基于负载分布的路由算法(LPR)

给出基于路由分布的路由算法,将有效带宽分散于候选路由集中,以匹配到达的虚电路请求服务质量的分布特点。这一方案与传统的负载均衡化和负载打包相比,具有高效的负载公布,较好地支持了应用的实时服务质量。     

图像识别技术在停车场安全系统中的应用

介绍利用图像识别技术设计停车场安全系统的方法     

基于修正思想的车牌图像定位与二值化处理

车牌图像定位和二值化是车牌识别系统中一个关键的部分。传统的处理方法是使用单一的算法,以便能够满足实时性的要求。但是算法本身的缺陷性使其不能适应一些具有独特特点的车牌,不能正确地识别出结果。基于提高算法的适应范围考虑,在满足识别速率要求的前提下,该文提出了基于修正思想的“去粗取精”处理模式,可以大大改善定位和二值化处理的效果,为后续的处理提供了一个良好效果的输入。     

嫦娥五号探月雷达的数据处理方法研究

探月雷达对于认识月球和开发月球资源具有重要意义,我国发射的嫦娥五号探测器已于2020年12月1日在月球表面着陆,圆满完成了嫦娥三期工程"采样返回"任务.根据嫦娥五号的任务安排,月壤结构仪在月表采集的雷达数据传回地表后,需要准时对月壤钻头下方2m深度范围内的月壤结构和可能存在的月岩进行高分辨率成像,为后续月壤钻取任务提供...     

Real‐Time License Plate Detection in High‐Resolution Videos Using Fastest Available Cascade Classifier and Core Patterns

We present a novel method for real‐time automatic license plate detection in high‐resolution videos. Although there have been extensive studies of license plate detection since the 1970s, the suggested approaches resulting from such studies have difficulties in processing high‐resolution imagery in real‐time. Herein, we propose a novel cascade structure, the fastest classifier available, by rejecting false positives most efficiently. Furthermore, we train the classifier using the core patterns of various types of license plates, improving both the computation load and the accuracy of license plate detection. To show its superiority, our approach is compared with other state‐of‐the‐art approaches. In addition, we collected 20,000 images including license plates from real traffic scenes for comprehensive experiments. The results show that our proposed approach significantly reduces the computational load in comparison to the other state‐of‐the‐art approaches, with comparable performance accuracy.     

Corrosion of carbon steel in filling material in an urban environment

The corrosion process of carbon steel in soil has been investigated, in particular the influence of the soil of an urban environment. A field test was carried out with test panels buried in trenches. Localized and uniform corrosion rates were evaluated after 1 and 3 years. Soil samples from points adjacent to the panels were analyzed with respect to a number of physical and chemical parameters believed to influence the corrosion process. Corrosion products were analyzed and identified. The study shows that the localized corrosion rate of soil buried constructions may be remarkably high in a filling material in comparison to other soils. The heterogeneity of the soil seems to have a greater influence on the localized corrosion rate than the chemical composition of the soil. However, the uniform corrosion rate was comparatively low in the heterogeneous filling material. Both the high alkalinity in the soil water and the groundwater, and the high total hardness of the soil water in the filling material seem to reduce the uniform corrosion rate. Corrosion rate determinations with commercial probes is also discussed. The linear polarization resistance (LPR), the electric resistance (ER) and the corrosion potential measurement techniques are compared. All probes showed a seasonal variation in corrosion rate. The measurements with commercial probes were associated with some problems, mostly a result of poor contact between the probes and the soil.     

一种基于多特征提取的实用车牌识别方法

针对车牌识别系统的实际应用, 利用车牌区域的边缘梯度特征、几何形状特征、颜色特征、灰度纹理特征定位车牌, 然后校正车牌图像的颜色及倾斜度; 基于灰度投影法, 对普通及武警车牌均提出了有效字符分割方案, 通过自适应判别去除因字符断裂粘连、特殊字符等造成的干扰; 通过基于多特征值提取的神经网络方法初识别车牌; 最后将人眼的视觉特性用于模板匹配法, 解决易混淆字符及污损车牌的问题。通过大量实验证明, 该方法对车牌颜色、拍摄角度、光照条件等限制较少, 适用范围广、识别率高, 有较强的实用性。     

车牌的字符分割和字符识别的研究与实现

本文提出了一套简洁高效的车牌识别方法.首先,在字符分割上,改进了传统的投影算法,采用了在二值中对白色像素进行垂直投影的方法;识别则采用了一种基于模板匹配的方法,并结合统计学进行,即利用现有的特征向量,从待识别的图像中提取若干图像的特征向量与模板相对应的特征向量进行比较,计算模板向量和现有向量之间的相似度,然后将现有特征...     

一种基于字符分割与字符识别的LPR方法

对车牌识别(LPR)系统中字符分割与字符识别方法进行探讨.根据车牌字符的特点,首先利用投影法采用水平扫描和垂直扫描进行字符分割,接着对字符图像进行归一化处理,实现对字符的完全分割.在此基础上,利用BP神经网络识别算法实现车牌字符的识别,从而提高系统的识别速度和识别率.数字仿真的识别结果验证了该方法的正确性和有效性.     

在车牌识别项目中对阈值选定法的一点改进

汽车牌照的识别在交通管理体系中占着非常重要的地位，而在进行汽车牌照自动识别的过程中，应用一个恰当的阈值对图像进行二值化处理是整个识别过程的基础，适当的阈值会减轻后续工作量。介绍了几种阈值选定办法，并在大津法的基础上针对车牌这种特殊图像的识别作了一点改进。