基于计算机视觉和图像处理的交通参数检测

本文提出了一种基于计算机视觉和图像处理的车流量检测方法,通过分析CCD TV 摄 像机获取的图像中车辆和场景信息来有效地检测交通参数．本方法可以完成双向四车道高速 公路和城市道路的车辆计数和车辆速度检测．实验结果表明：车辆计数的正确率为94％,车 辆速度检测的正确率达92%,并具有满意的实时特性．     

用于图像恢复的基于SVR的自适应新滤波器的研究*

提出了一种用SVR回归器识别脉冲噪声的思想,并将其应用于图像滤波和恢复,形成了用于对脉冲噪声进行滤波的SVR自适应滤波器。这种滤波器在滤波时,先用SVR对待识别像素作噪声识别,再对含噪声的像素作中值滤波。用SVR作噪声识别时,先对滤波窗口作SVR回归,通过待识别像素回归距的大小判断其是否含有噪声。在进行SVR回归时,使用鲁棒的Huber损失函数。由于更充分地利用了待识别像素点的局部背景信息,这种滤波器提高了脉冲噪声识别的正确率。实验表明,在保留原图像的细节信息方面,其滤波效果要优于基于SVC的中值滤波器。     

一种基于配对相关变换的多描述图像编码方案

多描述图像编码能够使图像数据在多个有损信道中传输,并允许某些信道的数据发生丢失的情况下,仍能重构出可接受的图像质量。对基于配对相关变换的多描述图像编码方法进行了分析,并把它结合到JPEG编码算法中,最后给出了编码的验证结果。     

一种低比特率下的快速SAR图像压缩方法*

提出了一种低比特率的快速压缩方法,通过基于小波的降采样增强像素间的相关,继而使用小波包分解降采样后的图像并使用基于零块的方法对系数进行编码。实验结果表明用该方法进行压缩能够得到优于JPEG2000的主观效果,对边缘保持更好,并且计算量小,适合实时实现。     

痰液显微图像细胞边缘提取的数学形态学新方法

根据痰液细胞图像的边缘灰度变化特点,在经典微分算子检测基础上,运用适当的改进的数学形态学方法对痰液细胞进行边缘提取。在实验中对同一幅痰液细胞图像分别用Sobel算子、Roberts算子、Laplacian算子和基于数学形态学的方法进行边缘检测。结果表明,基于数学形态学的边缘提取算法对于痰液细胞图像边缘提取有很好的效果。     

On Similarity Measures for Multimedia Database Applications

A multimedia database query consists of a set of fuzzy and boolean (or crisp) predicates, constants, variables, and conjunction, disjunction, and negation operators. The fuzzy predicates are evaluated based on different media criteria, such as color, shape, layout, keyword. Since media-based evaluation yields similarity values, results to such a query is defined as an ordered set. Since many multimedia applications require partial matches, query results also include tuples which do not satisfy all predicates. Hence, any fuzzy semantics which extends the boolean semantics of conjunction in a straight forward manner may not be desirable for multimedia databases. In this paper, we focus on the problem of ‘given a multimedia query which consists of multiple fuzzy and crisp predicates, how to provide the user with a meaningful overall ranking.’ More specifically, we study the problem of merging similarity values in queries with multiple fuzzy predicates. We describe the essential multimedia retrieval semantics, compare these with the known approaches, and propose a semantics which captures the retrieval requirements in multimedia databases. Received 13 August 1999 / Revised 13 May 2000 / Accepted in revised form 26 July 2000     

Synthesis and characterisation of alumina pillared Texas montmorillonite and determination of the effective Keggin ion charge

Controlled calcination of Texas montmorillonite has allowed production of a range of materials of cation exchange capacity from 70 mequiv./100 g dry clay to virtually zero. Pillaring of these with Chlorhydrol precursor solution has then provided a family of materials of pillar density ranging from about one per six unit cells to zero. The analytical technique based on isomorphous metal dilution (IMD) that follows pillaring is validated. The results provide a consistent value for the precursor (Keggin) ion charge, in the conditions normally used, of 3.15±0.10 rather than the formal value of 7. An approach to the attainment of pillar densities consistent with the introduction of shape/size selectivity on pillared layered materials is outlined.     

Preparation of acidic or bifunctional catalysts by means of straightforward calcination of as-synthesized [Ga]-ZSM-5 zeolites obtained from alkali-free media. Propane aromatization

Propane aromatization (530°C, 1 atm) was used as a reaction model to evaluate the effect of the calcination temperature on the catalytic properties of an as-synthesized [Ga_1.3]-ZSM-5 zeolite obtained from alkali-free media and calcined at two different temperatures: 530°C (C-530) and 750°C (C-750). Results show that in spite of its lower acidity, C-750 is more active and selective toward aromatics than C-530. This is probably due to the fact that at higher temperature the decomposition of organic compounds used during the zeolite synthesis is accompanied by a partial degalliation of the zeolitic support leading to the production of a bifunctional xGa₂O₃ /H-[Ga_y-ZSM-5(2x+y=1.3)catalyst.     

An adaptive associative memory system based on autonomous reaction between image memories

To construct a “thinking-like” processing system, a new architecture of an adaptive associative memory system is proposed. This memory system treats “images” as basic units of information, and adapts to the environment of the external world by means of autonomous reactions between the images. The images do not have to be clear, distinct symbols or patterns; they can be ambiguous, indistinct symbols or patterns as well. This memory system is a kind of neural network made up of nodes and links called a localist spreading activation network. Each node holds one image in a localist manner. Images in high-activity nodes interact autonomously and generate new images and links. By this reaction between images, various forms of images are generated automatically under constraints of links with adjacent nodes. In this system, three simple image reaction operations are defined. Each operation generates a new image by combining pseudofigures or features and links of two images. This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999     

A MODIFIED METHOD FOR SUPERVISOR SPECIFICATION AND SYNTHESIS OF A CLASS OF DISCRETE EVENT SYSTEMS

In this paper, a model‐refining method is proposed to alleviate the complexity involved in specification interpretation of DES control problems. The legal constraint language is defined in terms of illegal states and events in contrast with constructing the automaton of the specification language. This method could provide a more intuitive view of the DES control problem and would be suitable for practical implementation. Two examples, which have commonly been used in the literature, are employed to show the efficiency of the proposed method. Further, under this framework, it is shown that the supremal controllable sublanguage can take a simpler form based on the concept of an illegal state set. A state‐based supervisor synthesis procedure is presented, and a simple example is provided.