共查询到20条相似文献，搜索用时 281 毫秒
1.
2.
史磊 《测绘与空间地理信息》2012,(7):156-159,163
以辽阳地区为试验区,采用ETM多波段和SPOT全色遥感影像为主要信息源。利用遥感图像处理软件ERDAS对影像进行几何配准、图像增强等一系列处理。利用HIS变换和主成分分析法进行影像融合试验,对比分析融合结果,融合后影像同时具有多光谱和高分辨率的特性,提高了影像解译度。参考国家分类标准,选取农村、水体、旱地、林地、菜地、城市和水田七大类进行分类试验。采用监督分类的方法对主成分变换融合后的影像进行土地利用分类。最后,在ArcGIS软件中进行矢量化处理,制作土地利用分类图。使用该方法制作的辽阳地区土地利用分类图,可以满足一般用户对土地利用分类图的要求。 相似文献
3.
土地资源是一个国家或地区赖以生产和发展的重要物质基础，利用3S技术和数字化测绘技术对土地资源进行定期调查与动态监测，逐渐成为人们加强对土地资源的合理利用问题研究的重要手段。以1∶5万湖北省武汉市、陕西省韩城市土地覆盖/土地利用图的制作为试验样本，利用遥感和数字图像处理领域的前沿技术——基于Erdas Imagine 8.4的非监督分类、监督分类，辅以人工干预方法，以遥感影像数据（Landsat 7）为数据源，对土地资源的定期调查与快速监测的工艺流程与方法进行了较为深入的研究探讨。 相似文献
4.
基于SOM神经网络的城市土地覆盖遥感分类研究 总被引：1，自引：0，他引：1
土地覆盖及其变化的研究作为区域及全球环境变化研究所需的极为重要的地表参数,是遥感应用分析的主要内容之一。以往所采用的遥感分类方法主要针对侧重于土地社会属性的土地利用类型的分类研究且很难获得理想的精度。本文在非监督的自组织映射神经网络的基础上进行了一定的改进,构建了有监督的神经网络模型,以湖南省长沙市主城区的土地自然属性为侧重点,对其土地覆盖进行分类。实验结果表明:利用本文所使用的方法得到的分类结果,其总体精度和Kappa系数均高于传统的分类方法得出来的分类结果。 相似文献
5.
6.
用SPOT-VGT数据制作中国2000年度土地覆盖数据 总被引：13，自引：1，他引：13
土地覆盖是自然环境与人类活动相互作用的中心,准确而现势性强的土地覆盖数据是科学研究、资源管理和环境监测等应用的基础资料。该研究作为欧盟联合研究中心2000年全球土地覆盖计划(GLC2000)的一部分,利用2000年的1km空间分辨率的SPOT-4VGTS10数据与DEM、积温和降水等通过AHP方法合成的自然因子数据,采用FAO的土地覆盖分类系统(LCCS),通过非监督分类方法制作中国2000年的土地覆盖图。研究结果表明,在HANTS方法去云处理的基础上,结合气候分区,利用一年内每10天最大值合成的NDVI时间序列自然因子数据集可对除干旱区外大部分地区进行很好的分类,对干旱区则采用8月下旬的VGT原始数据取代NDVI数据参加分类,可达到较好的分类结果。 相似文献
7.
详细阐述了应用全国1km土地利用/覆盖25层分层栅格数据合并生成单层土地利用/覆盖图的方法。通过对初始合成结果的归类、合并和空间平滑,有效减少了图像上像元分布零散的情况,突出了土地利用的空间总体分布格局。具体应用表明,这种处理方法得到的土地利用/覆盖图能够满足水文、地学分析的要求。 相似文献
8.
土地利用/覆盖分类通常是利用地物的波谱反射特征进行监督或非监督分类,分类结果由于"同物异谱、异物同谱"现象的存在,往往分类精度不高。而植被指数和地表温度作为表征地表覆盖状况的生物物理参数,已成功用于宏观尺度的土地利用/覆盖分类,使得分类结果有所提高,而对于区域尺度的土地利用/覆盖分类却少见报道。本文充分利用TM数据的多光谱特征,从中提取了植被指数NDVI、地表温度Ts、温度植被角度TVA和温度植被距离TVD这四种分类特征进行监督分类,通过对7种组合方案(反射率波段组合、NDVI与反射率波段组合、Ts与反射率波段组合、NDVI与Ts和反射率波段组合、TVA与反射率波段组合、TVD与反射率波段组合、TVA与TVD和反射率波段组合)的分类结果进行比较,得出以下结论:①NDVI、Ts、NDVI和Ts、TVD作为分类特征参与到多波段地表反射率影像分类中,能够提高分类精度,而TVA、TVA和TVD的加入却没有改善分类结果;②总体分类精度受到训练样本与检验样本比例的影响。 相似文献
9.
乔卫芳 《测绘与空间地理信息》2011,(6):14-17
土地利用信息对于土地利用的动态监测、非点源污染物的迁移、生态环境保护规划和决策都有重要意义。以河南境内的丹江口水库汇水区2007年9月份的TM影像为数据源,结合遥感图像处理软件,利用监督分类方法对该区域的土地利用进行分类,最后利用ArcGIS软件对提取的土地利用信息制作出土地利用专题图。 相似文献
10.
土地覆盖/土地利用（LC/LU）调查已经成为开展土地利用动态变化预测、自然灾害防治及土地利用规划、土地管理和环境保护的一项关键的基础性工作,受到广泛关注和重视。随着遥感技术和各种地学分析模型的发展和成熟,利用遥感技术获得的影像数据对区域的LC/LU情况进行土地覆盖分类和监测,成为一种最为迅速可靠和理想有效的手段。本文综合论述了遥感地学智能图解模型支持下的LC/LU分类,并以西部测图工程1∶50 000无图区塔里木东部地区为试验对象,采用多平台遥感数据和辅助地理信息软件,进行了LC/LU遥感应用分类研究。 相似文献
11.
Inderjit Singh 《Journal of the Indian Society of Remote Sensing》1988,16(4):43-52
LANDSAT-TM has been evaluated for forest cover type and landuse classification in subtropical forests of Kumaon Himalaya (U.P.) Comparative evaluation of false colour composite generated by using various band combinations has been made. Digital image processing of Landsat-TM data on VIPS-32 RRSSC computer system has been carried out to stratify vegetation types. Conventional band combination in false colour composite is Bands 2, 3 and 4 in Red/Green/Blue sequence of Landsat TM for landuse classification. The present study however suggests that false colour combination using Landsat TM bands viz., 4, 5 and 3 in Red/Green/Blue sequence is the most suitable for visual interpretation of various forest cover types and landuse classes. It is felt that to extract full information from increased spatial and spectral resolution of Landsat TM, it is necessary to process the data digitally to classify land cover features like vegetation. Supervised classification using maximum likelihood algorithm has been attemped to stratify the forest vegetation. Only four bands are sufficient enough to classify vegetaton types. These bands are 2,3,4 and 5. The classification results were smoothed digitaly to increase the readiability of the map. Finally, the classification carred out using digital technique were evaluated using systematic sampling design. It is observed that forest cover type mapping can be achieved upto 80% overall mapping accuracy. Monospecies stand Chirpine can be mapped in two density classes viz., dense pine (<40%) with more than 90% accuracy. Poor accuracy (66%) was observed while mapping pine medium dense areas. The digital smoothening reduced the overall mapping accuracy. Conclusively, Landsat-TM can be used as operatonal sensor for forest cover type mapping even in complex landuse-terrain of Kumaon Himalaya (U.P.) 相似文献
12.
S. Sudhakar R. K. Das D. Chakraborty B. K. Bardhan Roy A. K. Raha P. Shukla 《Journal of the Indian Society of Remote Sensing》1994,22(1):21-29
Indian Remote Sensing Satellite-1A (IRS-1A) LISS-II data of 24th Nov., 1988 was analysed digitally to differentiate three density classes viz. dense/closed forest, open forest and degraded forest within each vegetation type in the district, Jalpaiguri, West Bengal. Stratification approach was used to classify separately forest cover into pure sal forests, mixed forests, riverine forests along with man-made sal/teak plantations. In this approach the forested and non-forested areas were classified separately through supervised classification techniques using maximum likelihood algorithm using VAX 11/780 based VIPS-32 Image Processing software. Later the two classified outputs were composited to provide entire area of the district. The forest cover of the district was 1420.89 sq. km, (22.82 percent). Other broad landuse/landcover dominant in the district include agricultural areas.(45.20 percent) and tea gardens (10.49 percent). The accuracy of the classified output was estimated to be 90 percent for forested areas and 85 percent in case of other landuse/landcover classes. 相似文献
13.
In the present study, forest type classification using Landsat TM False Colour Composite (FCC) bands 2, 3, 4 has been evaluated for mapping highly heterogeneous forest environment of Western Ghats (Kerala). Visual interpretation of Landsat TM FCC has been carried out to identify bioclimatic vegetation types. For accuracy estimation maps prepared from 1∶15,000 scale black-and-white aerial photographs have been used as ground check data. For comparison aerial photomap classes have been aggregated to match with Landsat-TM-derived map. The classification accuracy of ten major bioclimatic and landcover types was estimated using systematic sampling procedure. The overall classification accuracy of the forest types for the study area was 88.33%. 相似文献
14.
S. Sudhakar Arvind Kumar M. L. Arrawatia S. Sengupta 《Journal of the Indian Society of Remote Sensing》1994,22(3):155-168
Remote sensing techniques have been applied to classify tour density classes within each of the forest type along with other major landuse/landcover classes in the East district, Sikkim using IRS-1A LISS II satellite data pertaining to the period of November, 1988. The shadow problem in rugged terrain and difficulty in acquiring cloud free data for different seasons pose problems to achieve considerable mapping accuracy. In the present study, the forests of the district were delineated through supervised classification techniques using maximum likelihood algorithm into five forest types as sal forests, subtropical broad-leaved forests, Himalayan wet temperate forests, Rhododendron forests and alpine forests. The alpine forests were further stratified into two categories as moist alpine scrub and dry alpine scrub. The statistical data obtained from the present study shows that 55.47 percent of the total geographical area of the East district was under forest cover. An overall accuracy of more than 85 percent in correctly delineating forest classes was achieved. 相似文献
15.
S. Sudhakar G. Sridevi I. V. Ramana V. Venkateswara Rao A. K. Raha 《Journal of the Indian Society of Remote Sensing》1999,27(4):217-224
The accuracy of three classification techniques namely Maximum likelihood, contextual and neural network for landuse/landcover with special emphasis on forest type mapping was evaluated in Jaldapara Wildlife Sanctuary area using IRS-1B LISS II data of Dec. 1994. The area was segregated into ten categories by using all the three classification techniques taking same set of training areas. The classification accuracy was evaluated from the error matrix of same set of training and validating pixels. The analysis showed that the neural net work achieved maximum accuracy of 95 percent, maximum likelihood algorithm with 91.06 percent and contextual classifier with 87.42 percent. It is concluded that the neural network classifier works better in heterogeneous and contextual in homogenous forestlands whereas the maximum likelihood is the best in both the conditions. 相似文献
16.
The Mumbai-Navi Mumbai cities (Bombay and New Bombay) are among the highest populated cities in the country. The population pressure has caused drastic landuse change in the last seventy years. Multi-date data from SOI topographical maps and Landsat TM digital data have been used to study the landuse change. The change has been quantified using A GIS It was observed that 55% reduction in forest/agricultural land, while a 300% increase in built-up land has taken place in the last seventy years. This has affected the natural drainage system of the cities, causing flooding during monsoons. The quantum of draînage basin area and stream length, in the ten basins which drain the area, under influence of built-up land was found by using a map overlay of the drainage network map and landuse map of 1994. The results shed light on the extent of drainage network disruption within these two neighbouring cities. 相似文献
17.
Priyom Roy J. Chandramohan K. Vinod Kumar Arul Raj Mobina Shaik Vinod Bothale P. G. Diwakar 《Journal of the Indian Society of Remote Sensing》2017,45(4):667-672
The article outlines a procedure of pre-feasibility analysis of planned rural water supply pipeline grids in India. Usually, these type of pre feasibility studies prior to actual implementation, is carried out based on ground surveys and is time consuming. In this work, we use thematic spatial data, such as geomorphology and landuse–landcover along with digital elevation model (DEM) to carry out the pre-feasibility assessment of proposed pipeline grids. DEM generated from CartoSat-1 stereo data has been used to understand the possible topographic hindrances along the planned pipeline route and optimise the same. Further, topographic data also indicates the possible routes of gravity assisted flow. The geomorphology thematic data interpreted from Resourcesat-1 LISS III imagery is used to identify possible geomorphologic hindrances along the pipeline route. Similarly, landuse–landcover information derived from Resourcesat-2 LISS III images, was used to assess the land use/cover impact of the planed pipeline corridor. This has been demonstrated, in the current article using a hypothetical pipeline route. The activity can be carried in a specially designed geo-spatial interface in NRSC/ISRO Bhuvan geoportal. This type of assessment can prove to be time saving and cost effective at a pre-feasibility stage. 相似文献
18.
为研究我国首颗携带红边波段的高分六影像（GF-6）在林地与非林地上的识别贡献，本文选择复杂林地类型的安徽省黄山市作为研究区，采用特征优选（RFE）与随机森林（RF）相结合的方法开展了林地与非林地识别潜力研究。首先根据实地调查、Google Earth影像及林地"一张图"样本数据构建了样本库；然后基于DEM、多时相光谱特征、植被指数、红边指数等特征开展分类，并比较不同模型精度及不同变量的重要度。结果表明：GF-6红边信息对林地非林地识别较为重要，引入红边信息可将总体分类精度提升2%，其他新增波段及地形特征对林地与非林地识别贡献并不明显；多时相数据的运用相比单时相数据可整体提高林地类型的分类精度2.93%~4.1%，单时相分类结果6月最好，9月次之，12月最差；特征优选可以有效减少数据输入维数（46到15），并取得最高分类精度，在不牺牲精度的同时保证了运算数据量的减少且明确了不同变量的贡献，具有较强的应用意义。 相似文献
19.
To tackle the problems arising due to rapid urbanization, the urban planners need relevant data base. Since the conventional methods of data acquisition and processing ate not cost and time effective, introduction of new techniques is necessary. Application of satellite remote sensing is an alternative. Ia this paper attempt has been made to find out the usefulness of visual interpretation technique of satellite remote sensing data in the selection of new residential site. SPOT 1 HRV 1 MLA (FCC) date has been used to map existing landuse/landcover of Hisar town and its environs. Based on existing landuse/lsndcover conditions and evaluation of various suitability parameters like physiography, slope, drainage, availability of drinking water and wind direction, a new residential site has been selected. This study may be useful to the urban planners in the preparation of a comprehensive plan Df the town. 相似文献
20.
Rui Zhang Chengquan Huang Xiwu Zhan Huiran Jin Xiao-Peng Song 《International Journal of Digital Earth》2018,11(2):212-232
With the launch of the Joint Polar Satellite System (JPSS)/Suomi National Polar-orbiting Partnership (S-NPP) satellite in October 2011, many of the terrestrial remote sensing products generated from Moderate Resolution Imaging Spectroradiometer (MODIS), such as the global land cover map, have been inherited and expanded into the JPSS/S-NPP mission using the new Visible Infrared Imaging Radiometer Suite (VIIRS) data. In this study, an improved algorithm including the use of a new classifier support vector machines (SVM) classifier was proposed to produce VIIRS surface type maps. In addition to the new classification algorithm, a new post-processing strategy involving the use of new ancillary data to refine the classification output is implemented. As a result, the new global International Geosphere-Biosphere Programme (IGBP) map based on the 2014 VIIRS surface reflectance data was generated with a 78.5 ± 0.6% overall classification accuracy. The new map was compared to a previously delivered VIIRS surface type map, and to the MODIS land cover product. Validation results including the error matrix, overall accuracy, and the user’s and producer’s accuracy suggest the new global surface type map provides similar classification accuracy compared to the old VIIRS surface type map, with higher accuracy achieved in agricultural types. 相似文献