共查询到20条相似文献，搜索用时 500 毫秒
1.
针对基于全天空极光图像的极光事件自动分类问题,提出一种基于方向能量二元编码重组表征的自动分类方法。首先,通过对多个方向上能量分解来描述极光事件中的局部纹理和各个方向上的运动信息,并且结合分块策略获得极光事件的全局形态信息;然后,借鉴一种二元编码重组的方式对多个方向能量进行融合,从而使得极光事件的表征具有同时表征局部纹理、全局形态和运动信息的能力。该表征方法完全不依赖于极光事件的长度,可用于表征不同持续时间的极光事件,并且不需要复杂的训练过程。利用最近邻和支撑向量机分类器分别对从中国北极黄河站拍摄到的极光图像中挑选的特定极光事件进行自动分类,结果表明,与其他两种典型的动态纹理描述方法相比,本文所提出的表征方法结合最近邻分类器,得到了最好的分类效果,能有效用于极光事件的分析,为海量数据中的极光事件自动分类提供了一种新方法。 相似文献
2.
以位于中国科学院内蒙古草原生态研究定位站灌丛化样地实验平台为研究区，基于低空无人机遥感影像，结合实地调查，开展草原灌丛遥感辨识方法研究。通过对灌丛、草地和裸地归一化植被指数（NDVI）的方差统计分析，确定了裸地与植被的分割阈值为-0.08，并使用该阈值提取植被覆盖区，然后分别利用面向对象的决策树（DT）、贝叶斯（Bayes）、K最邻近（KNN）、支持向量机（SVM）机器学习分类器进行灌丛辨识。研究表明：借助Estimation of Scale Parameter（ESP）最优分割尺度评价工具可以快速确定分割参数，获取灌丛、草地影像对象；利用特征空间优化工具选取了18个的对象特征，可以有效避免盲目选择而导致的计算量增大；通过对不同分类器分类结果的对比和样本数量敏感性实验得出：Bayes分类器精度稳定、无需设置参数，灌丛分类精度最高，总体精度和Kappa系数分别达到92%和0.83，结果与影像地物嵌合最好，能够精确识别单株灌丛；根据Bayes分类器分类结果统计得研究区灌丛盖度为14.74%，平均冠幅为0.6 m2，与样方调查结果基本一致。由于4种分类器的算法特征以及对训练样本数量的敏感性各不相同，因此选择合适的分类器还需根据具体影像的地物特征、空间分辨率和研究区范围来确定。 相似文献
3.
Object-oriented image classification has tremendous potential to improve classification accuracies of land use and land cover (LULC), yet its benefits have only been minimally tested in peer-reviewed studies. We aim to quantify the benefits of an object-oriented method over a traditional pixel-based method for the mixed urban–suburban–agricultural landscape surrounding Gettysburg, Pennsylvania. To do so, we compared a traditional pixel-based classification using maximum likelihood to the object-oriented image classification paradigm embedded in eCognition Professional 4.0 software. This object-oriented paradigm has at least four components not typically used in pixel-based classification: (1) the segmentation procedure, (2) nearest neighbor classifier, (3) the integration of expert knowledge, and (4) feature space optimization. We evaluated each of these components individually to determine the source of any improvement in classification accuracy. We found that the combination of segmentation into image objects, the nearest neighbor classifier, and integration of expert knowledge yields substantially improved classification accuracy for the scene compared to a traditional pixel-based method. However, with the exception of feature space optimization, little or no improvement in classification accuracy is achieved by each of these strategies individually. 相似文献
4.
地学应用中的遥感图像处理若干问题的分析 总被引：5，自引：3，他引：5
遥感技术在地理学应用中是如何从遥感影像上直观、准确的得到所需的信息,为本专业服务。文章从地学应用部门在进行遥感影像处理时遇到的几个问题:多光谱数据的选取与合成;多源信息的复合;新型图像分类器的应用;专题提取的精度等方面的进展作了分析。 相似文献
5.
针对多源遥感影像土地覆盖分类结果一致性与分类精度改进的要求,对两组中等空间分辨率的光学影像进行土地覆盖分类,以支持向量机分类结果为基础,采用Kappa统计量、双错误测量、Q统计量、相同错误率从不同角度评价了不同分类结果的一致性。实验表明,多源遥感数据分类结果总体上常规一致性程度较好,二值先验一致性程度尚可,错误一致性程度较小;不同土地覆盖类别的一致性程度并不相同,有的类别甚至出现不一致现象。提出组合法和替换法两种策略以综合数据优点、实现多传感器数据集成应用,能够有效提高分类精度。 相似文献
6.
为研究沙地信息提取的方法，采用基于CART决策树的面向对象方法，提取中卫市沙坡头区的沙地信息。首先对研究区进行多尺度分割和光谱差异分割得到对象层，然后选择合适的提取特征和训练样本点，最后输入选择的提取特征和样本点生成CART规则树，并对地物进行分类，提取出沙地信息。结果表明：采用面向对象的CART决策树方法提取沙地信息具有较高自动化程度和精确度，依此构建的CART决策树总体分类精度可达到77%，是最近邻分类结果的1.12倍，支持向量机分类结果的1.57倍，此外，NDBI（归一化裸露指数）、GSI（粒度指数）和SWIR 2（第七波段）均值可以成功的将沙地、戈壁和裸岩石砾地三个易混地物区分开来，是沙地提取过程中三个重要的特征指数。 相似文献
7.
无人机遥感在红树林资源调查中的应用 总被引：6，自引：0，他引：6
低空无人机（UAV,Unmanned Aerial Vehicles）遥感系统具有数据采集灵活、低成本且可快速获取超高分辨率影像的特色,是传统航空遥感和卫星遥感的重要补充。以广东省和广西壮族自治区交界处的英罗港港湾两侧为研究区域,将无人机遥感系统用于红树林资源的遥感调查,通过无人机航拍获取高分辨率影像,并且使用拼接的影像和目视解译方法提取红树林空间分布信息,进一步选择典型研究样地,采用面向对象的最近邻分类方法对红树林树种类型进行分类研究,并对比综述了无人机遥感和常规航空航天遥感技术对红树林资源调查监测的优缺点,无人机遥感系统非常适用于红树林资源调查。通过2 h 30 min的3架次无人机航飞工作,获取了研究区域25.29 km2的无人机影像,基于无人机影像和面向对象遥感分类方法提取的红树林空间分布信息精度超过了90%。未来无人机遥感系统将可成为调查和监测红树林资源的重要技术手段,可为相关管理部门对红树林资源的保护、管理、开发等方面的工作提供基础信息和技术支持。 相似文献
8.
基于多类型无人机数据的红树林遥感分类对比 总被引：2，自引：0，他引：2
使用固定翼无人机、消费级旋翼无人机和专业级旋翼无人机获取广东珠海淇澳岛红树林保护区多类型无人机遥感影像，使用基于面向对象分类的K-最近邻与随机森林分类器对研究区影像进行红树林树种精细分类和对比分析，并探讨了不同类型无人机平台在红树林资源调查应用中的优缺点。结果表明：1）固定翼无人机、消费级旋翼无人机和专业级旋翼无人机数据使用K-最近邻法的分类精度分别为：73.8%、72.8%和79.7%；使用随机森林法的分类精度分别为：81.1%、84.8%和89.3%。3种平台类型的无人机数据均适用于红树林精细分类研究，对于无人机红树林遥感数据，随机森林的分类方法优于K-最近邻方法。2）以拍摄面积与用时之比估算采集效率，固定翼无人机、消费级旋翼无人机和专业级旋翼无人机分别为0.036、0.013和0.003 km2/min。固定翼无人机的采集效率具有明显优势。3）固定翼无人机适合大范围红树林数据采集，要求较高；消费级旋翼无人机适于获取小范围精细数据，成本低且易学易用；专业级旋翼无人机适合搭载质量稍大的如成像光谱仪、LiDAR等专业传感器获取多源数据。最后给出了无人机在红树林遥感研究中的注意事项和建议。 相似文献
9.
Monitoring lava dome instabilities is crucial to efficiently monitor active dome building volcanoes. The Doppler radar technique provides a unique opportunity to gather information about the number of instability events occurring at the growing dome and about the dynamic processes that take place during different types of instabilities. So far, three different kinds of processes have been identified: sliding material, gravitational break-offs and explosive outbursts. In addition, Doppler radars provide rain measurements, which can be used to investigate possible correlations between rainfall and dome activity. Two radar systems have been installed at Merapi volcano in October 2001 and January 2005 to continuously monitor dome instabilities. Due to the large number of instability events that occur during times of high activity, manual processing and analysis of instability events is not practical for monitoring purposes. Therefore, an automatic classification system has been developed, which is capable of identifying different kinds of instabilities as well as rainfall. Two different kinds of classifier models have been applied: (1) neural network and (2) K-nearest-neighbour classifier model. Both classify Doppler spectra according to the underlying dynamic process, that is, rain, sliding material, gravitational break-off or explosive outburst. The classifiers are able to identify disturbances, which have no physical source, but are merely artefacts from the radar device itself. Because radar events are sequences of Doppler spectra, a rule set has been defined, which finally determines the event class. All classifiers have been trained and tested on independent data sets to estimate the classification performance. The overall classification rate is about 90 per cent. Discrimination of instabilities and non-volcanic events reaches about 98 per cent accuracy. 相似文献
10.
基于ASTER影像的近海水产养殖信息自动提取方法 总被引：5，自引：1，他引：5
水产养殖地已经成为海洋环境监测的热点目标之一。采用具有高光谱分辨率和较高空间分辨率(15m)的ASTER遥感影像,以九龙江河口地区为研究示范区,进行近海水产养殖信息的自动提取方法研究。结果表明,利用ASTER影像的光谱信息和水产养殖地的纹理结构信息,可以实现近海水产养殖地的自动提取。先利用监督分类方法提取混淆有其他水体的水产养殖信息,采用邻域分析来增强水产养殖地的空间纹理信息。通过综合监督分类和水产养殖地空间纹理增强的结果,在专家决策分类器中建立决策规则,进行水产养殖地的自动提取,提取的精度达93%。 相似文献
11.
Hexiang Bai Feng Cao M. Peter Atkinson Qian Chen Jinfeng Wang 《International journal of geographical information science》2020,34(10):2077-2114
ABSTRACT This paper proposes a new classification method for spatial data by adjusting prior class probabilities according to local spatial patterns. First, the proposed method uses a classical statistical classifier to model training data. Second, the prior class probabilities are estimated according to the local spatial pattern and the classifier for each unseen object is adapted using the estimated prior probability. Finally, each unseen object is classified using its adapted classifier. Because the new method can be coupled with both generative and discriminant statistical classifiers, it performs generally more accurately than other methods for a variety of different spatial datasets. Experimental results show that this method has a lower prediction error than statistical classifiers that take no spatial information into account. Moreover, in the experiments, the new method also outperforms spatial auto-logistic regression and Markov random field-based methods when an appropriate estimate of local prior class distribution is used. 相似文献
12.
John R. Dymond Paul G. Luckman 《International journal of geographical information science》2013,27(4):357-367
Abstract Rule-based classifiers are used regularly with geographical information systems to map categorical attributes on the basis of a set of numeric or unordered categorical attributes. Although a variety of methods exist for inducing rule-based classifiers from training data, these tend to produce large numbers of rules when the data has noise. This paper describes a method for inducing compact rule-sets whose classification accuracy can, at least in some domains, compare favourably with that achieved by larger less succinct rule-sets produced by alternative methods. One rule is induced for each output class. The condition list for this rule represents a box in n-dimensional attribute space, formed by intersecting conditions which exclude other classes. Despite this simplicity, the classifier performed well in the test application prediction of soil classes in the Port Hills, New Zealand, on the basis of regolith type and topographic attributes obtained from a digital terrain model. 相似文献
13.
14.
Calibrating a Land Parcel Cellular Automaton (LP-CA) for urban growth simulation based on ensemble learning 总被引：1，自引：0，他引：1
Yimin Chen 《International journal of geographical information science》2017,31(12):2480-2504
The reliability of raster cellular automaton (CA) models for fine-scale land change simulations has been increasingly questioned, because regular pixels/grids cannot precisely represent irregular geographical entities and their interactions. Vector CA models can address these deficiencies due to the ability of the vector data structure to represent realistic urban entities. This study presents a new land parcel cellular automaton (LP-CA) model for simulating urban land changes. The innovation of this model is the use of ensemble learning method for automatic calibration. The proposed model is applied in Shenzhen, China. The experimental results indicate that bagging-Naïve Bayes yields the highest calibration accuracy among a set of selected classifiers. The assessment of neighborhood sensitivity suggests that the LP-CA model achieves the highest simulation accuracy with neighbor radius r = 2. The calibrated LP-CA is used to project future urban land use changes in Shenzhen, and the results are found to be consistent with those specified in the official city plan. 相似文献
15.
Giles M. Foody 《International journal of geographical information science》2013,27(5):527-542
Abstract Remote sensing is an important source of land cover data required by many GIS users. Land cover data are typically derived from remotely–sensed data through the application of a conventional statistical classification. Such classification techniques are not, however, always appropriate, particularly as they may make untenable assumptions about the data and their output is hard, comprising only the code of the most likely class of membership. Whilst some deviation from the assumptions may be tolerated and a fuzzy output may be derived, making more information on class membership properties available, alternative classification procedures are sometimes required. Artificial neural networks are an attractive alternative to the statistical classifiers and here one is used to derive a fuzzy classification output from a remotely–sensed data set that may be post–processed with ancillary data available in a GIS to increase the accuracy with which land cover may be mapped. With the aid ancillary information on soil type and prior knowledge of class occurrence the accuracy of an artificial neural network classification was increased by 29–93 to 77–37 per cent. An artificial neural network can therefore be used generate a fuzzy classification output that may be used with other data sets in a GIS, which may not have been available to the producer of the classification, to increase the accuracy with which land cover may be classified. 相似文献
16.
基于空间索引的规则格网DTM内插算法研究 总被引：2，自引：0，他引：2
从离散点内插规则格网数字地形模型(DTM)方法的关键是如何提高待插点周围数据的搜索效率。该文针对离散点的空间分布特性,给出了基于网格分块和KD-Tree两种空间索引技术的规则格网内插方法。实验表明,这两种索引方法能显著提高搜索速度,算法内插效率较高。最后,在算法效率分析的基础上,对两种索引方法所适应的条件进行了讨论。 相似文献
17.
Lin Wan Zhou Huang Xia Peng Ran Li 《International journal of geographical information science》2018,32(11):2225-2246
Geo-tagged travel photos on social networks often contain location data such as points of interest (POIs), and also users’ travel preferences. In this paper, we propose a hybrid ensemble learning method, BAyes-Knn, that predicts personalized tourist routes for travelers by mining their geographical preferences from these location-tagged data. Our method trains two types of base classifiers to jointly predict the next travel destination: (1) The K-nearest neighbor (KNN) classifier quantifies users’ location history, weather condition, temperature and seasonality and uses a feature-weighted distance model to predict a user’s personalized interests in an unvisited location. (2) A Bayes classifier introduces a smooth kernel function to estimate a-priori probabilities of features and then combines these probabilities to predict a user’s latent interests in a location. All the outcomes from these subclassifiers are merged into one final prediction result by using the Borda count voting method. We evaluated our method on geo-tagged Flickr photos and Beijing weather data collected from 1 January 2005 to 1 July 2016. The results demonstrated that our ensemble approach outperformed 12 other baseline models. In addition, the results showed that our framework has better prediction accuracy than do context-aware significant travel-sequence-patterns recommendations and frequent travel-sequence patterns. 相似文献
18.
基于GF-1卫星数据的面向对象的民勤绿洲植被分类研究 总被引：1，自引：0，他引：1
以民勤绿洲为研究区,以GF-1遥感影像为数据源,采用面向对象的分类方法,结合分层技术,对影像逐级进行分类,以获取植被信息。根据归一化植被指数（NDVI）阈值区分植被与非植被,分割尺度为10;使用归一化水体指数（NDWI）阈值提取非植被中的水体,分割尺度为35;利用野外采样点获取的训练样本,将植被进一步分为耕地、林地和草地,分割尺度为25。总体分类精度达到83.02%,Kappa系数为0.745 1,比较基于象元的监督分类,其总体分类精度为69.37%,Kappa系数为0.497 0,表明面向对象的分类方法在干旱区绿洲植被信息的提取上较传统的基于象元的分类方法更有优势,分类精度更高。 相似文献
19.
Hexiang Bai Deyu Li Yong Ge Jinfeng Wang 《International journal of geographical information science》2019,33(2):240-268
When classical rough set (CRS) theory is used to analyze spatial data, there is an underlying assumption that objects in the universe are completely randomly distributed over space. However, this assumption conflicts with the actual situation of spatial data. Generally, spatial heterogeneity and spatial autocorrelation are two important characteristics of spatial data. These two characteristics are important information sources for improving the modeling accuracy of spatial data. This paper extends CRS theory by introducing spatial heterogeneity and spatial autocorrelation. This new extension adds spatial adjacency information into the information table. Many fundamental concepts in CRS theory, such as the indiscernibility relation, equivalent classes, and lower and upper approximations, are improved by adding spatial adjacency information into these concepts. Based on these fundamental concepts, a new reduct and an improved rule matching method are proposed. The new reduct incorporates spatial heterogeneity in selecting the feature subset which can preserve the local discriminant power of all features, and the new rule matching method uses spatial autocorrelation to improve the classification ability of rough set-based classifiers. Experimental results show that the proposed extension significantly increased classification or segmentation accuracy, and the spatial reduct required much less time than classical reduct. 相似文献
20.
东亚飞蝗生境的遥感分类——以河北省黄骅地区为例 总被引：1，自引：0，他引：1
东亚飞蝗生境的分类研究是东亚飞蝗监测和防治的一项重要基础工作。本文以河北省黄骅地区为研究区,基于两个时相的TM图像,采用三种遥感波段组合方案,以及最大似然分类和基于知识的分层分类两种分类方法,进行了东亚飞蝗生境的分类研究。结果表明,三种组合方案的分类总精度相差不大,其中加入图像纹理信息的最大似然分类法的分类总精度最高。但是,基于知识的分层分类法的分类精度在各单项生境类型之间相差较小,从而显示出该方法在应用上仍有一定的优越性。 相似文献