空时自适应混合高斯模型复杂背景运动目标检测

为克服传统基于单像素建模方法存在的缺陷,解决复杂背景下的运动目标检测问题,将视频图像序列的空间信息引入背景建模过程中,研究了邻域更新、二维联合直方图信息熵判别、空时平滑等方法.采用引导滤波方法对视频图像进行预处理,以消除图像噪声,并保留图像中目标的边缘信息,给出了算法处理流程和实现步骤.在不同的评测数据库及现实捕获的视频图像上进行了定性及定量实验,结果表明,本文提出的算法在目标检测准确度和完整性等指标上优于传统的同类型算法,为复杂背景环境下的运动目标检测提供了一种新的解决方法.      

蓖麻油生物沥青调和沥青混合料使用性能研究

为了评价蓖麻油生物沥青调和沥青混合料的使用性能,设计了具有5种蓖麻油生物沥青掺量且级配均为AC-20C的沥青混合料,根据各掺量最佳油石比制作试件并进行混合料使用性能试验.根据试验结果分析了不同掺量调和沥青混合料的高温稳定性、水稳定性、低温抗裂性、路面设计参数等性能指标.分析表明,随着生物沥青掺量的增加,调和沥青混合料的高温稳定性、水稳定性、抗压回弹模量逐渐降低,但在一定掺量范围内满足JTG F40—2004《公路沥青路面施工技术规范》的要求,此外水稳定性在加入消石灰后得到显著改善.随着生物沥青掺量的增加,劈裂抗拉强度降低至一谷值后略有提高,低温抗裂性得到改善.由此可见,将蓖麻油生物沥青调和沥青替代石油沥青用于混合料,在一定掺量范围内是可行的.     

Semiparametric Preference Learning

Unlike traditional supervised learning problems,preference learning learns from data available in the form of pairwise preference relations between instances.Existing preference learning methods are either parametric or nonparametric in nature.We propose in this paper a semiparametric preference learning model,abbreviated as SPPL,with the aim of combining the strengths of the parametric and nonparametric approaches.SPPL uses multiple Gaussian processes which are linearly coupled to determine the preference relations between instances.SPPL is more powerful than previous models while keeping the computational complexity low （linear in the number of distinct instances）.We devise an efficient algorithm for model learning.Empirical studies have been conducted on two real-world data sets showing that SPPL outperforms related preference learning methods.     

模的极小逼近的一个等价条件

设Λ为Artin代数,C,X,Y是有限生成右Λ-模,χ,γ为有限生成右Λ-模范畴的子范畴.证明了C有右极小χ-逼近0→Y→X→C→0当且仅当Ext_Λ~1(C,)|_γ以Hom_Λ(Y,)|_γ为投射盖.类似地给出了当C有左极小γ-逼近时的等价条件.     

Higher-order principal component pursuit via tensor approximation and convex optimization

Recovering the low-rank structure of data matrix from sparse errors arises in the principal component pursuit （PCP）. This paper exploits the higher-order generalization of matrix recovery, named higher-order principal component pursuit （HOPCP）, since it is critical in multi-way data analysis. Unlike the convexification （nuclear norm） for matrix rank function, the tensorial nuclear norm is stil an open problem. While existing preliminary works on the tensor completion field provide a viable way to indicate the low complexity estimate of tensor, therefore, the paper focuses on the low multi-linear rank tensor and adopt its convex relaxation to formulate the convex optimization model of HOPCP. The paper further propose two algorithms for HOPCP based on alternative minimization scheme： the augmented Lagrangian alternating direction method （ALADM） and its truncated higher-order singular value decomposition （ALADM-THOSVD） version. The former can obtain a high accuracy solution while the latter is more efficient to handle the computationally intractable problems. Experimental results on both synthetic data and real magnetic resonance imaging data show the applicability of our algorithms in high-dimensional tensor data processing.     

Semantic image annotation based on GMM and random walk model

Automatic image annotation has been an active topic of research in computer vision and patternrecognition for decades.A two stage automatic image annotation method based on Gaussian mixturemodel (GMM) and random walk model (abbreviated as GMM-RW) is presented.To start with,GMM fitted by the rival penalized expectation maximization (RPEM) algorithm is employed to estimatethe posterior probabilities of each annotation keyword.Subsequently, a random walk processover the constructed label similarity graph is implemented to further mine the potential correlations ofthe candidate annotations so as to capture the refining results, which plays a crucial role in semanticbased image retrieval.The contributions exhibited in this work are multifold.First, GMM is exploitedto capture the initial semantic annotations, especially the RPEM algorithm is utilized to train themodel that can determine the number of components in GMM automatically.Second, a label similaritygraph is constructed by a weighted linear combination of label similarity and visual similarity ofimages associated with the corresponding labels, which is able to avoid the phenomena of polysemyand synonym efficiently during the image annotation process.Third, the random walk is implementedover the constructed label graph to further refine the candidate set of annotations generated byGMM.Conducted experiments on the standard Corel5k demonstrate that GMM-RW is significantlymore effective than several state-of-the-arts regarding their effectiveness and efficiency in the task of automatic image annotation.     

新条件下一类特殊函数的Muntz有理逼近

目的讨论有界变差函数BV[0，1]和Sobolev类w：[0，1]的Muntz有理逼近问题。方法应用构造性分析的方法进行研究。结果给出了在较为广泛条件下Muntz有理逼近的速度估计。结论所得结果说明Muntz有理函数可以实现对于有界变差函数和Sobolev函数的逼近。     

Bernstein-Kantorovich算子线性组合同时逼近的点态估计

借助于Ditzian-Totik光滑模ωψλr(f,t)(0≤λ≤1)给出了Bernstein-Kantorovich算子线性组合同时逼近的点态估计.     

水泥稳定沙砾试铺方案探讨

对水泥稳定沙砾试铺筑过程中的人员安排、机械配备、施工工艺及现场试验等内容进行了总结,确定了施工中的施工工艺、松铺系数、碾压遍数等。     

ARFIMA approximation and forecasting of the limiting aggregate structure of long‐memory process

This article studies Man and Tiao's (2006) low‐order autoregressive fractionally integrated moving‐average (ARFIMA) approximation to Tsai and Chan's (2005b) limiting aggregate structure of the long‐memory process. In matching the autocorrelations, we demonstrate that the approximation works well, especially for larger d values. In computing autocorrelations over long lags for larger d value, using the exact formula one might encounter numerical problems. The use of the ARFIMA(0, d, d?₁) model provides a useful alternative to compute the autocorrelations as a really close approximation. In forecasting future aggregates, we demonstrate the close performance of using the ARFIMA(0, d, d?₁) model and the exact aggregate structure. In practice, this provides a justification for the use of a low‐order ARFIMA model in predicting future aggregates of long‐memory process. Copyright © 2008 John Wiley & Sons, Ltd.