一种基于人工免疫的图像分割算法

提出了二维熵图像分割的人工免疫算法。在遥感高分辨率图像上的实验显示,该算法不仅能准确搜索到最优阈值对,而且计算时间只有传统算法的1.8%。该算法也验证了人工免疫思想用于图像分割的可行性和有效性。     

应用人工免疫算法快速规划3DTF/TA~2航线

针对复杂环境下单(双)机TF/TA2飞行路径规划问题,提出了满足飞机可飞性和可操作性的人工免疫算法飞行航线规划方法;设计了综合3D威胁信息的惩罚函数(亲和力函数);构建了包含动态、静态威胁及不可飞区域的综合威胁模型。据此,设计了不同威胁度环境下的单、双飞行航线,并将人工免疫算法规划的航线与遗传算法进行比较。结果表明,在简单威胁环境下,遗传算法规划时间短、路径较长;在复杂环境下,遗传算法的单机规划失败率极高(大于95%),双机规划失败。人工免疫算法能够为单(双)机规划出一条最优及多条待选飞行航线。     

人工智能时代的测绘工程教育改革

人工智能技术发展至今,已掀起了第三次浪潮。人工智能时代的到来必将推动测绘工程教育的改革。本文从人工智能技术的发展历程出发,阐述了人工智能在测绘行业的应用现状和发展趋势,分析了人工智能对教育行业的影响,探讨了人工智能与高等教育相结合的应用前景。结合测绘工程高等教育的现状,分别从培养理念、知识结构、教学方法和创新能力4个方面构建了人工智能时代测绘工程专业的教育改革体系,为探索我国测绘工程高等教育同人工智能的深度融合提供理论参考和经验借鉴。     

基于人工免疫系统的遥感图像检索

为了提高遥感图像检索的准确性,提出了一种基于人工免疫系统(artificial immune system)的遥感图像检索算法。该算法根据相关反馈技术及免疫机理,利用克隆选择算法对用户反馈的图像特征进行泛化学习,从而提高了系统对用户语义的理解能力。实验结果表明,该算法能有效理解用户的反馈信息,能提高检索的准确性。     

基于遗传算法的多光谱影像非监督训练分类系统

本文将遗传算法（GA）应用于非监督训练,提高了遥感数据的分类精度。遗传竞争学习算法（GA-CL）综合了遗传算法和简单的竞争学习算法,可用于改进非监督训练的结果。遗传算法在典型样本聚类的过程中可以避免得到局部最优值。Jeffries-Matusita（J-M）距离法是通过统计测量两个训练类别之间的分离度,可用于评价这种算法。将此算法应用于TM数据的结果显示,遗传算法改进了简单的竞争学习算法,与其他非监督训练算法相比,其提供了K-均值,GA-K-均值和简单的竞争学习算法。     

Geospatial Agents, Agents Everywhere . . .

The use of the related terms “agent‐based”, “multi‐agent”, “software agent” and “intelligent agent” have witnessed significant growth in the Geographic Information Science (GIScience) literature in the past decade. These terms usually refer to both artificial life agents that simulate human and animal behavior and software agents that support human‐computer interactions. In this article we first comprehensively review both types of agents. Then we argue that both these categories of agents borrow from Artificial Intelligence (AI) research, requiring them to share the characteristics of and be similar to AI agents. We also argue that geospatial agents form a distinct category of AI agents because they are explicit about geography and geographic data models. Our overall goal is to first capture the diversity of, and then define and categorize GIScience agent research into geospatial agents, thereby capturing the diversity of agent‐oriented architectures and applications that have been developed in the recent past to present a holistic review of geospatial agents.     

基于GIS和神经网络的森林植被分类

本文综述了国际遥感分类研究,使用Landsat7 ETM＋遥感数据和地理辅助数据,应用BP神经网络方法,将莽汉山林场作为研究区进行了遥感影像的分类研究。比较了BP神经网络分类与最大似然、简单和复杂非监督分类法之间的类型与数量精度。BP神经网络分类的总类型精度是70.5%,总数量精度为84.65%,KAPPA系数是0.6455。结果说明BP神经网络的分类质量优于其他方法,其总的类型精度与其他三种分类方法相比分别增加了10.5%、32%和33%,总的质量精度增加了5.3%。因此,辅以地理参考数据的BP神经网络分类可以作为一种有效的分类方法。     

基于ArcGIS Engine的飞机人工增雨航线自动化设计算法研究

人工增雨作为应急抗旱和缓解水资源紧张的重要手段,与社会经济可持续发展、生态安全和人民生活密切相关。航线设计是飞机人工增雨作业方案设计的一项重要内容,基于GIS平台自动化设计飞行航线将成为趋势。在传统飞行航线设计方案的基础上,研究提出了基于ArcGIS Engine的半圆弧过渡条播航线、＂弓＂字形条播航线和＂之＂字形条播航线三种层状云作业＂穿云＂航线与一种对流云或层积混合云作业＂绕云＂航线的自动化设计算法。应用结果显示,四种自动化算法均能够快速有效地设计出飞机航线,取得很好的效果。     

HJ-1A/B卫星CCD影像辅助的MODIS水色大气校正产品质量改进

针对我国近岸高浑浊水体区域MODIS短波红外波段大气校正产品中存在的信号饱和及条带问题,利用神经网络模型,采用准同步的HJ-1A/B卫星CCD影像及实测遥感反射率数据对MODIS/Terra水色遥感大气校正产品进行了质量改进。改进后结果与MODIS/Terra遥感反射率产品相比,平均相对误差为13.3%,信号饱和区域修复结果与实测数据各波段平均相对误差为28.2%。结果表明,该方法在保证结果精度的情况下,能有效地修复MODIS/Terra水色波段因为信号饱和而产生的数据空白区域,同时也能较好地解决MODIS/Terra大气校正产品中的条带问题。     

On fine orbit selection for particular geodetic and oceanographic missions involving passage through resonances

 The identification of mean semi-major axes (suitably defined) for satellite orbits to satisfy a variety of requirements for geodesy, geophysics and oceanography, in terms of repeat orbits (with orbital resonances), is investigated. Various options for the definition of semi-major axis, from the viewpoint of satellite dynamics, are described. Simple simulations of the expected resonant changes in inclination are presented, and tools for the analysis of orbit resonances to extract certain lumped harmonic coefficients of the geopotential (e.g. from the very precise CHAMP orbit) are resurrected. Finally, a preliminary example of the 46th-order resonance analysis possible for CHAMP, based on the mean orbital elements produced by GFZ (GeoForschungs Zentrum) for ephemeris prediction, is presented. Received: 10 July 2001 / Accepted: 17 July 2002 Correspondence to: J. Klokočník at Ondřejov Observatory Acknowledgements. We thank Prof. Dr. Ch. Reigber, Dr. P. Schwintzer, Dr. T. Gruber and Dr. R. K?nig from GFZ Potsdam for various consultations and discussions, and for the CHAMP two-line mean elements. This investigation was performed under the aegis of CEDR (Center for Earth's Dynamics Research, Prague-Ondřejov); it has been supported by project LN00A005 (provided by the Ministry of Education of the Czech Republic) and by grant A 3004 of the Grant Agency of the Academy of Sciences of the Czech Republic.