基于主分量分析的多维时间序列特征选择方法研究

研究了多维时间序列的特征选择问题。首先,讨论了主分量分析的原理;然后,将提出的斜率趋势算法和核函数分类算法应用于多维时间序列的特征选择过程中,并探讨了两类方法的优缺点;最后,采用两种算法对目标距离像多维时间序列进行了仿真实验。实验结果表明了所应用方法的可行性和有效性.     

基于图论分割的多光谱图像非监督分类方法

针对传统基于像素的多光谱遥感图像分类方法存在的"麻点"现象、采样成本高等问题,提出了一种基于图论分割的非监督分类方法,首先采用基于图论的分割算法,按局部邻近相似像素点分割成若干子区域,再以分割后子区域为基本单元,整体进行模糊 C均值聚类,最终实现对多光谱图像的非监督分类.实验证明,该方法结合了局部邻近像素点的相互关系以及相似区域的整体特征,有效解决了麻点问题,具有较高的分类精度和算法效率,降低了采样成本.     

基于支持向量机的无参考遥感图像质量评价方法

针对遥感图像主观评价方法的低效率以及常用客观评价方法无法充分考虑人眼对图像的感知特性的问题,文章提出了一种基于支持向量机的无参考遥感图像质量（quality）评价方法。首先建立遥感图像主观评价库,然后在不需要图像失真信息的基础上,利用支持向量机（SVM）将图像的失真类型分为三类,并对每类进行单项评价,再通过加权得到遥感图像的总评分,最后将本文方法、信噪比与信息熵的评价结果回归到主观评价空间并进行对比。实验证明,文章所提方法能客观地评价遥感图像的质量,且优于信噪比和信息熵两种质量评价方法,其结果与人眼视觉感受相符。     

Assessment of the impact of dimensionality reduction methods on information classes and classifiers for hyperspectral image classification by multiple classifier system

Identification of the appropriate combination of classifier and dimensionality reduction method has been a recurring task for various hyperspectral image classification scenarios. Image classification by multiple classifier system has been evolving as a promising method for enhancing accuracy and reliability of image classification. Because of the diversity in generalization capabilities of various dimensionality reduction methods, the classifier optimal to the problem and hence the accuracy of image classification varies considerably. The impact of including multiple dimensionality reduction methods in the MCS architecture for the supervised classification of a hyperspectral image for land cover classification has been assessed in this study. Multi-source airborne hyperspectral images acquired over five different sites covering a range of land cover categories have been classified by a multiple classifier system and compared against the classification results obtained from support vector machines (SVM). The MCS offers acceptable classification results across the images or sites when there are multiple dimensionality reduction methods in addition to different classifiers. Apart from offering acceptable classification results, the MCS indicates about 5% increase in the overall accuracy when compared to the SVM classifier across the hyperspectral images and sites. Results indicate the presence of dimensionality reduction method specific empirical preferences by land cover categories for certain classifiers thereby demanding the design of MCS to support adaptive selection of classifiers and dimensionality reduction methods for hyperspectral image classification.     

Towards a cooperation between the arts,space science research and the European Space Agency – Preliminary findings of the ESA Topical Team Arts and Sciences (ETTAS)

The arts offer alternative insights into reality, which are explored by science in general, and broadened by the activities conducted by the European Space Agency [4] and other space agencies. Similar to the way the members of ESA are ambassadors for spaceflight and science, artists and cultural professionals are ambassadors for human expression, experimentation, and exploration. In June 2011, the ESA Topical Team Arts and Sciences (ETTAS) held a three-day workshop at the European Astronaut Centre in Cologne, Germany. During this workshop, topics and ideas were discussed to develop initiatives between the arts, sciences and ESA. The aim was to foster and expand the human and cultural aspects of space exploration, and at the same time offer a means of communication that aims to reach audiences beyond the scope of traditional space-related channels. The consensus of the team was that establishing and sustaining a transdisciplinary professional community consisting of ESA representatives, scientists and artists would fuel knowledge transfer, and mutual inspiration. Potential ways to provide a sustainable cooperation within and between the various groups were discussed. We present the preliminary findings including a number of measures and mechanisms to initiate and conduct such an initiative. Plausible organisational measures, procedures and consequences, as well as a proposition on how to proceed are also discussed. Overall, the involvement and cooperation between the arts, space science research and ESA will enhance in the citizens of the ESA member states the sense of public ownership of ESA results, and participation in ESA?s research.     

基于双重分类深度学习的低空目标自动检测方法

由于图像数量多,因此准确、高效的目标检测是提升靶场光测图像处理自动化程度的关键步骤.针对低空目标图像及目标类型多、目标特性变化等情况导致传统目标检测算法适应性差的问题,提出了一种基于双重分类深度学习的低空目标自动检测方法.该方法基于深度学习目标检测框架YOLO V3,根据低空目标的亮度和形状的双重属性特征,将网络输出层...     

基于多种空间信息的高光谱遥感图像分类方法

在高光谱遥感图像分类方法中,空间特征和光谱特征的融合可以有效地改善分类效果。针对单一空间特征的信息表达不充分问题,提出了一种联合多种空间特征的高光谱图像空谱分类方法。利用超像素信息对分类结果进行后处理去掉椒盐噪声,并创造性地将超像素信息应用于分类前处理,提出了一种利用超像素信息对像素点的特征向量进行线性加权融合的方法。试验结果表明,所提方法的性能优于目前的通常方法。     

基于支持向量机的机场智能驱鸟决策

为提高机场鸟击防范管理水平,实现探鸟雷达与多种驱鸟设备联动,提出一种基于支持向量机（SVM）的机场智能驱鸟决策方法。该方法包括训练和测试两部分。训练部分利用机场鸟类探测预警与驱赶联动系统获取的大量历史鸟情信息,结合专家知识,通过数据预处理与支持向量机训练,建立驱鸟策略分类模型;测试部分根据驱鸟实时智能决策结果,对驱鸟策略分类模型进行持续修正与优化。通过某机场的实测鸟情信息数据与若干驱鸟实例,证明驱鸟策略分类模型具有较高的决策正确率,并能够通过自身修正与优化应对各种新问题。本文方法针对实时鸟情信息,实现了多种驱鸟设备的优化组合,克服了驱鸟设备长期重复运行造成的鸟类对驱鸟设备的耐受性问题,极大改善了驱鸟效果。      

核空间聚类在图像纹理分类中的简化算法

模糊c均值聚类已广泛应用于模糊模式识别领域,但对于线性不可分数据并不适用.在核方法中通过将输入数据经过非线性映射投影到高维特征空间来解决非线性分类的问题.将传统的模糊c均值聚类算法应用于核空间中,对线性不可分的样本进行了核空间聚类的分类实验,得到了正确的分类结果.由于图像分类中分类样本(对应图像像素)数目庞大,造成了核空间聚类算法中特征距离的计算量过大.因此,在核空间聚类的基础上,提出了对图像先进行过分割,再对过分割的图像块进行核空间聚类的方法,大大降低了高维空间特征距离计算的运算成本,并取得了良好的分类效果.