基于多特征的高分遥感图像分割算法研究

针对传统的图像分割算法不能完全适用具有多种特征〖BF〗（〖BFQ〗光谱特征、纹理特征和几何特征〖BF〗）〖BFQ〗的高分辨率遥感图像的问题,提出了一种基于多特征的遥感图像分割算法。算法基于改进的均值漂移滤波和自动标记分水岭分割方法来实现最终分割。首先利用自动标记分水岭分割方法对遥感图像进行分割,进而采用仿射不变矩形状特征算子提取图像几何特征;其次对图像进行主成分分析,计算第一主成分灰度共生矩阵,分析矩阵特性得出纹理特征;然后结合光谱特征通过改进的均值漂移方法得到多特征滤波结果;最后利用分水岭分割方法实现高分辨率遥感图像分割。为了表明算法的分割效果,利用基于多光谱信息熵方法对算法和单一的分水岭分割方法进行非监督评价。研究结果表明,算法可较好地改善遥感图像的过分割问题,是一种适合高空间分辨率多光谱遥感图像的分割算法。     

基于自适应阈值的粒子滤波非线性系统故障诊断

针对实际非线性系统传统方法难以实现可靠故障诊断的问题,采用粒子滤波算法,利用对数似然函数和作为评价指标,并借助自适应阈值的设计,研究了非线性非高斯系统的故障检测和故障隔离。阈值的选取,是准确判别系统是否发生故障的标准,本文通过分析非线性系统残差的统计特性,在判定残差统计特性成正态分布的基础上,设计了一种基于粒子滤波故障诊断的自适应阈值方法,减少了故障诊断的漏报和误报。通过非恒温连续搅拌水箱式反应堆的仿真实例,验证了该方法在故障诊断中的准确性和有效性。      

A model of the effects of heavy ion radiation on human tissue

In heavy ion radiotherapy and space travel humans are exposed to energetic heavy ions (C, Si, Fe and others). This type of irradiation often produces more severe biological effects per unit dose than more common X-rays. A new Monte Carlo model generates a physical space with the complex geometry of human tissue or a cell culture based model of tissue, which is affected by the passage of ionizing radiation. For irradiation, the model relies on a physical code for the ion track structure; for tissues, cellular maps are derived from two- or three-dimensional confocal microscopy images using image segmentation algorithm, which defines cells as pixilated volumes. The model is used to study tissue-specific statistics of direct ion hits and the remote ion action on cells. As an application of the technique, we considered the spatial pattern of apoptotic cells after heavy ion irradiation. The pattern of apoptosis is modeled as a stochastic process, which is defined by the action cross section taken from available experimental data. To characterize the degree of apoptosis, an autocorrelation function that describes the spatial correlation of apoptotic cells is introduced. The values of the autocorrelation function demonstrate the effect of the directionality of the radiation track on the spatial arrangements of inactivated cells in tissue. This effect is intrinsic only to high linear-energy-transfer radiation.     

基于小波包分解和FCM聚类的纹理图像分割方法

提出了一种新的图像特征提取中选取最优小波分解树的方法.塔式小波分解对信号解不够全面,而小波包全分解又引入庞大的计算量,因此小波分解最优树的选取尤为重要.结合模糊c均值(FCM,Fuzzy C-Mean)聚类,提出了一种能同时进行小波自适应分解和纹理特征分类的纹理图像分割方法,该方法将无监督聚类中的聚类有效性参数引入到自适应小波分解的判决中,能根据无监督聚类分割的需要,自适应地选取小波包分解的树形结构和分解层数.相对于小波包全分解,节省了大量的运算,并能取得良好的分割效果.      

彩色图像分割算法研究与费歇算法应用

图像分割是图像分析和模式识别需要解决的首要问题和经典难题。彩色图像比灰度图像具有更多的视觉信息,因而受到了越来越多的重视。文中对各种彩色图像分割方法进行了系统论述,分析了各种方法的优缺点,重点介绍了费歇算法。该算法能有效地对彩色图像进行分割,在工业实践中取得了比较好的效果。     

Ku波段镜像抑制混频器的研制

介绍一种小型化Ku波段镜像抑制混频器设计方案,以单片无源双平衡混频器为基础,对主要关键电路射频正交耦合器、中频正交耦合器以及本振同相功分器进行电路优化设计及制作。在近1GHz的带宽内成功实现了镜像抑制大于20dB,插入损耗小于10dB,隔离度大于25dB的Ku波段无源镜像抑制混频器。实测结果表明,系统具有低损耗、高隔离度、高镜像抑制及高集成度的特点,在捷变频雷达、通信及遥测等系统中具有较好的应用前景。     

基于神经网络预测模型的歼击机结构故障检测方法

提出了一种基于预测神经网络的歼击机结构故障检测新方法 ,与传统的基于模型的非线性系统的故障检测方法相比 ,神经网络方法有着非线性逼近能力强和故障检测实时性好等优点。给出了基于预测神经网络的故障检测方案 ,以及多步直接预测算法和阈值选取原则 ,最后以某型歼击机为例进行了仿真验证 ,仿真结果表明本方法能有效地检测出歼击机的各种结构故障。     

An ensemble deep learning based shoreline segmentation approach (WaterNet) from Landsat 8 OLI images

Shorelines constantly vary due to natural, urbanization and anthropogenic effects such as global warming, population growth, and environmental pollution. Sustainable monitoring of coastal changes is vital in terms of coastal resource management, environmental preservation and planning. Publicly available Landsat 8 OLI (Operational Land Manager) images provide accurate, reliable, temporal and up-to-date information about coastal areas. Recently, the use of machine learning and deep learning algorithms have become widespread. In this study, we used our public Landsat 8 OLI satellite image dataset to create a majority voting method which is an ensemble automatic shoreline segmentation system (WaterNet) to obtain shorelines automatically. For this purpose, different deep learning architectures have been utilized namely as Standard U-Net, Dilated U-Net, Fractal U-Net, FC-DenseNet, and Pix2Pix. Also, we have suggested a novel framework to create labeling data from OpenStreetMap service to create a unique dataset called YTU-WaterNet. According to the results, IoU and F1 scores have been calculated as 99.59% and 99.79% for the WaterNet. The results indicate that the WaterNet method outperforms other methods in terms of shoreline extraction from Landsat 8 OLI satellite images.     

连续型和非连续型蜂窝芯材的共振吸声结构性能研究

以芳纶纸蜂窝、内嵌树脂隔板和微穿孔面板为原料,制备了连续和非连续双自由度共振吸声结构,对两种共振吸声结构的力学性能和吸声系数进行对比研究。结果表明：连续蜂窝芯材所制备共振吸声结构的压缩和拉伸性能高于非连续型共振吸声结构,其中非稳定型压缩强度和拉伸强度高19%,稳定型压缩强度高32%,稳定型压缩模量高43%,剪切性能基本相当;两层蜂窝芯材容易出现孔格错位（非连续型共振吸声结构）,引起错位区域的微孔堵塞,使该结构的共振吸收峰与理论值出现较大差异。     

铅化合物在双基推进剂燃烧过程的作用机理

本文提出了铅化合物催化双基推进剂燃烧的反应历程。充分说明这类化合物是最终通过提高燃烧表面处嘶嘶区温度梯度提高燃速的。本文还提出了“铅化合物有通过增加燃烧表面上碳质物量增加燃速的一面,还有通过减少碳质物抑制燃速增加的一面”这一新的论点及抑制碳质物增加的反应并阐明了压力对这种抑制能力的影响。最后根据本文提出的作用机理及传热原理圆满解释了超速、平平和/或麦撒效应。