Multisensor image segmentation using Dempster-Shafer fusion inMarkov fields context

This paper deals with the statistical segmentation of multisensor images. In a Bayesian context, the interest of using hidden Markov random fields, which allows one to take contextual information into account, has been well known for about 20 years. In other situations, the Bayesian framework is insufficient and one must make use of the theory of evidence. The aim of the authors' work is to propose evidential models that can take into account contextual information via Markovian fields. They define a general evidential Markovian model and show that it is usable in practice. Different simulation results presented show the interest of evidential Markovian field model-based segmentation algorithms. Furthermore, an original variant of generalized mixture estimation, making possible the unsupervised evidential fusion in a Markovian context, is described. It is applied to the unsupervised segmentation of real radar and SPOT images showing the relevance of the proposed models and corresponding segmentation methods in real situations     

A MRF model-based segmentation approach to classification formultispectral imagery

An unsupervised segmentation approach to classification of multispectral image is suggested here in Markov random field (MRF) frame work. This work generalizes the work of Sarkar et al. (2000) on gray value images for multispectral images and is extended for landuse classification. The essence of this approach is based on capturing intrinsic characters of tonal and textural regions of any multispectral image. The approach takes an initially oversegmented image and the original. multispectral image as the input and defines a MRF over region adjacency graph (RAG) of the initially segmented regions. Energy function minimization associated with the MRF is carried out by applying a multivariate statistical test. A cluster validation scheme is outlined after obtaining optimal segmentation. Quantitative evaluation of classification accuracy of test data for three illustrations are shown and compared with conventional maximum likelihood procedure. Comparison of the proposed methodology with a recent work of texture segmentation in the literature has also been provided. The findings of the proposed method are found to be encouraging     

Robust data fusion for multisensor detection systems

Minimax robust data fusion schemes for multisensor detection systems with discrete-time observations characterized by statistical uncertainty are developed and analyzed. Block, sequential, and serial fusion rules are considered. The performance measures used, and made robust with respect to the uncertainties, include the error probabilities of the hypothesis testing problem in the block fusion case and the error probabilities and expected numbers of samples or sensors in the sequential and serial fusion cases. For different sensor observation statistics, the minimax robust fusion rules are derived for two asymptotic cases of interest: when the number of sensors is large and when the number of times the fusion center collects the local (sensor) decisions is large. Moreover, for the case of identical sensor observation statistics and a large number of sensors, it is shown that there is no loss in optimality, if local tests using likelihood ratios and equal thresholds are used in the sequential fusion rule. In all situations, the robust decision rules at the sensors and the fusion center are shown to make use of likelihood ratios and thresholds that depend on the least-favorable probability distributions of the uncertainty class describing the statistics of sensor observations     

Use of multiresolution wavelet feature pyramids for automatic registration of multisensor imagery.

The problem of image registration, or the alignment of two or more images representing the same scene or object, has to be addressed in various disciplines that employ digital imaging. In the area of remote sensing, just like in medical imaging or computer vision, it is necessary to design robust, fast, and widely applicable algorithms that would allow automatic registration of images generated by various imaging platforms at the same or different times and that would provide subpixel accuracy. One of the main issues that needs to be addressed when developing a registration algorithm is what type of information should be extracted from the images being registered, to be used in the search for the geometric transformation that best aligns them. The main objective of this paper is to evaluate several wavelet pyramids that may be used both for invariant feature extraction and for representing images at multiple spatial resolutions to accelerate registration. We find that the bandpass wavelets obtained from the steerable pyramid due to Simoncelli performs best in terms of accuracy and consistency, while the low-pass wavelets obtained from the same pyramid give the best results in terms of the radius of convergence. Based on these findings, we propose a modification of a gradient-based registration algorithm that has recently been developed for medical data. We test the modified algorithm on several sets of real and synthetic satellite imagery.     

On the positioning of multisensor imagery for exploitation andtarget recognition

Modern image exploitation tasks have evolved from the early single-image, pixel-based and model-less methods to the current multi-image, multisensor, multiplatform, and model-based approaches. In this context, image positioning, which is the process of establishing the precise geometric relationship of an acquired image to the three-dimensional (3-D) world, has become an enabling technique for state-of-the-art multisensor data exploitation. Precise image positioning provides several benefits. Image registration, traditionally formulated as an image-to-image alignment problem, can now be carried out in accordance with interior and exterior sensor geometries. Images from sensors in arbitrary locations and orientations can be positioned with respect to a focal vertical and geocentric coordinate systems. This paper presents techniques for positioning images derived from various sensors such as electro-optical (E-O), synthetic aperture radar (SAR), and interferometric synthetic aperture radar (IFSAR). Applications to model-supported image exploitation are also discussed     

A fuzzy-logic architecture for autonomous multisensor data fusion

Fuzzy logic techniques have become popular to address various processes for multisensor data fusion. Examples include the following: (1) fuzzy membership functions for data association; (2) evaluation of alternative hypotheses in multiple hypothesis trackers; (3) fuzzy-logic-based pattern recognition (e.g., for feature-based object identification); and (4) fuzzy inference schemes for sensor resource allocation. These approaches have been individually successful but are limited to only a single subprocess within a data fusion system. At The Pennsylvania State University, Applied Research Laboratory, a general-purpose fuzzy-logic architecture has been developed that provides for control of sensing resources, fusion of data for tracking, automatic object recognition, control of system resources and elements, and automated situation assessment. This general architecture has been applied to implement an autonomous vehicle capable of self-direction, obstacle avoidance, and mission completion. The fuzzy logic architecture provides interpretation and fusion of multisensor data (i.e., perception) as well as logic for process control (action). This paper provides an overview of the fuzzy-logic architecture and a discussion of its application to data fusion in the context of the Department of Defense (DoD) Joint Directors of Laboratories (JDL) Data Fusion Process Model. A new, robust, fuzzy calculus is introduced. An application example is provided     

Image classification using spectral and spatial information basedon MRF models

A new criterion for classifying multispectral remote sensing images or textured images by using spectral and spatial information is proposed. The images are modeled with a hierarchical Markov Random Field (MRF) model that consists of the observed intensity process and the hidden class label process. The class labels are estimated according to the maximum a posteriori (MAP) criterion, but some reasonable approximations are used to reduce the computational load. A stepwise classification algorithm is derived and is confirmed by simulation and experimental results.     

Target tracking in infrared imagery using weighted composite reference function-based decision fusion.

In this paper, we propose a novel decision fusion algorithm for target tracking in forward-looking infrared image sequences recorded from an airborne platform. An important part of this study is identifying the failure modes in this type of imagery. Our strategy is to prevent these failure modes from developing into tracking failures. The results furnished by competing ego-motion compensation and tracking algorithms are evaluated based on their similarity to a target model constructed using the weighted composite reference function.     

Novel round-robin tabu search algorithm for prostate cancer classification and diagnosis using multispectral imagery.

Quantitative cell imagery in cancer pathology has progressed greatly in the last 25 years. The application areas are mainly those in which the diagnosis is still critically reliant upon the analysis of biopsy samples, which remains the only conclusive method for making an accurate diagnosis of the disease. Biopsies are usually analyzed by a trained pathologist who, by analyzing the biopsies under a microscope, assesses the normality or malignancy of the samples submitted. Different grades of malignancy correspond to different structural patterns as well as to apparent textures. In the case of prostate cancer, four major groups have to be recognized: stroma, benign prostatic hyperplasia, prostatic intraepithelial neoplasia, and prostatic carcinoma. Recently, multispectral imagery has been used to solve this multiclass problem. Unlike conventional RGB color space, multispectral images allow the acquisition of a large number of spectral bands within the visible spectrum, resulting in a large feature vector size. For such a high dimensionality, pattern recognition techniques suffer from the well-known "curse-of-dimensionality" problem. This paper proposes a novel round-robin tabu search (RR-TS) algorithm to address the curse-of-dimensionality for this multiclass problem. The experiments have been carried out on a number of prostate cancer textured multispectral images, and the results obtained have been assessed and compared with previously reported works. The system achieved 98%-100% classification accuracy when testing on two datasets. It outperformed principal component/linear discriminant classifier (PCA-LDA), tabu search/nearest neighbor classifier (TS-1NN), and bagging/boosting with decision tree (C4.5) classifier.     

基于卫星云图的云分类研究

各种类型云的辐射特性以及分布情况,对大气收支平衡以及天气气候都有重大影响,对云进行正确分类是遥感领域的重要应用和研究热点.文章基于对卫星云图进行自动准确识别和分类研究的前提,通过介绍几种特征提取和选择方法,以及介绍无监督、有监督和神经网络3类云分类研究常用分类方法,对国内外近几十年来所做的卫星云图分类研究进行综述介绍.并简要介绍了云分类结果的评价方法,对分类研究的结果进行定性讨论.     

A novel region feature used in multisensor image fusion

A new region feature which emphasized the salience of target region and its neighbors is proposed. In region segmentation-based multisensor image fusion scheme, the presented feature can be extracted from each segmented region to determine the fusion weight. Experimental results demonstrate that the proposed feature has extensive application scope and it provides much more information for each region. It can not only be used in image fusion but also be used in other image processing applications.     

Texture classification system using colour space fusion

A novel colour texture classification system is presented based on an ensemble of independent classifiers each assigned to a different colour representation model. Gaussian Markov random fields features are used in a study to illustrate this previously unexplored approach and its potential to combine information from different colour spaces to improve accuracy. Experimental results illustrate that colour space information fusion results in significant improvements in accuracy.     

基于LMI方法的参数不确定多传感器系统的集中式融合估计

研究了范数有界不确定描述模型和多胞形不确定描述模型所代表的一类参数不确定多传感器系统的集中融合估计问题。应用H∞理论详细地比较了基于不同模型的两种融合方法时域和频域功能，给出了集中鲁棒融合估计的理论结果。并应用MATLAB的LMI工具箱，分析了仿真计算结果。     

Anomaly detection and classification for hyperspectral imagery

Anomaly detection becomes increasingly important in hyperspectral image analysis, since hyperspectral imagers can now uncover many material substances which were previously unresolved by multispectral sensors. Two types of anomaly detection are of interest and considered in this paper. One was previously developed by Reed and Yu to detect targets whose signatures are distinct from their surroundings. Another was designed to detect targets with low probabilities in an unknown image scene. Interestingly, they both operate the same form as does a matched filter. Moreover, they can be implemented in real-time processing, provided that the sample covariance matrix is replaced by the sample correlation matrix. One disadvantage of an anomaly detector is the lack of ability to discriminate the detected targets from another. In order to resolve this problem, the concept of target discrimination measures is introduced to cluster different types of anomalies into separate target classes. By using these class means as target information, the detected anomalies can be further classified. With inclusion of target discrimination in anomaly detection, anomaly classification can be implemented in a three-stage process, first by anomaly detection to find potential targets, followed by target discrimination to cluster the detected anomalies into separate target classes, and concluded by a classifier to achieve target classification. Experiments show that anomaly classification performs very differently from anomaly detection.     

Optimal dimensionality reduction of sensor data in multisensor estimation fusion

When there exists the limitation of communication bandwidth between sensors and a fusion center, one needs to optimally precompress sensor outputs-sensor observations or estimates before the sensors' transmission in order to obtain a constrained optimal estimation at the fusion center in terms of the linear minimum error variance criterion, or when an allowed performance loss constraint exists, one needs to design the minimum dimension of sensor data. This paper will answer the above questions by using the matrix decomposition, pseudo-inverse, and eigenvalue techniques.     

Change detection in multisensor SAR images using bivariate gamma distributions.

This paper studies a family of distributions constructed from multivariate gamma distributions to model the statistical properties of multisensor synthetic aperture radar (SAR) images. These distributions referred to as multisensor multivariate gamma distributions (MuMGDs) are potentially interesting for detecting changes in SAR images acquired by different sensors having different numbers of looks. The first part of this paper compares different estimators for the parameters of MuMGDs. These estimators are based on the maximum likelihood principle, the method of inference function for margins, and the method of moments. The second part of the paper studies change detection algorithms based on the estimated correlation coefficient of MuMGDs. Simulation results conducted on synthetic and real data illustrate the performance of these change detectors.     

Adaptive parametric estimation and classification of remotelysensed imagery using a pyramid structure

An unsupervised region-based image segmentation algorithm implemented with a pyramid structure has been developed. Rather than depending on traditional local splitting and merging of regions with a similarity test of region statistics, the algorithm identifies the homogeneous and boundary regions at each level of the pyramid; the global parameters of each class are then estimated and updated with the values of the homogeneous regions represented at that level of the pyramid using mixture distribution estimation. The image is then classified through the pyramid structure. Classification results obtained for both simulated and SPOT imagery are presented     

Information fusion Wiener filter for the multisensor multichannel ARMA signals with time-delayed measurements

For the multisensor multichannel autoregressive moving average (ARMA) signals with time-delayed measurements, a measurement transformation approach is presented, which transforms the equivalent state space model with measurement delays into the state space model without measurement delays, and then using the Kalman filtering method, under the linear minimum variance optimal weighted fusion rules, three distributed optimal fusion Wiener filters weighted by matrices, diagonal matrices and scalars are presented, respectively, which can handle the fused filtering, prediction and smoothing problems. They are locally optimal and globally suboptimal. The accuracy of the fuser is higher than that of each local signal estimator. In order to compute the optimal weights, the formulae of computing the cross-covariances among local signal estimation errors are given. A Monte Carlo simulation example for the three-sensor target tracking system with time-delayed measurements shows their effectiveness.     

Target-cluster fusion approach for classifying high resolution IKONOS imagery

To extract GIS features from high spatial resolution imagery is an important task in remote sensing applications. However, traditional pixel-based classification methods, which were developed in the era of 10-100 m ground pixel size imagery, cannot exploit the advantages of new images provided by IKONOS and QuickBird. This is due to the increase of the within-class variability inherent from more detailed and higher spatial resolution data. To successfully extract various land covers from high resolution imagery, a target-clustering fusion (TCF) system is presented in the paper. Compared to the conventional classification methods that typically produce more salt-and-pepper-like results, the proposed TCF system can preserve detailed spatial information on each classified target related to its neighbours. To evaluate the efficacy of TCF, experiments are conducted using real IKONOS images.     

采用扩展MRF的红外目标自适应检测方法

针对天基红外监视系统中不同形状目标的联合检测问题,提出基于扩展马尔可夫随机场的自适应目标检测算法。首先分析了天基红外监视系统中的目标特性,在此基础上以典型目标形状为模板,构建了扩展的马尔可夫随机场邻域系统;其次构建了新的马尔可夫势函数,并利用红外图像中背景与目标之间的马尔可夫势差异,将复杂背景中不同形状目标联合检测问题转换为马尔可夫势差异的判别问题,有效解决了马尔可夫随机场理论框架下混合形状目标检测问题。仿真试验结果表明,所提出的算法能够根据目标形状的变化自适应地检测各类目标,并可在不同图像信杂比条件下进行目标检测处理,具有较强的鲁棒性。