对遥感影像做了详细分析和预处理,在此基础上得到较高精度的分类结果。
Based on the detailed analysis and pretreatment to the remote sensing imagery, we obtained relatively high precision classification result.
利用遥感影像进行土地利用分类有多种方法和指标。
The method and index of using remote sense image to classify the land use are various.
BP神经网络近年来广泛地应用于遥感影像分类中。
BP neural network is widely used for classification of remote sensing image data nowadays.
传统统计模式识别方法进行遥感影像分类时要求数据服从正态分布且难以加入地理辅助数据。
The traditional statistical classifier is suitable in making RS image classification in normal distribution and unsuitable in doing with the data in discrete distribution, such as the geographic data.
遥感已广泛应用于森林动态监测,遥感影像实物分类统计法为森林覆盖动态监测提供了可能。
Remote sensing has being applied broadly to forest dynamic monitoring, real object classification statistical method offers the feasibility for forest cover dynamic monitoring.
提高计算机遥感影像的分类精度,是遥感应用中研究的主要问题之一。
To improve remotely sensed imagery classification accuracy is one of the main topics in the field of remote sensing application research.
最后通过利用ERSSAR数据和TM影像进行融合分析,证明该方法在遥感图像自动分类中有很好的应用前景。
At the end, it is demonstrated that evidential reasoning has extensive applications in the classification of remote sensing images through the fusion analysis of ERS SAR and TM image.
遥感影像分类是遥感定量化分析的重要手段,遥感影像融合是提高分类正确率的有效途径之一。
Remote sensing image classification is an important means for quantified remote sensing image analysis, and remote sensing image fusion can effectively improve the accuracy of image classification.
最佳特征影像组合的选择是决定遥感影像信息提取与影像分类效果的关键环节之一。
Selection of optimal feature combinations is one of the key procedures for remotely sensed image classification and information abstraction.
实验结果表明,本文给出的高光谱遥感影像优化分类波段组合选择方法是非常有效的。
The experiment results indicate that the optimal classification bands combination selecting approach supplied in this paper is quite effective.
然后,在遥感影像分类实验中,借助样本数量与波段数目的关系,验证了理论分析的结果。
Then, an experiment of remote sensing image classification is carried out to verify the authenticity based on the relations between samples and bands.
目前遥感影像分类的常用模型和算法有统计学方法、神经网络、贝叶斯等。
Current remote sensing image classification models and algorithms commonly used statistical methods, neural networks, Bayesian and so on.
此外,该算法对隐藏了机密信息后的伪遥感影像的各种应用,如边缘检测和影像分类等均没有影响。
Furthermore this algorithm has no influence on such applications as edge detection and image classification of the disguised remote sensing image which has hidden the secrete information.
着重介绍了在进行遥感影像处理过程中所用到遥感影像辐射增强、计算机分类等的处理技术。
The point is about introduction of Highlighted in remote sensing image process used radiation to enhance remote sensing image, computer classification process technology.
高光谱遥感影像具有丰富的光谱信息,在地物分类识别方面具有明显的优势。
The hyperspectral remote sensing image is rich in spectrum information, so it can be better to carry on the ground targets classification.
把影像的空间信息融入分类决策,提出了一种基于证据理论与神经网络的遥感影像分类方法。
The spatial information of the image and evidence theory is applied to classification of remote sensing image based on neural networks.
纹理分析是提高遥感影像分类精度的重要手段之一。
Texture analysis has become an important means for improving the accuracy of remote sensing image classification.
在基于小波的纹理分类算法的基础上,提出了逐点特征加权和活动窗口算法,使小波纹理分析能够用于高分辨率遥感影像的分类。
This paper discusses the shortage of conventional algorithms of texture classification based on wavelet transform, presents two improved approaches of point feature weighting and smart windows.
景观分类是利用遥感影像特征解译石漠化强度和分布面积所必不可少的;
The first category is necessary to use remote images to interpret the degree and distribution of karst rocky desertification area.
由于传统遥感影像分类方法存在不足,因而采用神经网络算法进行遥感影像分类研究。
This paper describes the problem in the BP neural network approach and the approach of BP neural network based on vector information to the classification of remote sensing images.
实验证明,中巴资源卫星影像较好地实现喀斯特地区大比例尺土地利用分类,完全可以替代国外遥感影像TM而运用于喀斯特山区土地利用调查中。
It is proved that CBERS can preferably realize land use classification in karst area with big scale and, can substitute national image TM and can be applied for land use investigation in karst area.
利用监督分类和非监督分类相结合的分层提取分类方法对南川市2000年遥感影像进行解译。
The image of Nanchuan in 2000 was interpreted using a multi-extracting method combining supervised classification with non-supervised classification.
为了提高遥感影像分类精度,从抽象级和测量级的两个层次出发,提出混合多分类器结合算法。
To enhance the accuracy of image classification, proposed hybrid multiple classifier combination method from abstract level and measurement level.
因此,进行多分类器组合研究,探讨其在遥感影像自动分类中的应用,具有重要的理论与实践意义。
Therefore, it is theoretically and practically significant to study the method of combining multiple classifiers and explore its application in automatic classification of remote sensing images.
本项目的顺利开展,对于解决遥感影像中不确定信息分类问题具有较高的理论价值和良好的应用前景。
Smooth implementation of this project, for solving uncertain information in remote sensing image classification has a high theoretical value and a good prospect.
于是,有些学者将面向对象信息提取技术运用到遥感影像的分类中,大大提高了高分辨率遥感影像的分类精度。
Thus, some scholars use object-oriented information extraction technology to classify the remote sensing image, greatly increased the accuracy of high-resolution remote sensing image classification.
该方法及其思想不仅可用于去除云层和阴影对遥感图像质量的影响,而且也可用于其他图像处理中,如影像的割补、分类后处理等。
These methods and ideas can be used not only to remove the influence of cloud and its shadow on the quality of remote image hut also to process other images, such as patching and recoding images.
传统的基于像素光谱信息分类的方法在对这些高分辨率的遥感影像分类时显得力不从心,所得到的精确度远远达不到生产的要求。
Traditional pixel-based classification method can not give a satisfied performance for High Resolution Imagery. Its accuracy of classification is far from productive demand.
并在不同滤波器长度下,对22幅遥感地貌纹理影像进行了分类试验,获得了较高的分类正确率。
The classification experiment had been carried out for 22 relief images for different length of filtering. And high accuracy was obtained.
面对数量激增、包含信息日趋复杂的遥感影像,如何快速有效地自动分类已成为遥感领域亟待解决的问题。
The amount of remotely data images increases rapidly, and the information that the images contain becomes more and more complicated.
应用推荐