Search

In this paper, we mainly discuss a discrete estimation of the average differential entropy for a continuous time-stationary ergodic space-time random field. By estimating the probability value of a time-stationary random field in a small range, we give an entropy estimation and obtain the average entropy estimation formula in a certain bounded space region. It can be proven that the estimation of the average differential entropy converges to the theoretical value with a probability of 1. In addition, we also conducted numerical experiments for different parameters to verify the convergence result obtained in the theoretical proofs.

Multispectral pedestrian detection has achieved great success in past years, which can be used in autonomous driving for intelligent transportation system. Most existing multispectral pedestrian detection approaches are developed on the assumption that training and test data belong to an identical distribution, which does not guarantee a good generalization to cross-domain (unseen) data. In this paper, we aim to develop a generalizable multispectral pedestrian detector, which achieves a favorable performance on both intra-dataset evaluation and cross-dataset evaluation. To achieve this goal, we conduct intra-dataset and cross-dataset experiments using single-modal and multi-modal data. By deep analysis, we find that, compared to visible or multi-modal data, thermal data not only has a best cross-dataset generalization, but also generates high-quality proposals on intra-dataset and cross-dataset evaluations. Inspired by this, we propose a novel thermal-first and fusion-second network (called TFNet) for multispectral pedestrian detection. In our TFNet, we first employ a thermal-based proposal network to extract candidate pedestrian proposals. After that, we design a transformer fusion based head network to further classify/regress these proposals. Experiments are performed on three public datasets. The comprehensive results demonstrate the effectiveness of our proposed TFNet on both intra-dataset and cross-dataset evaluations. We hope that our simple design can promote the future study on generalizable multispectral pedestrian detection.

In this paper, we mainly study the discrete approximation about average differential entropy of continuous bounded space‐time random field. The estimation of differential entropy on random variable is a classic problem, and there are many related studies. Space‐time random field is a theoretical extension of adding random variables to space‐time parameters, but studies on discrete estimation of entropy on space‐time random field are relatively few. The differential entropy forms of continuous bounded space‐time random field and discrete estimations are discussed, and three estimation forms of differential entropy in the case of random variables are generated in this paper. Furthermore, it is concluded that under the condition that the entropy estimation formula after space‐time segmentation converges with probability 1, the average entropy in the bounded space‐time region can also converge with probability 1, and three generalized entropies are verified respectively. In addition, we also carried out numerical experiments on the convergence of average entropy estimation based on parameters, and the numerical results are consistent with the theoretical results, which indicting further study of the average entropy estimation problem of space‐time random fields is significant in the future.

With complementary multi-modal information (i.e. visible and thermal), multispectral pedestrian detection is essential for around-the-clock applications, such as autonomous driving, video surveillance, and vicinagearth security. Despite its broad applications, the requirements for expensive thermal device and multi-sensor alignment limit the utilization in real-world applications. In this paper, we propose a pseudo-multispectral pedestrian detection (called PseudoMPD) method, which employs the gray image converted from the RGB image to replace the real thermal image, and learns the pseudo-thermal feature through deep thermal feature guidance (TFG). To achieve this goal, we first introduce an image base-detail decomposition (IBD) module to decompose image information into base and detail parts. Afterwards, we design a base-detail hierarchical feature fusion (BHFF) module to deeply exploit the information between these two parts, and employ a TFG module to guide pseudo-thermal base and detail feature learning. As a result, our proposed method does not require the real thermal image during inference. The comprehensive experiments are performed on two public multispectral pedestrian datasets. The experimental results demonstrate the effectiveness of our proposed method.

The problem of approximation of homogeneous random field from asymmetric local average sampling is considered in this paper. As a general sampling result, a sufficient condition is obtained to ensure the homogeneous random field be approximated from local averages with probability 1, which extended the result for weak sense stochastic process from local averages to homogeneous random field.

This paper presents an effective method for marine sewage detection from a remote-sensing image. It is inspired by the Grab-Cut mechanism that iterative estimation and incomplete labeling allow a considerably reduced degree of user interaction for a given quality of result. By establishing the relationship between the color feature and the object seeds, we first model object and background with Gaussian mixture model, respectively, followed by iteratively updating the parameter of model to decline the energy function. To improve the computation efficiency, we propose to extend the region of interest as background. The proposed method accounts for not only the effect of color feature, but also the geographical information. The experimental results demonstrate that the proposed method is more reliable in marine sewage detection compared to other state-of-the-art methods.

A promising research that has drawn considerable attentions is exploiting the inherent structures in the sparse signal. In this work, we apply the property to the multiple measurement vector (MMV) problem, in which a group of collected sparse signals that share an identical sparsity support are recovered from undersampled measurements. The main objective of this paper is to introduce a Bayesian model with taking both spatial and temporal dependencies into account and show how this model can be used for MMV with spatial structured sparsity patterns. Due to the property of the beta process that the sparse representation can be decomposed to values and sparsity indicators, the proposed algorithm ingeniously captures the temporal correlation structure by the learning of amplitudes and the spatial correlation structure by the estimation of clustered sparsity patterns. Detailed numerical experiments including synthetic and real data demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Product variation reduction is critical to improve process efficiency and product quality, especially for multistage machining process (MMP). However, due to the variation accumulation and propagation, it becomes quite difficult to predict and reduce product variation for MMP. While the method of statistical process control can be used to control product quality, it is used mainly to monitor the process change rather than to analyze the cause of product variation. In this paper, based on a differential description of the contact kinematics of locators and part surfaces, and the geometric constraints equation defined by the locating scheme, an improved analytical variation propagation model for MMP is presented. In which the influence of both locator position and machining error on part quality is considered while, in traditional model, it usually focuses on datum error and fixture error. Coordinate transformation theory is used to reflect the generation and transmission laws of error in the establishment of the model. The concept of deviation matrix is heavily applied to establish an explicit mapping between the geometric deviation of part and the process error sources. In each machining stage, the part deviation is formulized as three separated components corresponding to three different kinds of error sources, which can be further applied to fault identification and design optimization for complicated machining process. An example part for MMP is given out to validate the effectiveness of the methodology. The experiment results show that the model prediction and the actual measurement match well. This paper provides a method to predict part deviation under the influence of fixture error, datum error and machining error, and it enriches the way of quality prediction for MMP.

In the paper, the stability and stabilization are considered for neutral-type neural network with Lévy noise and mixed time-varying delays. By employing a class of appropriate Lyapunov functionals, the analysis process of mean square exponential stability for neutral-type neural network with Lévy noise and mixed time-varying delays can be effectively carried out. Based on the linear matrix inequalities technique, the sufficient conditions are presented to ensure the mean square exponential stability for the system. In view of the unstable situation of the system, a feedback controller is designed to stabilize the system, and the corresponding LMIs conditions are given. At last, two numerical examples show the validity of the obtained results. • A class of Lyapunov functionals is employed to analysis the mean square exponential stability neutral-type neural network. • The sufficient conditions of the mean square exponential stability for the system are presented. • A feedback controller is designed to stabilize the system, and the corresponding LMIs conditions are given. [ABSTRACT FROM AUTHOR]

For linear combinations of Bernstein operators Bn, r(f, x), we give an equivalent theorem with ω2rφλ(f, t), where ω2rφλ(f, t) is the Ditzian–Totik modulus of smoothness (1−1/rλ1). It is the generalization of corresponding results by Z. Ditzian and V. Totik (1987, “Moduli of Smoothness”, Springer-Verlag, Berlin/New York).

We present an effective method for defocus map estimation from a single natural image. It is inspired by the observation that defocusing can significantly affect the spectrum amplitude at the object edge locations in an image. By establishing the relationship between the amount of spatially varying defocus blur and spectrum contrast at edge locations, we first estimate the blur amount at these edge locations, then a full defocus map can be obtained by propagating the blur amount at edge locations over the entire image with a nonhomogeneous optimization procedure. The proposed method takes into consideration not only the affect of light refraction but also the blur texture of an image. Experimental results demonstrate that our proposed method is more reliable in defocus map estimation compared to various state-of-the-art methods.

The current researches mainly adopt “Guide to the expression of uncertainty in measurement (GUM)” to calculate the profile error. However, GUM can only be applied in the linear models. The standard GUM is not appropriate to calculate the uncertainty of profile error because the mathematical model of profile error is strongly non-linear. An improved second-order GUM method (GUMM) is proposed to calculate the uncertainty. At the same time, the uncertainties in different coordinate axes directions are calculated as the measuring points uncertainties. In addition, the correlations between variables could not be ignored while calculating the uncertainty. A k-factor conversion method is proposed to calculate the converge factor due to the unknown and asymmetrical distribution of the output quantity. Subsequently, the adaptive Monte Carlo method (AMCM) is used to evaluate whether the second-order GUMM is better. Two practical examples are listed and the conclusion is drawn by comparing and discussing the second-order GUMM and AMCM. The results show that the difference between the improved second-order GUM and the AMCM is smaller than the difference between the standard GUM and the AMCM. The improved second-order GUMM is more precise in consideration of the nonlinear mathematical model of profile error.

The robust principal component analysis (RPCA) refers to the decomposition of an observed matrix into the low-rank component and the sparse component. Conventional methods model the sparse component as pixel-wisely sparse (e.g., ℓ 1 -norm for the sparsity). However, in many practical scenarios, elements in the sparse part are not truly independently sparse but distributed with contiguous structures. This is the reason why representative RPCA techniques fail to work well in realistic complex situations. To solve this problem, a Bayesian framework for RPCA with structured sparse component is proposed, where both amplitude and support correlation structure are considered simultaneously in recovering the sparse component. The model learning is based on the variational Bayesian inference, which can potentially be applied to estimate the posteriors of all latent variables. Experimental results demonstrate the proposed methodology is validated on synthetic and real data. [ABSTRACT FROM AUTHOR]