| 1. | Studies on the purification of training samples in supervised classification by mode filtering
利用众数滤波对监督分类训练样本纯化的研究 |
| 2. | The image of nanchuan in 2000 was interpreted using a multi - extracting method combining supervised classification with non - supervised classification
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。 |
| 3. | The image of nanchuan in 2000 was interpreted using a multi - extracting method combining supervised classification with non - supervised classification
摘要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。 |
| 4. | Supported by the analysis and advance process to the geographical data using gis software , the paper discusses the question that whether the accuracy of bayes supervised classification will be improved considering the influence of the prior probability
本文尝试利用gis软件对地理数据进行分析和预处理,对考虑先验概率是否提高bayes监督分类精度这一问题作了探讨。 |
| 5. | The proportion based on the assistant data is used as the prior probability to replace the prior value in the conventional supervised classification ; the farther iterative prior probability is applied into classifying progress on landsat tm image
由辅助数据中计算各类别面积比率作为先验概率,替换传统监督分类中的先验值,并进一步对先验概率进行迭代,最后利用改进的先验概率对landsattm影像进行分类实验。 |
| 6. | Taken the northern slopes of the tianshan mountains as the research area , the multi - source remote sensing data were applied to investigate and classify in rangeland resources types based on supervised classification method ( mlc ) combined with " 3s " technical platform
摘要利用多源遥感数据和" 3s "技术平台，采用监督分类法对天山北坡山体垂直带内草地资源进行分类并获取资源分布格局图，探讨多源遥感数据在草地资源类型分类中的应用程度和发展前景。 |
| 7. | The paper establishes a ecological transect , with a length of 90 km and width of 16 km , utilizing the part of tm data on 16th august 1998 , from harbin to the natural secondary forests in maoershan , heilongjiang province . with supervised classification , the tm data which had been corrected and enhanced via erdas , combining the data of gps in the field , was classified by seven types including : residential area , glebe , paddy field
本论文利用1998年8月16日的tm卫星数据的一部分，设置从黑龙江省哈尔滨市到帽儿山天然次生林区，长90km ，宽16km的生态研究样带。通过用erdas对卫星数据的校正、图像增强等处理，结合gps野外实地调查数据，进行有监督分类。共分为7种类型：居民点、旱田、水田、河流、灌丛、阔叶林、针叶林，并建立了卫星影像分类解译标志。 |
| 8. | The paper has made detailed observation by the existing apparatus and the field observation stations . based on the image and the vector database of the yutian oasis , the study has obtained the precise coordinates of investigation points by gps technique , and overlapped them with the images . after classifying the images with the maximum likelihood supervised classification method , we import the result into cis software , and analyze the yutian oasis changes about land cover " s quantity , quality and spatial position from 1976 to 2001
本文利用现有仪器设备和野外观测网站进行详细观测，在建立于田绿洲图像库和矢量数据库的基础上，运用gps技术取得野外考察样点的精确坐标并与研究区各时期影像叠加，对影像进行了最大似然法监督分类，并将分类结果转入gis软件处理，全面分析了1976年至2001年该绿洲的土地覆盖类型数量、质量与空间上的变化。 |
| 9. | The result indicates that the precision of msavi method is 79 . 6 % , higher than that of supervised classification and unsupervised classification . such precision is able to meet the requirement of monitoring on grassland desertification at large scale based remote sensing data . all the study is based on tm images on 11th august 1987 and 9th august 2001 . the grassland desertification in the middle part of naiman of inner mongolia was taken as a detailed case study to discuss the discipline and driving forces of the dynamic of the grassland desertification during two periods
采用上述研究方法，利用1987年8月11日和2001年8月9日两时相的tm数据，对奈曼旗中部十个乡镇的草地沙化动态进行了分析，结果表明研究区草地严重沙化的总体趋势得到控制，并且开始逆转，生态环境建设已经产生了成效，但还存在着局部的恶化趋势，草地沙化发展与逆转并存，草地沙化防治的形势依然严峻。 |
| 10. | An attribute means clustering binary tree is presented in this paper . the binary tree is extends naturally and turns to be a supervised classification method . the orl database is used to evaluate the proposed method . the performance of the attribute means clustering binary tree used in face recognition is compared with the standard eigenface approach and improves their performance much in the experiment
在无监督的属性聚类网络的基础上，提出了一种二叉树分类方法。此二叉树自然地在无监督聚类的基础上扩展开来，成为一有监督的分类方法。用orl人脸数据库做了测试，同标准的特征脸eigenface方法相比，识别率得到了较大的提高。 |
