Efficient collection of training data for sub-pixel land cover classification using neural networks

Artificial neural networks (ANNs) are a popular class of techniques for performing soft classifications of satellite images. They have successfully been applied for estimating crop areas through sub-pixel classification of medium to low resolution images. Before a network can be used for classification and estimation, however, it has to be trained. The collection of the reference area fractions needed to train an ANN is often both time-consuming and expensive. This study focuses on strategies for decreasing the efforts needed to collect the necessary reference data, without compromising the accuracy of the resulting area estimates. Two aspects were studied: the spatial sampling scheme (i) and the possibility for reusing trained networks in multiple consecutive seasons (ii). Belgium was chosen as the study area because of the vast amount of reference data available. Time series of monthly NDVI composites for both SPOT-VGT and MODIS were used as the network inputs. The results showed that accurate regional crop area estimation (R² > 80%) is possible using only 1% of the entire area for network training, provided that the training samples used are representative for the land use variability present in the study area. Limiting the training samples to a specific subset of the population, either geographically or thematically, significantly decreased the accuracy of the estimates. The results also indicate that the use of ANNs trained with data from one season to estimate area fractions in another season is not to be recommended. The interannual variability observed in the endmembers’ spectral signatures underlines the importance of using up-to-date training samples. It can thus be concluded that the representativeness of the training samples, both regarding the spatial and the temporal aspects, is an important issue in crop area estimation using ANNs that should not easily be ignored.     

Multi-resolution integration of land cover for sub-pixel estimation of urban impervious surface and forest cover

Abstract

A methodology is presented for estimating percent coverage of impervious surface (IS) and forest cover (FC) within Landsat thematic mapper (TM) pixels of urban areas. High-resolution multi-spectral images from Quickbird (QB) play a key role in the sub-pixel mapping process by providing information on the spatial distributions of ISs and FCs at 2.4 m ground sampling intervals. Thematic classifications, also derived from the Landsat imagery, have then been employed to define relationships between 30 m Landsat-derived greenness values and percent IS and FC. By also utilizing land cover/land use classification derived from Landsat and defining unique relationships for urban sub-classes (i.e. residential, commercial/industrial, open land), confusion between impervious and fallow agricultural lands has been overcome. Test results are presented for Ottawa-Gatineau, an urban area that encompasses many aspects typical of the North American urban landscape. Multiple QB scenes have been acquired for this urban centre, thereby allowing us to undertake an in-depth study of the error budgets associated with the fractional inference process.     

Airborne MSS for land cover classification II

A basic methodology for land cover classification using airborne multispectral scanner (MSS) imagery is outlined. This includes waveband selection and radiometric calibration; correction for scan angle and atmosphere; training and classification and accuracy assessment. Refinements to this basic methodology include per‐field sampling and the addition of low‐pass filtering, image texture, prior probabilities and two dates of imagery.

For a study area in upland England, eight land covers were classified with a mean accuracy of 52.6 percent using the basic methodology. This was increased to 79.0 percent by using a suitability refined methodology. Per‐field sampling accounted for the largest proportion of this increase.     

Per-pixel and object-oriented classification methods for mapping urban land cover extraction using SPOT 5 imagery

To have sustainable management and proper decision-making, timely acquisition and analysis of surface features are necessary. Traditional pixel-based analysis is the popular way to extract different categories, but it is not comparable by the achievements that can be achieved through the object-based method that uses the additional characteristics of features in the process of classification. In this paper, three types of classification were used to classify SPOT 5 satellite image in mapping land cover; Support vector machine (SVM) pixel-based, SVM object-based and Decision Tree (DT) pixel-based classification. Normalised Difference Vegetation Index and the brightness value of two infrared bands (NIR and SWIR) were used in manually developed DT classification. The classification of the SVM (pixel based) was generated using the selected groups of pixels that represent the selected features. In addition, the SVM (object based) was implemented by using radial-based function kernel. The classified features were oil palm, rubber, urban area, soil, water and other vegetation. The study found that the overall classification of the DT was the lowest at 69.87% while those of SVM (pixel based) and SVM (object based) were 76.67 and 81.25%, respectively.     

Texture classification of Mediterranean land cover

Maximum likelihood (ML) and artificial neural network (ANN) classifiers were applied to three Landsat Thematic Mapper (TM) image sub-scenes (termed urban, agricultural and semi-natural) of Cukurova, Turkey. Inputs to the classifications comprised (i) spectral data and (ii) spectral data in combination with texture measures derived on a per-pixel basis. The texture measures used were: the standard deviation and variance and statistics derived from the co-occurrence matrix and the variogram. The addition of texture measures increased classification accuracy for the urban sub-scene but decreased classification accuracy for agricultural and semi-natural sub-scenes. Classification accuracy was dependent on the nature of the spatial variation in the image sub-scene and, in particular, the relation between the frequency of spatial variation and the spatial resolution of the imagery. For Mediterranean land, texture classification applied to Landsat TM imagery may be appropriate for the classification of urban areas only.     

MODIS土地覆盖分类的尺度不确定性研究

以空间异质性较强的枯水期鄱阳湖为研究区,以搭载于同一卫星平台、具有同一观测时间和较高空间分辨率的ASTER数据为参照,分析研究了MODIS数据在土地覆盖分类中由空间尺度带来的不确定性。首先基于MODIS三角权重函数,建立了从ASTER到MODIS的尺度转换方法;然后对不同空间分辨率的数据进行土地覆盖分类,并基于误差矩阵和线性模型分析了MODIS土地覆盖分类结果的误差来源。结果表明,空间分辨率和光谱分辨率与成像方式这两类因素对MODIS与ASTER分类结果差异的贡献比例约为(6.6—11.2):2;MODIS像元尺度对研究区水体的分类不确定性影响较低,而对森林的不确定性影响可达63%。由此可见,在基于MODIS数据的土地覆盖分类研究中,空间尺度所产生的不确定性是比较显著的。这些研究结果对于土地覆盖分类及变化检测、尺度效应和景观生态学不确定性研究,有积极的参考意义。     

多源数据的土地覆被样本自动提取

随着遥感数据获取能力的不断增强,自动化程度已经成为大尺度遥感土地覆被分类面临的关键问题。然而,现有训练样本的人工选取方法成为制约土地覆被分类自动化的瓶颈。本文以河南、贵州两省为研究区,提出一种基于多源数据的土地覆被样本自动提取方法,以构建适用于大尺度的土地覆被自动分类。首先,以2010年1∶10万土地利用数据CHINALC和30 m分辨率全球土地覆被数据Globle Land30为样本数据源;然后,利用空间一致性分析及异质性分析确定样本初选区域;最后,通过样本提纯去除无效样本。结果表明:(1)应用多源数据的土地覆被样本自动提取方法获得的分类产品总体分类精度高于人工样本提取方法制作的全球土地覆被产品MCD12Q1。(2)与单源样本自动提取方法相比,应用多源数据的土地覆被样本自动提取方法,可获得更好的分类稳定性。综上,多源数据的土地覆被样本自动提取方法可在保证精度的同时,提升土地覆被分类的自动化程度。     

Fusion of PolSAR and PolInSAR data for land cover classification

The main research goal of this study is to investigate the complementarity and fusion of different frequencies (L- and P-band), polarimetric SAR (PolSAR) and polarimetric interferometric (PolInSAR) data for land cover classification. A large feature set was derived from each of these four modalities and a two-level fusion method was developed: Logistic regression (LR) as ‘feature-level fusion’ and the neural-network (NN) method for higher level fusion. For comparison, a support vector machine (SVM) was also applied. NN and SVM were applied on various combinations of the feature sets.     

A kernel functions analysis for support vector machines for land cover classification

Information about the Earth's surface is required in many wide-scale applications. Land cover/use classification using remotely sensed images is one of the most common applications in remote sensing, and many algorithms have been developed and applied for this purpose in the literature. Support vector machines (SVMs) are a group of supervised classification algorithms that have been recently used in the remote sensing field. The classification accuracy produced by SVMs may show variation depending on the choice of the kernel function and its parameters. In this study, SVMs were used for land cover classification of Gebze district of Turkey using Landsat ETM+ and Terra ASTER images. Polynomial and radial basis kernel functions with their estimated optimum parameters were applied for the classification of the data sets and the results were analyzed thoroughly. Results showed that SVMs, especially with the use of radial basis function kernel, outperform the maximum likelihood classifier in terms of overall and individual class accuracies. Some important findings were also obtained concerning the changes in land use/cover in the study area. This study verifies the effectiveness and robustness of SVMs in the classification of remotely sensed images.     

面向对象的沿海地区土地利用/覆被信息提取研究

土地利用/覆被(LUC)可为土地资源领域相关研究提供基础数据.本文构建了面向对象的LUC分类方法,并以沿海特殊土地类型区连云港市为例,应用Landsat 8影像开展了实证研究。结果表明:①总体分类精度达到85.06%,总体Kappa系数为0.83,超过了0.7的最低允许判别精度;②该方法可以有效地减少研究区因南北部区域耕地植被覆盖度不同导致的错分现象,并可以用于盐田与滩涂信息的提取工作;③该方法既可为研究区土地利用相关研究提供符合精度要求的数据.也可为其他沿海地区进行土地利用/覆被信息提取工作提供参考和借鉴。     

Effect of seasonal spectral variations on land cover classification

The supervised classification (Maximum likelihood) on three dates of IRS (LISS III) satellite data was performed to study the effect of seasonal spectral variation on land cover classification for the study area falling in the Solan district of Himachal Pradesh at latitude 30° 50’ N to 31° ’N and longitude 77° 00’ E to 77° 15’ E. It was found that the summer dataset was better with overall classification accuracy of 76% as compared to winter and spring dataset with classification accuracy of 49 and 46%, respectively.     

高精度地表覆盖数据优化分割的土地利用分类

针对土地利用类型多样、特征易混淆和高分辨率遥感影像信息海量、人工提取费时费力等问题,该文以北京二号卫星影像为数据源,采用高精度地表覆盖数据优化分割的面向对象分析方法、无地表覆盖数据辅助分类的面向对象分析方法,运用朴素贝叶斯、CART决策树、随机森林和K最邻近分类器,开展武功县土地利用分类,并对分类结果进行精度评估.结果 表明:①与无地表覆盖数据辅助分类方法相比,高精度地表覆盖数据优化分割的面向对象分类方法,在精度方面有较大的提升,其分类总体精度提高18.73％,Kappa系数提高0.21;②随机森林对于土地类型多样的影像对象具有较好的识别能力,获得较高的总体精度(95.3％)和Kappa系数(0.94).研究表明一种利用高精度地表覆盖数据优化影像分割的土地利用分类方法具有更好的可行性和鲁棒性.     

遥感图像土地覆盖分类中多源特征数据选择研究

多源特征数据可以提高遥感图像的分类精度,选择合适的特征数据十分重要。利用基尼指数对多尺度纹理信息、主成分变换前三分量、地形数据等特征进行选择,选出最佳特征子集。利用支持向量机、神经网络分类法、最大似然法分别对全部特征数据和最佳特征子集结合多光谱数据进行分类。实验结果表明:基尼指数可以有效地对多源特征数据进行选择,特征选择可以提高分类器效率,提高分类精度。     

地表覆盖成果质量的模糊综合评价模型与方法

本文针对地理国情监测地表覆盖成果质量合理评价问题,应用多因素模糊综合评价理论与方法,设计了一套基于模糊综合评价法的地理国情监测地表覆盖成果质量评价模型与方法,并选取我国北方27个县级测区的地理国情监测地表覆盖成果质量检查数据进行了试验验证。试验结果表明,相比最小值法、加权平均法等常规质量评价方法,基于模糊综合评价法的成果质量评价结果更为客观、合理,可为自然资源统一调查监测中的地表覆盖成果等新型测绘地理信息成果质量评价提供技术参考。     

The analysis of SPOT-5 characteristics on land cover Classification

<正>KnowledgeaboutlandcoverandlandusehasbecomeincreasinglyimportantastheNationplanstoovercometheproblemsofuncontrolleddevelopment,deterioratingenvironmentalquality,lossofprimeagriculturallandsetc.Landuseandlandcoverdataareneededintheanalysisofenvironmentalprocessesandproblemstoknowiflivingconditionsandstandardsaretobeimprovedormaintainedatcurrentlevels.     

极化SAR参数优化与光学波谱相结合的面向对象土地覆盖分类

提出一种基于极化参数优化的面向对象分类方法。该方法结合光学和SAR数据,有效提高了对地物的识别能力。本文方法的关键在于:在■分解中,使用光学影像指导SAR影像选择同质点,使其更精确地估计极化参数并结合光学波谱信息作为输入特征;使用面向对象的分类方法,仅将光学影像作为分割输入,避免SAR噪声引起的分割错误。以美国Bakersfield地区的Sentinel-1/2数据为例,确定7种地物类型,对比分析不同输入与不同分类器对分类结果的影响。研究表明,优化输入参数在纹理丰富区域能够有效提高分类精度;面向对象的分类结果更加稳定并较好地维持地表几何特征;改进分类方法较传统分类方法总体精度提高了近10%,达到92.6%。     

A Boosted Genetic Fuzzy Classifier for land cover classification of remote sensing imagery

A Boosted Genetic Fuzzy Classifier (BGFC) is proposed in this paper, for land cover classification from multispectral images. The model comprises a set of fuzzy classification rules, which resemble the reasoning employed by humans. Fuzzy rules are generated in an iterative fashion, incrementally covering subspaces of the feature space, as directed by a boosting algorithm. Each rule is able to select the required features, further improving the interpretability of the obtained model. After the rule generation stage, a genetic tuning stage is employed, aiming at improving the cooperation among the fuzzy rules, thus increasing the classification performance attained after the first stage. The BGFC is tested using an IKONOS multispectral VHR image, in a lake-wetland ecosystem of international importance. For effective classification, we consider advanced feature sets, containing spectral and textural feature types. Comparative results with well-known classifiers, commonly employed in remote sensing tasks, indicate that the proposed system is able to handle multi-dimensional feature spaces more efficiently, effectively exploiting information from different feature sources.     

面向对象的高分辨率遥感影像土地覆盖信息提取

利用高分辨率影象提取土地覆盖信息的关键技术在于如何利用丰富的纹理信息来弥补光谱信息的不足。面向对象的图像分类技术改变了传统的面向像素的分类技术:(1)用来解译图像的信息并不在单个像元中,而是在图像对象和其相互关系中;采用多分辨率对象分割方法生成图像对象,提高了分类信息的信噪比;基于对象的分类技术不同于纯粹的光谱信息分类,图像对象还包含了许多的可用于分类的一些其他特征:形状、纹理、相互关系、上下关系等信息。面向对象的土地覆盖分类结果与传统分类方法相比,其特征提取算子更加地适合于几何信息和结构信息丰富的高分辨率图像的自动识别分类。     

Selection of LiDAR geometric features with adaptive neighborhood size for urban land cover classification

LiDAR has been an effective technology for acquiring urban land cover data in recent decades. Previous studies indicate that geometric features have a strong impact on land cover classification. Here, we analyzed an urban LiDAR dataset to explore the optimal feature subset from 25 geometric features incorporating 25 scales under 6 definitions for urban land cover classification. We performed a feature selection strategy to remove irrelevant or redundant features based on the correlation coefficient between features and classification accuracy of each features. The neighborhood scales were divided into small (0.5–1.5 m), medium (1.5–6 m) and large (>6 m) scale. Combining features with lower correlation coefficient and better classification performance would improve classification accuracy. The feature depicting homogeneity or heterogeneity of points would be calculated at a small scale, and the features to smooth points at a medium scale and the features of height different at large scale. As to the neighborhood definition, cuboid and cylinder were recommended. This study can guide the selection of optimal geometric features with adaptive neighborhood scale for urban land cover classification.