A statistical signal processing approach to multisensor image fusion is presented. This approach is based on an image formation model in which the sensor images are described as the true scene corrupted by additive no...
详细信息
A statistical signal processing approach to multisensor image fusion is presented. This approach is based on an image formation model in which the sensor images are described as the true scene corrupted by additive non-Gaussian distortion. A hidden Markov model (HMM) is fitted to the wavelet transforms of the sensor images to describe the correlations between the coefficients across wavelet decomposition scales. A set of iterative equations was developed using the expectation-maximization (EM) algorithm to estimate the model parameters and produce the fused images. We demonstrated the efficiency of this approach by applying this method to visual and radiometric images in concealed weapon detection (CWD) cases and night vision applications.
作者：
A.A. FaragA. El-BazG. Gimel'farbCVIP
University of Louisville Louisville KY USA CVIE
University of Louisville Louisville KY USA CITR
University of Auckland Auckland New Zealand
In this paper we present a new approach for density estimation. The proposed approach is based on modifying expectation-maximization (EM) algorithm to approximate an empirical probability density function of scalar da...
详细信息
In this paper we present a new approach for density estimation. The proposed approach is based on modifying expectation-maximization (EM) algorithm to approximate an empirical probability density function of scalar data with a linear combination of Gaussians (LCG). We also propose a novel EM-based sequential technique to get a close initial LCG approximation the modified EM algorithm should start with. Due to both positive and negative components, the LCG approximates inter-class transitions more accurately than a conventional mixture of only positive Gaussians. Experiments on simulated images demonstrate the accuracy of our approach.
Conventional MLEM and OSEM algorithms used in SPECT Tc-99m sestamibi scintimammography produce hot spot artifacts (HSA). We investigated a suitable modification of MLEM and OSEM algorithms needed to reduce HSA. Patien...
详细信息
Conventional MLEM and OSEM algorithms used in SPECT Tc-99m sestamibi scintimammography produce hot spot artifacts (HSA). We investigated a suitable modification of MLEM and OSEM algorithms needed to reduce HSA. Patients with suspicious breast lesions were administered 10 mCi of Tc-99m sestamibi and SPECT scans with patients in prone position with uncompressed breasts were acquired. In addition, to simulate breast lesions, some patients were imaged with a number of breast skin markers each containing 1 /spl mu/Ci of Tc-99m. We modified MLEM and OSEM algorithms by removing from the backprojection step the rays that traverse the periphery of the support region on the way to a detector bin when their path length trough this region is shorter than some preset critical length. Such very short paths result in a very low projection counts contributed to the detector bin and this in turn gives rise to a overestimation of the activity in the peripheral voxels in the backprojection step, thus creating HSA. We analyzed the breast-lesion contrast and suppression of HSA in the images reconstructed using conventional and modified MLEM and OSEM algorithms vs. critical path length (CPL). For CPL/spl ges/0.01 pixel size, we observed improved breast-lesion contrast and lower noise in the images reconstructed, and a very significant reduction of HSA in the maximum intensity projection (MIP) images.
In this paper, the problem of blind separation of an instantaneous mixture of independent sources by exploiting their nonstationarity and/or nonGaussianity is addressed. We show that nonstationarity and nonGaussianity...
详细信息
In this paper, the problem of blind separation of an instantaneous mixture of independent sources by exploiting their nonstationarity and/or nonGaussianity is addressed. We show that nonstationarity and nonGaussianity can be exploited by modeling the distribution of the sources using Gaussian mixture model. The maximum likelihood estimator is utilized in order to derive two novel source separation techniques. Both methods are based on estimation of the sensor distribution parameters via the expectation-maximization algorithm for GMM parameter estimation. In the first method, the separation matrix is estimated by applying simultaneous joint diagonalization of the estimated GMM covariance matrices. In the second proposed method the separation matrix is estimated by applying singular value decomposition of a weighted sum of the estimated GMM covariance matrices. The performance of the two proposed methods is evaluated and compared to existing blind source separation techniques. The results show the superior performance of the proposed methods in terms of interference-to-signal ratio.
We study sensor-actuator networks, extensions of sensor networks that consist of nodes that both monitor and interact with the environment. In particular, we focus on the evaluation of average causal effect within suc...
详细信息
We study sensor-actuator networks, extensions of sensor networks that consist of nodes that both monitor and interact with the environment. In particular, we focus on the evaluation of average causal effect within such networks. We describe a distributed algorithm that enables individual actuator nodes to determine the probable consequences of local action on the global environment and hence decide if such action is conducive to achieving the aims of the network. Our approach represents the relationship between actuation and sensor measurements using a causal graph, and applies a distributed expectation-maximization algorithm to estimate the average causal effect of actuation. We evaluate the effectiveness of our approach through simulations that examine the benefits of including side-information regarding possible event outcomes.
This paper presents a turbo multiuser detector for turbo-coded DS-CDMA systems, based on the utilization of a PIC and a bank of turbo decoders in which the PIC performs interference cancellation after each constituent...
详细信息
This paper presents a turbo multiuser detector for turbo-coded DS-CDMA systems, based on the utilization of a PIC and a bank of turbo decoders in which the PIC performs interference cancellation after each constituent decoder of the turbo decoding scheme. Moreover, the soft output of the turbo decoders are used iteratively to improve the updating step of the channel parameter estimation which is formally equivalent to one step of the expectation-maximization algorithm. By means of computer simulations, we have shown that the proposed receiver achieves performance comparable with systems which suppose perfect channel parameters knowledge for medium to high system loads in AWGN channel. The proposed receiver is also tested in a satellite channel.
We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person. We start by extracting a set of continuous, phase aligned spatio-temp...
详细信息
We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person. We start by extracting a set of continuous, phase aligned spatio-temporal curves from trajectories of random points tracked over several cycles of locomotion in a monocular video sequence. We analyze a PCA representation of a set of cyclic curves, pointing out properties of the representation which can be used for spatio-temporal alignment in tracking and recognition tasks. We model the curve distribution density by a mixture of Gaussians using expectation-maximization algorithm. For recognition, we use maximum a posteriori estimate combined with linear data adaptation. We tested the algorithms on CMU MoBo database with favourable results for the recognition of people "by walking "from monocular video sequences captured from the side view.
Sensor networks have exciting potential applications in agriculture and medicine, where after the application of treatment, it is beneficial not merely to track the response but to assess the causal impact of the trea...
详细信息
Sensor networks have exciting potential applications in agriculture and medicine, where after the application of treatment, it is beneficial not merely to track the response but to assess the causal impact of the treatment reception. We describe a distributed algorithm for the evaluation of the average causal effect of treatment reception upon response. Our procedure applies the expectation-maximization algorithm across a graphical model of the system, using local message-passing techniques. The key collaborative step in the algorithm is simple message aggregation and averaging, which we perform over a tree network topology. Finally, for completeness purposes, we describe a simple framework for the construction and maintenance of the tree topology that provides a robust mechanism for executing the algorithm using spread-spectrum or ultra-wideband communication.
Multivariate extensions of the Poisson distribution are plausible models for multivariate discrete data. The lack of estimation and inferential procedures reduces the applicability of such models. In this paper, an EM...
详细信息
Multivariate extensions of the Poisson distribution are plausible models for multivariate discrete data. The lack of estimation and inferential procedures reduces the applicability of such models. In this paper, an EM algorithm for Maximum Likelihood estimation of the parameters of the Multivariate Poisson distribution is described. The algorithm is based on the multivariate reduction technique that generates the Multivariate Poisson distribution. Illustrative examples are also provided. Extension to other models, generated via multivariate reduction, is discussed.
An enhanced version of the space-alternating generalised expectation maximisation (SAGE) algorithm based on distributed-source modelling is proposed. This new algorithm shows an improved performance compared to that o...
详细信息
An enhanced version of the space-alternating generalised expectation maximisation (SAGE) algorithm based on distributed-source modelling is proposed. This new algorithm shows an improved performance compared to that of the classical SAGE algorithm when applied to a distributed-source environment, especially when the successive interference cancellation (SIC) technique is employed within the SAGE algorithm.
暂无评论