the model is evaluated by fusing Landsat TM images and ERS-1-SAR images for land-use classification. The fusion model gives significant improvements in the classification error rates compared to the conventional single-source classifiers     

Scale aware remote sensing image enhancement using rolling guidance

Enhancement of remotely sensed images is a challenging problem, since the enhanced image has to have an improved contrast and edge information while preserving the original radiance values as much as possible. In this paper, a scale aware enhancement method based on rolling guidance is proposed for remotely sensed images. For each scale, a guidance image is defined and the approximation image is provided by an iterative joint filtering of the approximation and guidance images. Then the extracted details are amplified through an adaptive scheme and added to the final level approximation layer to provide the resulting enhanced image. A comparative study between the proposed methods with classical edge preserving filters and traditional methods have been carried out by using several criteria. The proposed methods have an average of 12% improvement for contrast gain (CG) metric and 81% improvement for enhancement measurement (EME) metric compared to the closest comparison method.     

Decomposition of morphological structuring elements with integer linear programming

A method is proposed for decomposing morphological structuring elements based on integer linear programming. A decomposition problem is formulated into a set of linear constraints, and an optimal decomposition is a solution to the constraints, obtained by the cutting-plane simplex algorithm. The method has several advantages. It provides a systematic way of decomposing arbitrarily shaped structuring elements. For convex images, factors can be of any size, not restricted to 3 /spl times/ 3; the candidate set can be freely assigned by the user; and the optimality criteria can be flexible.     

Analysis and implementation of morphological skeleton transforms

This paper presents the analysis and the implementation algorithms of the morphological skeleton transform (MST) of binary images. A general MST algorithm is provided from which different subclasses of MSTs can be derived by choosing different structuring elements. Three subclasses of MSTs are discussed in this paper: the uniform-step-distance MST (USDMST), the periodically-uniform-step-distance MST (PUSDMST) and the pseudo-Euclidean MST (PEMST). A general discrete distance called morphological distance relates distance measures to the definitions of structuring elements. The PEMST is proposed which uses isotropic discrete structuring elements called quasi-circular structuring elements (QCSE). The QCSEs of all integer sizes are composed by a dilation interpolation method so that they can be decomposed into simplest elements in order to reduce computation. The PEMST has better performance in terms of rotation-invariance than any existing MSTs. The algorithm has an approximately linear computational complexity. Finally, the implementation of the three MSTs are discussed.     

A Novel Adaptive Approach to Process Binary Fingerprint Images Using Directional Morphological Operations

An adaptive algorithm for removing false ridges, bridges and filling gaps in binary fingerprint images based on morphological operations is presented. A novel procedure for structuring elements design based on the specific fingerprint characteristic is described. Using the images from FVC2000 database, we have compared our method proposed here with the approach proposed by other ones. The Experimental results have demonstrated the efficiency of our method.     

A Novel Adaptive Approach to Process Binary Fingerprint Images Using Directional Morphological Operations

An adaptive algorithm for removing false ridges, bridges and filling gaps in binary fingerprint images based on morphological operations is presented. A novel procedure for structuring elements design based on the specific fingerprint characteristic is described. Using the images from FVC2000 database, we have compared our method proposed here with the approach proposed by other ones. The Experimental results have demonstrated the efficiency of our method.     

Rotated texture classification by improved iterative morphologicaldecomposition

An improved algorithm based on iterative morphological decomposition (IMD) proposed by Wang et al. (1993) is described. The proposed algorithm requires less computation than the original IMD algorithm. The improved iterative morphological decomposition (IIMD) is compared with granulometric moments, multiresolution rotation-invariant SAR (MRRISAR) models and multichannel Gabor filters. It is found that the IIMD is superior to granulometric moments and MRRISAR in rotated texture classification. The IIMD may also perform better than multichannel Gabor filters by employing many different kinds of structuring elements. In the study, three kinds of pseudo rotation-invariant structuring elements, namely the disc, octagon and square, as well as a line structuring element are tested. Since the line structuring element is rotation-variant in nature, the image is rotated to different orientations of equal angular separation to find a set of primitive features. A Fourier transform is then applied to convert these features to rotation-invariant ones. An accuracy rate as high as 96% is achieved in classifying 30 classes of textured images in the experiment. It is also demonstrated that using both the normalised variance and the mean can give a better classification accuracy rate than using both the variance and the mean when classified by a simplified Bayes or Mahalanobis distance measure     

基于独立成分分析的图像颜色特征提取研究

结合独立成分分析（Independent Components Analysis,ICA）和最大相似度分类器（Maximum Likelihood）的特点,本文提出了一种基于ICA的多频谱遥感图像色彩分类的算法.该算法提取图像的色彩的独立成分,去除了图像的R、G、B之间的相关性,光谱独立成份用来聚集像素,使用Maximum Likelihood对像素进行颜色分类.实验结果表明,该方法识别性能好,准确度高,是对多频谱遥感图像的颜色特征提取的一种有效方法.     

广义多结构元素并行复合形态滤波器

本文基于数学形态学中的广义形态开-闭和闭-开运算,采用多结构元素,构造了一类并行复合形态滤波器。这类滤波器具有平移不变性、递增性、对偶性和幂等性等重要性质,并遵守阈值叠加准则,不仅可以有效地抑制图象中的噪声,而且较好地保持了图象的几何结构特征。计算机模拟结果证实了滤波算法的有效性.     

结合光谱和尺度特征的高分辨率图像边缘检测算法

高分辨率遥感图像具有高度细节化的多尺度表达能力,在有效表达地物边缘信息的同时,目标内部几何细节常以噪声的形式出现.提出将光谱相异性和小波变换相结合的边缘特征检测算法,克服了小波变换导致的边缘变形,并能够有效抑制噪声.根据光谱角原理定义归一化光谱相异性模型,并与二进小波变换结合,同时利用梯度方向余弦值对各个波段的梯度幅值加权,最后根据向量场模型计算多光谱图像的梯度幅值和梯度方向,细化后获取由细到粗的多层次边缘特征.实验结果与小波变换和传统检测算子的检测结果相比,表明该算法利用光谱相异性信息增强边缘响应强度,保证了所有尺度下获取的边缘轮廓不失真,边缘点定位准确;加权处理突出了多波段梯度主方向信息,也有效抑制了高分辨率图像上目标内部精细几何细节形成的噪声.     

Consensual and Hierarchical Classification of Remotely Sensed Multispectral Images

Consensual and hierarchical approaches are developed for the classification of remotely sensed multispectral images. The proposed method consists of preprocessing of input patterns, generating multiple classification results by hierarchical neural networks, and a combining scheme to generate a consensus of multiple classification results. Transformations of input patterns by random matrices and nonlinear filtering are used for preprocessing. By varying the input patterns, the multiple classification results are generated with sufficiently independent errors by using a single type of classifier. This helps to improve classification performance when the multiple classification results are combined. Hierarchical neural networks involve the use of successive classifiers which are tuned to reduce the remaining errors to increase the classification performance. This structure includes detection schemes to decide whether successive classifiers are utilized for each input. Consensual and hierarchical approaches generate more reliable and accurate results based on group decision.     

Classification of hyperspectral data from urban areas based on extended morphological profiles

Classification of hyperspectral data with high spatial resolution from urban areas is investigated. A method based on mathematical morphology for preprocessing of the hyperspectral data is proposed. In this approach, opening and closing morphological transforms are used in order to isolate bright (opening) and dark (closing) structures in images, where bright/dark means brighter/darker than the surrounding features in the images. A morphological profile is constructed based on the repeated use of openings and closings with a structuring element of increasing size, starting with one original image. In order to apply the morphological approach to hyperspectral data, principal components of the hyperspectral imagery are computed. The most significant principal components are used as base images for an extended morphological profile, i.e., a profile based on more than one original image. In experiments, two hyperspectral urban datasets are classified. The proposed method is used as a preprocessing method for a neural network classifier and compared to more conventional classification methods with different types of statistical computations and feature extraction.     

A joint multicontext and multiscale approach to Bayesian imagesegmentation

In this paper, a joint multicontext and multiscale (JMCMS) approach to Bayesian image segmentation is proposed. In addition to the multiscale framework, the JMCMS applies multiple context models to jointly use their distinct advantages, and we use a heuristic multistage, problem-solving technique to estimate sequential maximum a posteriori of the JMCMS. The segmentation results on both synthetic mosaics and remotely sensed images show that the proposed JMCMS improves the classification accuracy, and in particular, boundary localization and detection over the methods using a single context at comparable computational complexity     

多结构元多路加权形态边缘检测算法研究

边缘检测是图像特征提取与模式识别的基础。形态学边缘检测因其算法简单,噪声抑制和边缘保持能力已成为研究热点。但很多算法采用单一结构元素,很难对弱边界进行有效处理。基于此,利用多结构元思想构造多结构元抗噪型数学形态学边缘检测器,很好地抑制了噪声和提取到弱边缘。     

Constrained subpixel target detection for remotely sensed imagery

Target detection in remotely sensed images can be conducted spatially, spectrally or both. The difficulty of detecting targets in remotely sensed images with spatial image analysis arises from the fact that the ground sampling distance is generally larger than the size of targets of interest in which case targets are embedded in a single pixel and cannot be detected spatially. Under this circumstance target detection must be carried out at subpixel level and spectral analysis offers a valuable alternative. In this paper, the problem of subpixel spectral detection of targets in remote sensing images is considered, where two constrained target detection approaches are studied and compared. One is a target abundance-constrained approach, referred to as nonnegatively constrained least squares (NCLS) method. It is a constrained least squares spectral mixture analysis method which implements a nonnegativity constraint on the abundance fractions of targets of interest. Another is a target signature-constrained approach, called constrained energy minimization (CEM) method. It constrains the desired target signature with a specific gain while minimizing effects caused by other unknown signatures. A quantitative study is conducted to analyze the advantages and disadvantages of both methods. Some suggestions are further proposed to mitigate their disadvantages