The use of remotely sensed data to detect channel hydromorphology; River Tummel,Scotland

Colour aerial photography and multi‐spectral imagery acquired from airborne platforms for the River Tummel, Scotland, was used in conjunction with field survey to assess the feasibility of monitoring hydromorphology and human alteration within the river corridor. The study was undertaken to investigate the possibility of remotely sensing the physical status of a nation's rivers at the national scale to comply with the requirement of the European Water Framework Directive. Visual assessment and unsupervised and supervised automated classifications of the imagery were undertaken and compared with field survey data. In the absence of overhanging vegetation canopies most features above the water line of interest were visible on the imagery. Below the water line, morphology and substrate composition together with bank materials on vertically cut banks are less easily detected. The overall accuracy of automated classification procedures, compared to field survey, was 60% for the colour aerial photography and 68% for the multi‐spectral imagery. Supervised classification was superior to unsupervised classification procedures. Sun glint on water surfaces and shadows caused by high banks, trees and buildings were observed as the cause of most misclassification of features. Overall, the study demonstrates that remotely sensed digital imagery has the potential to allow panoptic mapping of river hydromorphology and human impacts. The possibilities and constraints, in light of the findings of this study, are discussed. In the context of new legislation which requires environmental protection agencies to have robust tools for monitoring the physical status, as part of meeting the objective of good ecological status, of rivers across an entire nation, remote sensing appears to provide a way forward. Copyright © 2004 John Wiley & Sons, Ltd.     

基于改进GHSOM的运动想象脑电信号自适应识别方法

为解决运动想象脑电信号(MI-EEG)的识别方法泛化能力受限和自适应性差等问题,对传统的生长、分层自组织映射神经网络(GHSOM)进行改进,并提出一种主成分分析法(PCA)与改进的GHSOM神经网络(IGHSOM)相结合的脑电自适应识别方法。由于IGHSOM能够根据上一层扩展神经元的量化误差进行自动分层判断,使得其不仅对数据映射更加准确和详细,而且增强了网络的稳定性和自适应性。基于脑机接口(BCI)竞赛数据库,利用PCA进行特征提取,以IGHSOM为分类器进行实验研究。结果表明,该方法获得了较高的识别精度,验证了GHSOM改进策略及该识别方法的正确性和有效性。     

SAR图像舰船尾迹检测及其真假判别方法

针对常规Radon变换域中尾迹峰值检测的不确定性问题,提出了一种基于特征空间决策的尾迹检测算法.该算法首先门限化图像的Radon变换系数,提取出所有可能的峰值点;然后对这些相应的局部峰值的"截面"进行连续小波变换峰值匹配,再根据提取到的参数形成决策矢量在特征空间中进行决策.对仿真和实际数据处理的结果表明,该方法能有效、准确地检测到SAR图像中的舰船尾迹.     

基于相关向量机的高光谱影像混合像元分解

 提出了一种利用相关向量机后验概率进行高光谱影像混合像元分解的方法.基于支持向量机后验概率输出的高光谱影像混合像元分解方法中,类别后验概率需要通过带参数的S形函数近似,而且模型需要通过交叉验证获取较好的规则化系数.相关向量机是在贝叶斯框架下提出的更加稀疏的学习机器,它没有规则化系数,核函数不需要满足Mercer条件.本文从分析支持向量机用于高光谱影像混合像元分解存在的不足出发,介绍了稀疏贝叶斯分类模型和模型参数推断,采用了快速序列稀疏贝叶斯学习算法.通过PHI影像的混合像元分解实验分析,表明了基于相关向量机的高光谱影像混合像元分解方法的优势.     

浅析意境在东方园林中的运用

由诗词展开,简要分析意境的内涵,阐述了园林意境的特点及与诗画的区别和联系,并结合相关景观实例,重点分析了意境在中国园林及日本园林中的运用,最后总结出意境在园林建设中达到的艺术境界与探索园林意境的继承和发展的重要意义。     

Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques

Penicillium fungi are among the main defects that may affect the commercialization of citrus fruits. Economic losses in fruit production may become enormous if an early detection of that kind of fungi is not carried out. That early detection is usually based either on UltraViolet light carried out manually. This work presents a new approach based on hyperspectral imagery for defect segmentation. Both the physical device and the data processing (geometric corrections and band selection) are presented. Achieved results using classifiers based on Artificial Neural Networks and Decision Trees show an accuracy around 98%; it shows up the suitability of the proposed approach.     

Mapping variations in weight percent silica measured from multispectral thermal infrared imagery—Examples from the Hiller Mountains, Nevada, USA and Tres Virgenes-La Reforma, Baja California Sur, Mexico

Remotely sensed multispectral thermal infrared (8-13 μm) images are increasingly being used to map variations in surface silicate mineralogy. These studies utilize the shift to longer wavelengths in the main spectral feature in minerals in this wavelength region (reststrahlen band) as the mineralogy changes from felsic to mafic. An approach is described for determining the amount of this shift and then using the shift with a reference curve, derived from laboratory data, to remotely determine the weight percent SiO₂ of the surface. The approach has broad applicability to many study areas and can also be fine-tuned to give greater accuracy in a particular study area if field samples are available. The approach was assessed using airborne multispectral thermal infrared images from the Hiller Mountains, Nevada, USA and the Tres Virgenes-La Reforma, Baja California Sur, Mexico. Results indicate the general approach slightly overestimates the weight percent SiO₂ of low silica rocks (e.g. basalt) and underestimates the weight percent SiO₂ of high silica rocks (e.g. granite). Fine tuning the general approach with measurements from field samples provided good results for both areas with errors in the recovered weight percent SiO₂ of a few percent. The map units identified by these techniques and traditional mapping at the Hiller Mountains demonstrate the continuity of the crystalline rocks from the Hiller Mountains southward to the White Hills supporting the idea that these ranges represent an essentially continuous footwall block below a regional detachment. Results from the Baja California data verify the most recent volcanism to be basaltic-andesite.     

LOWTRAN7在动态红外图像仿真系统中的应用及系统集成

介绍海洋作战环境下动态红外图像仿真系统的工程实现。着重介绍了ＬＯＷＴＲＡＮ模型在动态红外图像仿真系统中的应用及仿真系统中的数据流程、系统结构和系统集成中的主要情况。     

Drawings and the design process: A review of protocol studies in design and other disciplines and related research in cognitive psychology

A characteristic of the design process in all areas of design is the use of a number of different types of drawings. The different types of drawings are associated with different stages of the process with one type, the relatively unstructured and ambiguous sketch, occurring early in the process. Designers place great emphasis on the sketch often because it is thought to be associated with innovation and creativity. Because of this emphasis researchers have also begun to focus on the sketch and its role in design. The first aim of this paper is to collect together and review the results of this research and to relate it to similar research that has looked at the role of drawings in problem solving in other disciplines. Recently, however, researchers in the design area have begun to relate their work to a number of areas of research in cognitive psychology and cognitive science. This work provides theoretical frameworks, experimental methodologies and a considerable body of research results that are of great potential importance to design research. The second aim of this paper is to review three of these areas, working memory, imagery reinterpretation and mental synthesis, and to examine their implications for design research generally but with a particular emphasis on the role of sketching in design.