基于Laplacian Eigenmap的图像变化检测虚警优化技术

对点目标的图像变化检测,现有的变化检测技术结果往往存在着虚警过大的问题。通过深入分析多个传统的变化检测方法的特点,利用各方法的互补性,提出了利用Laplacian Eigenmap对多个方法检测结果进行降维分类的优化技术。首先把各个方法对某个像素的检测结果用向量的形式进行表示,然后利用Laplacian Eigenmap对整个图像的数据流形在低维空间展开,最后利用模糊分类进行分类。该技术有两个优势：（1）在保证现有较高检测率的同时,大大降低了结果的虚警率;（2）它极大地降低了在传统方法中由于人为阈值取舍带来的偏差风险。但该技术的不足之处是增加了计算量。     

催化裂化催化剂积炭的杂原子组成及其再生转化机理

以不同工艺条件下的催化裂化待生、再生催化剂及催化剂再生烟气为研究对象,分析催化剂积炭的杂原子组成。依据密度泛函理论,利用Gaussian 09软件在B3LYP/def2-TZVP水平下对积炭中典型的含氮、含硫化合物进行几何优化,得到其最稳定构型;以Laplacian键级为判据,研究积炭中杂原子的转化机理。结果表明：催化剂积炭中的含氮化合物主要是吡啶类、吡咯类和季胺类化合物,含硫化合物主要是噻吩类化合物;催化剂再生初期,含氮化合物以∶NH和·CN的形式逸出,主要转化成NH₃和HCN;含硫化合物以·HS和∶S等形式逸出,主要转化为H₂S、COS;随着再生过程的进行,NH₃、HCN和H₂S、COS最终分别转化为NO_x和SO_x。模拟结果与不同再生工艺条件下再生烟气组成一致。     

Gaussian-Hermite moment-based depth estimation from single still image for stereo vision

Depth information of objects plays a significant role in image-based rendering. Traditional depth estimation techniques use different visual cues including the disparity, motion, geometry, and defocus of objects. This paper presents a novel approach of focus cue-based depth estimation for still images using the Gaussian-Hermite moments (GHMs) of local neighboring pixels. The GHMs are chosen due to their superior reconstruction ability and invariance properties to intensity and geometric distortions of objects as compared to other moments. Since depths of local neighboring pixels are significantly correlated, the Laplacian matting is employed to obtain final depth map from the moment-based focus map. Experiments are conducted on images of indoor and outdoor scenes having objects with varying natures of resolution, edge, occlusion, and blur contents. Experimental results reveal that the depth estimated from GHMs can provide anaglyph images with stereo quality better than that provided by existing methods using traditional visual cues.     

常曲率空间中具有调和曲率的超曲面

研究员常曲率空间中具有调和曲率的紧致超曲面．在一定的条件下，给出了一类超曲面结构的决定定理．     

Decentralized control of vehicle formations

This paper investigates a method for decentralized stabilization of vehicle formations using techniques from algebraic graph theory. The vehicles exchange information according to a pre-specified communication digraph, G. A feedback control is designed using relative information between a vehicle and its in-neighbors in G. We prove that a necessary and sufficient condition for an appropriate decentralized linear stabilizing feedback to exist is that G has a rooted directed spanning tree. We show the direct relationship between the rate of convergence to formation and the eigenvalues of the (directed) Laplacian of G. Various special situations are discussed, including symmetric communication graphs and formations with leaders. Several numerical simulations are used to illustrate the results.     

A Study on the Finite Difference Approach of the Surface Laplacian

The surface Laplacian of bioelectrical activity was first applied to the Electroencephalogram (EEG) by Hjorth[1]. In the field of ECG, the body surface Laplacian mapping was also developed to provide better spatial resolution than the body surface potential distribution[2]. There are generally two kinds of estimation of surface Laplacian: local methods and global methods. The former calculate the difference of potentials recorded from neighboring electrodes[1]. The latter are based on the…     

数据聚类技术的研究

在分析指出传统数据聚类方法的缺点和不足的基础上,提出了一种新的数据聚类方法,给当前数据聚类技术的研究提供了一个新的思路。     

Hypergraph imaging: an overview

Hypergraph theory as originally developed by Berge (Hypergraphe, Dunod, Paris, 1987) is a theory of finite combinatorial sets, modeling lot of problems of operational research and combinatorial optimization. This framework turns out to be very interesting for many other applications, in particular for computer vision. In this paper, we are going to survey the relationship between combinatorial sets and image processing. More precisely, we propose an overview of different applications from image hypergraph models to image analysis. It mainly focuses on the combinatorial representation of an image and shows the effectiveness of this approach to low level image processing; in particular to segmentation, edge detection and noise cancellation.     

Multiple statistical models for soft decision in noisy speech enhancement

Most speech enhancement algorithms are based on the assumption that speech and noise are both Gaussian in the discrete cosine transform (DCT) domain. For further enhancement of noisy speech in the DCT domain, we consider multiple statistical distributions (i.e., Gaussian, Laplacian and Gamma) as a set of candidates to model the noise and speech. We first use the goodness-of-fit (GOF) test in order to measure how far the assumed model deviate from the actual distribution for each DCT component of noisy speech. Our evaluations illustrate that the best candidate is assigned to each frequency bin depending on the Signal-to-Noise-Ratio (SNR) and the Power Spectral Flatness Measure (PSFM). In particular, since the PSFM exhibits a strong relation with the best statistical fit we employ a simple recursive estimation of the PSFM in the model selection. The proposed speech enhancement algorithm employs a soft estimate of the speech absence probability (SAP) separately for each frequency bin according to the selected distribution. Both objective and subjective tests are performed for the evaluation of the proposed algorithms on a large speech database, for various SNR values and types of background noise. Our evaluations show that the proposed soft decision scheme based on multiple statistical modeling or the PSFM provides further speech quality enhancement compared with recent methods through a number of subjective and objective tests.