Range Flow Estimation

We discuss the computation of the instantaneous 3D displacement vector fields of deformable surfaces from sequences of range data. We give a novel version of the basic motion constraint equation that can be evaluated directly on the sensor grid. The various forms of the aperture problem encountered are investigated and the derived constraint solutions are solved in a total least squares (TLS) framework. We propose a regularization scheme to compute dense full flow fields from the sparse TLS solutions. The performance of the algorithm is analyzed quantitatively for both synthetic and real data. Finally we apply the method to compute the 3D motion field of living plant leaves.     

Background estimation under rapid gain change in thermal imagery

We consider detection of moving ground vehicles in airborne sequences recorded by a thermal sensor with automatic gain control, using an approach that integrates dense optic flow over time to maintain a model of background appearance and a foreground occlusion layer mask. However, the automatic gain control of the thermal sensor introduces rapid changes in intensity that makes this difficult. In this paper we show that an intensity-clipped affine model of sensor gain is sufficient to describe the behavior of our thermal sensor. We develop a method for gain estimation and compensation that uses sparse flow of corner features to compute the affine background scene motion that brings pairs of frames into alignment prior to estimating change in pixel brightness. Dense optic flow and background appearance modeling is then performed on these motion-compensated and brightness-compensated frames. Experimental results demonstrate that the resulting algorithm can segment ground vehicles from thermal airborne video while building a mosaic of the background layer, despite the presence of rapid gain changes.     

Hierarchical bayesian models for regularisation in sequential learning

We show that a hierarchical Bayesian modeling approach allows us to perform regularization in sequential learning. We identify three inference levels within this hierarchy: model selection, parameter estimation, and noise estimation. In environments where data arrive sequentially, techniques such as cross validation to achieve regularization or model selection are not possible. The Bayesian approach, with extended Kalman filtering at the parameter estimation level, allows for regularization within a minimum variance framework. A multilayer perceptron is used to generate the extended Kalman filter nonlinear measurements mapping. We describe several algorithms at the noise estimation level that allow us to implement on-line regularization. We also show the theoretical links between adaptive noise estimation in extended Kalman filtering, multiple adaptive learning rates, and multiple smoothing regularization coefficients.     

Kullback–Leibler Divergence Based Composite Prior Modeling for Bayesian Super-Resolution

This paper proposes to adaptively combine the known total variation model and more recent Frobenius norm regularization for multi-frame image super-resolution (SR). In contrast to existing literature, in this paper both the composite prior modeling and posterior variational optimization are achieved in the Bayesian framework by utilizing the Kullback–Leibler divergence, and hyper-parameters related to the composite prior and noise statistics are all determined automatically, resulting in a spatially adaptive SR reconstruction method. Experimental results demonstrate that the new approach can generate a super-resolved image with higher signal-to-noise ratio and better visual perception, not only image details better preserved but also staircase effects better suppressed.     

Sparse on-line gaussian processes

We develop an approach for sparse representations of gaussian process (GP) models (which are Bayesian types of kernel machines) in order to overcome their limitations for large data sets. The method is based on a combination of a Bayesian on-line algorithm, together with a sequential construction of a relevant subsample of the data that fully specifies the prediction of the GP model. By using an appealing parameterization and projection techniques in a reproducing kernel Hilbert space, recursions for the effective parameters and a sparse gaussian approximation of the posterior process are obtained. This allows for both a propagation of predictions and Bayesian error measures. The significance and robustness of our approach are demonstrated on a variety of experiments.     

Weighted pseudometric discriminatory power improvement using a Bayesian logistic regression model based on a variational method

In this paper, we investigate the effectiveness of a Bayesian logistic regression model to compute the weights of a pseudo-metric, in order to improve its discriminatory capacity and thereby increase image retrieval accuracy. In the proposed Bayesian model, the prior knowledge of the observations is incorporated and the posterior distribution is approximated by a tractable Gaussian form using variational transformation and Jensen's inequality, which allow a fast and straightforward computation of the weights. The pseudo-metric makes use of the compressed and quantized versions of wavelet decomposed feature vectors, and in our previous work, the weights were adjusted by classical logistic regression model. A comparative evaluation of the Bayesian and classical logistic regression models is performed for content-based image retrieval as well as for other classification tasks, in a decontextualized evaluation framework. In this same framework, we compare the Bayesian logistic regression model to some relevant state-of-the-art classification algorithms. Experimental results show that the Bayesian logistic regression model outperforms these linear classification algorithms, and is a significantly better tool than the classical logistic regression model to compute the pseudo-metric weights and improve retrieval and classification performance. Finally, we perform a comparison with results obtained by other retrieval methods.     

Steerable pyramid-based face hallucination

In this paper we propose a robust learning-based face hallucination algorithm, which predicts a high-resolution face image from an input low-resolution image. It can be utilized for many computer vision tasks, such as face recognition and face tracking. With the help of a database of other high-resolution face images, we use a steerable pyramid to extract multi-orientation and multi-scale information of local low-level facial features both from the input low-resolution face image and other high-resolution ones, and use a pyramid-like parent structure and local best match approach to estimate the best prior; then, this prior is incorporated into a Bayesian maximum a posterior (MAP) framework, and finally the high-resolution version is optimized by a steepest decent algorithm. The experimental results show that we can enhance a 24×32 face image into a 96×128 one while the visual effect is relatively good.     

Bayesian sparse solutions to linear inverse problems with non-stationary noise with Student-t priors

Bayesian approach has become a commonly used method for inverse problems arising in signal and image processing. One of the main advantages of the Bayesian approach is the possibility to propose unsupervised methods where the likelihood and prior model parameters can be estimated jointly with the main unknowns. In this paper, we propose to consider linear inverse problems in which the noise may be non-stationary and where we are looking for a sparse solution. To consider both of these requirements, we propose to use Student-t prior model both for the noise of the forward model and the unknown signal or image. The main interest of the Student-t prior model is its Infinite Gaussian Scale Mixture (IGSM) property. Using the resulted hierarchical prior models we obtain a joint posterior probability distribution of the unknowns of interest (input signal or image) and their associated hidden variables. To be able to propose practical methods, we use either a Joint Maximum A Posteriori (JMAP) estimator or an appropriate Variational Bayesian Approximation (VBA) technique to compute the Posterior Mean (PM) values. The proposed method is applied in many inverse problems such as deconvolution, image restoration and computed tomography. In this paper, we show only some results in signal deconvolution and in periodic components estimation of some biological signals related to circadian clock dynamics for cancer studies.     

Improving sub-pixel correspondence through upsampling

Many fundamental computer vision problems, including optical flow estimation and stereo matching, involve the key step of computing dense color matching among pixels. In this paper, we show that by merely upsampling, we can improve sub-pixel correspondence estimation. In addition, we identify the regularization bias problem and explore its relationship to image resolution. We propose a general upsampling framework to compute sub-pixel color matching for different computer vision problems. Various experiments were performed on motion estimation and stereo matching data. We are able to reduce errors by up to 30%, which would otherwise be very difficult to achieve through other conventional optimization methods.     

Pre-Attentive and Attentive Detection of Humans in Wide-Field Scenes

We address the problem of localizing and obtaining high-resolution footage of the people present in a scene. We propose a biologically-inspired solution combining pre-attentive, low-resolution sensing for detection with shiftable, high-resolution, attentive sensing for confirmation and further analysis. The detection problem is made difficult by the unconstrained nature of realistic environments and human behaviour, and the low resolution of pre-attentive sensing. Analysis of human peripheral vision suggests a solution based on integration of relatively simple but complementary cues. We develop a Bayesian approach involving layered probabilistic modeling and spatial integration using a flexible norm that maximizes the statistical power of both dense and sparse cues. We compare the statistical power of several cues and demonstrate the advantage of cue integration. We evaluate the Bayesian cue integration method for human detection on a labelled surveillance database and find that it outperforms several competing methods based on conjunctive combinations of classifiers (e.g., Adaboost). We have developed a real-time version of our pre-attentive human activity sensor that generates saccadic targets for an attentive foveated vision system. Output from high-resolution attentive detection algorithms and gaze state parameters are fed back as statistical priors and combined with pre-attentive cues to determine saccadic behaviour. The result is a closed-loop system that fixates faces over a 130 deg field of view, allowing high-resolution capture of facial video over a large dynamic scene.     

A variational Bayesian strategy for solving the DOA estimation problem in sparse array

This paper reformulates the problem of direction-of-arrival (DOA) estimation for sparse array from a variational Bayesian perspective. In this context, we propose a hierarchical prior for the signal coefficients that amounts marginally to a sparsity-inducing penalty in maximum a posterior (MAP) estimation. Further, the specific hierarchy gives rise to a variational inference technique which operates in latent variable space iteratively. Our hierarchical formulation of the prior allow users to model the sparsity of the unknown signal with a high degree, and the corresponding Bayesian algorithm leads to sparse estimators reflecting posterior information beyond the mode. We provide experimental results with synthetic signals and compare with state-of-the-art DOA estimation algorithm, in order to demonstrate the superior performance of the proposed approach.     

多源空—谱遥感图像融合方法进展与挑战

多源空—谱遥感图像融合方法作为两路不完全观测多通道数据的计算重构反问题,其挑战在于补充信息不足、模糊和噪声等引起的病态性,现有方法在互补特征保持的分辨率增强方面仍有很大的改进空间。为了推动遥感图像融合技术的发展,本文系统概述目前融合建模的代表性方法,包括成分替代、多分辨率分析、变量回归、贝叶斯、变分和模型与数据混合驱动等方法体系及其存在问题。从贝叶斯融合建模的角度,分析了互补特征保真和图像先验在优化融合中的关键作用和建模机理,并综述了目前若干图像先验建模的新趋势,包括：分数阶正则化、非局部正则化、结构化稀疏表示、矩阵低秩至张量低秩表示、解析先验与深度先验的复合等。本文对各领域面临的主要挑战和可能的研究方向进行了概述和讨论,指出解析模型和数据混合驱动将是图像融合的重要发展方向,并需要结合成像退化机理、数据紧致表示和高效计算等问题,突破现有模型优化融合的技术瓶颈,进一步发展更优良的光谱信息保真和更低算法复杂度的融合方法。同时,为了解决大数据问题,有必要在Hadoop和SPARK等大数据平台上进行高性能计算,以更有利于多源数据融合算法的加速实现。     

A probabilistic framework for real-time performance assessment of inferential sensors

A definition for the reliability of inferential sensor predictions is provided. A data-driven Bayesian framework for real-time performance assessment of inferential sensors is proposed. The main focus is on characterizing the effect of operating space on the reliability of inferential sensor predictions. A holistic, quantitative measure of the reliability of the inferential sensor predictions is introduced. A methodology is provided to define objective prior probabilities over plausible classes of reliability based on the total misclassification cost. The real-time performance assessment of multi-model inferential sensors is also discussed. The application of the method does not depend on the identification techniques employed for model development. Furthermore, on-line implementation of the method is computationally efficient. The effectiveness of the method is demonstrated through simulation and industrial case studies.     

Blind image deconvolution using machine learning for three-dimensional microscopy

In this work, we propose a novel method for the regularization of blind deconvolution algorithms. The proposed method employs example-based machine learning techniques for modeling the space of point spread functions. During an iterative blind deconvolution process, a prior term attracts the point spread function estimates to the learned point spread function space. We demonstrate the usage of this regularizer within a Bayesian blind deconvolution framework and also integrate into the latter a method for noise reduction, thus creating a complete blind deconvolution method. The application of the proposed algorithm is demonstrated on synthetic and real-world three-dimensional images acquired by a wide-field fluorescence microscope, where the need for blind deconvolution algorithms is indispensable, yielding excellent results.     

基于支持向量机的在线建模方法及应用

针对常规v支持向量回归用于在线建模时存在的问题，提出了一种支持向量回归在线建模方法．利用贝叶斯证据框架优化模型参数，通过判断新增观测值是否满足原来的KKT条件，并对历史数据给予不同程度的加权以充分利用最新的数据信息，使模型随着时间的推移在线更新．工业PTA氧化过程中4-CBA含量预测的实例表明，该方法能很好地跟踪4-CBA含量的变化趋势，是一种有效的在线建模方法．     

正则化参数求解方法研究

针对BP神经网络算法训练过程中出现的过拟合问题,提出了利用一阶原点矩,二阶原点矩,方差和极大似然估计概念的推广来计算L2正则化中正则化参数λ值的方法。该方法通过对算法数据集[X,Y]中的X矩阵进行运算得到的四个λ值,BP神经网络算法训练时通常采用的是贝叶斯正则化方法,贝叶斯正则化方法存在着对先验分布和数据分布依赖等问题,而利用上述概念的推广计算的参数代入L2正则化的方法简便没有应用条件限制;在BP神经网络手写数字识别的实验中,将该方法与贝叶斯正则化方法应用到实验中后的算法识别结果进行比较,正确率提高了1.14-1.50个百分点;因而计算得到的λ值应用到L2正则化方法与贝叶斯正则化方法相比更能使得BP神经网络算法的泛化能力强,证明了该算法的有效性。     

Doherty功放的贝叶斯正则化神经网络逆向建模研究

针对直接逆向建模方法精度低、稳定性差等缺点,提出了一种采用规则化函数为L1/2范数的贝叶斯正则化神经网络逆向建模方法,L1/2正则化使得网络结构具有稀疏性,能够缩小网络的规模、加快网络的训练速度,用贝叶斯正则化方法可以使网络的输出更加平滑,提高网络的稳定性和泛化能力。将此方法应用到Doherty功率放大器的设计中,在已知Doherty主功放效率、输出匹配端的S11和S21的情况下,分别仿真得出相对应的输出功率和f,可以简化设计过程。实验结果表明,此逆向模型求得的输出功率、与S11相对的f、与S21相对的f比直接逆向建模方法的均方误差分别减少了8.83%、9.30%和9.00%,运行时间分别减少了99.34%、99.40%和99.23%,解决了设计中的多解问题,可用于设计射频微波器件。     

The Bayesian evidence scheme for regularizing probability-density estimating neural networks

Training probability-density estimating neural networks with the expectation-maximization (EM) algorithm aims to maximize the likelihood of the training set and therefore leads to overfitting for sparse data. In this article, a regularization method for mixture models with generalized linear kernel centers is proposed, which adopts the Bayesian evidence approach and optimizes the hyperparameters of the prior by type II maximum likelihood. This includes a marginalization over the parameters, which is done by Laplace approximation and requires the derivation of the Hessian of the log-likelihood function. The incorporation of this approach into the standard training scheme leads to a modified form of the EM algorithm, which includes a regularization term and adapts the hyperparameters on-line after each EM cycle. The article presents applications of this scheme to classification problems, the prediction of stochastic time series, and latent space models.