Soft classification for sub-pixel land cover extraction

With increasing resolution of the remotely sensed data the problems of images contaminated by mixed pixels arc frequent. Conventional classification techniques often produce erroneous results when applied to images dominated by mixed pixels. This may load to unrealistic representation of land cover, thereby, affecting efficient planning, management and monitoring of natural resources. Consequently, soft classification techniques providing sub-pixel land cover information may have to be utilised. From a range of soft classification techniques, the present study focuses on the utility of conventional maximum likelihood classifier and linear mixture modelling for sub-pixel. land cover classifications. The accuracy of the soft classifications has been assessed using distance measures and correlation co-efficient. The results show that linear mixture modelling has produced accuracies comparable to maximum likelihood classifier. Besides this the correlations between actual land cover proportions and proportions from linear mixture modelling, though not strong, arc statistically significant at 95% level of confidence. It has also been observed that the normalised likelihoods of maximum likelihood classifier also show strong correlations with the actual land cover proportions on ground and therefore has the potential to be used as a soft classification technique.     

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.     

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。     

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.     

The analysis of SPOT-5 characteristics on land cover Classification

<正>KnowledgeaboutlandcoverandlandusehasbecomeincreasinglyimportantastheNationplanstoovercometheproblemsofuncontrolleddevelopment,deterioratingenvironmentalquality,lossofprimeagriculturallandsetc.Landuseandlandcoverdataareneededintheanalysisofenvironmentalprocessesandproblemstoknowiflivingconditionsandstandardsaretobeimprovedormaintainedatcurrentlevels.     

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.     

Land use and land cover change detection with Landsat MSS and SPOT HRV data in Hong Kong

The objective of this paper is to map urban expansion in Hong Kong from 1979 to 1987 with a Landsat MSS and a SPOT HRV data. The data were radiometrically calibrated and geometrically registered. Three change detection techniques were applied. First, image overlay was used to enhance change areas visually. Second, a standardized principal components analysis was performed to yield minor components which were change related vectors. A thresholding technique was employed to separate the areas of changes from those of no-change. A binary change mask was created. Third, a post-classification comparison was merged with the change mask to identify the nature of specific land use and land cover changes. Major land development in the city can be easily detected and mapped with these techniques.     

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.     

Classifiers vs. input variables—The drivers in image classification for land cover mapping

The study investigates the performance of image classifiers for landscape-scale land cover mapping and the relevance of ancillary data for the classification success in order to assess and to quantify the importance of these components in image classification. Specifically tested are the performance of maximum likelihood classification (MLC), artificial neural networks (ANN) and discriminant analysis (DA) based on Landsat7 ETM+ spectral data in combination with topographic measures and NDVI. ANN produced high accuracies of more than 75% also with limited input information, while MLC and DA produced comparable results only by incorporating ancillary data into the classification process. The superiority of ANN classification was less pronounced on the level of the single land cover classes. The use of ancillary data generally increased classification accuracy and showed a similar potential for increasing classification accuracy than the selection of the classifier. Therefore, a stronger focus on the development of appropriate and optimised sets of input variables is suggested. Also the definition and selection of land cover classes has shown to be crucial and not to be simply adaptable from existing land cover class schemes. A stronger research focus towards discriminating land cover classes by their typical spectral, topographic or seasonal properties is therefore suggested to advance image classification.     

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

The analysis and classification of land cover is one of the principal applications in terrestrial remote sensing. Due to the seasonal variability of different vegetation types and land surface characteristics, the ability to discriminate land cover types changes over time. Multi-temporal classification can help to improve the classification accuracies, but different constraints, such as financial restrictions or atmospheric conditions, may impede their application. The optimisation of image acquisition timing and frequencies can help to increase the effectiveness of the classification process. For this purpose, the Feature Importance (FI) measure of the state-of-the art machine learning method Random Forest was used to determine the optimal image acquisition periods for a general (Grassland, Forest, Water, Settlement, Peatland) and Grassland specific (Improved Grassland, Semi-Improved Grassland) land cover classification in central Ireland based on a 9-year time-series of MODIS Terra 16 day composite data (MOD13Q1). Feature Importances for each acquisition period of the Enhanced Vegetation Index (EVI) and Normalised Difference Vegetation Index (NDVI) were calculated for both classification scenarios. In the general land cover classification, the months December and January showed the highest, and July and August the lowest separability for both VIs over the entire nine-year period. This temporal separability was reflected in the classification accuracies, where the optimal choice of image dates outperformed the worst image date by 13% using NDVI and 5% using EVI on a mono-temporal analysis. With the addition of the next best image periods to the data input the classification accuracies converged quickly to their limit at around 8–10 images. The binary classification schemes, using two classes only, showed a stronger seasonal dependency with a higher intra-annual, but lower inter-annual variation. Nonetheless anomalous weather conditions, such as the cold winter of 2009/2010 can alter the temporal separability pattern significantly. Due to the extensive use of the NDVI for land cover discrimination, the findings of this study should be transferrable to data from other optical sensors with a higher spatial resolution. However, the high impact of outliers from the general climatic pattern highlights the limitation of spatial transferability to locations with different climatic and land cover conditions. The use of high-temporal, moderate resolution data such as MODIS in conjunction with machine-learning techniques proved to be a good base for the prediction of image acquisition timing for optimal land cover classification results.     

Evaluation of image fusion methods using PALSAR,RADARSAT-1 and SPOT images for land use/ land cover classification

This research aimed to explore the fusion of multispectral optical SPOT data with microwave L-band ALOS PALSAR and C-band RADARSAT-1 data for a detailed land use/cover mapping to find out the individual contributions of different wavelengths. Many fusion approaches have been implemented and analyzed for various applications using different remote sensing images. However, the fusion methods have conflict in the context of land use/cover (LULC) mapping using optical and synthetic aperture radar (SAR) images together. In this research two SAR images ALOS PALSAR and RADARSAT-1 were fused with SPOT data. Although, both SAR data were gathered in same polarization, and had same ground resolution, they differ in wavelengths. As different data fusion methods, intensity hue saturation (IHS), principal component analysis, discrete wavelet transformation, high pass frequency (HPF), and Ehlers, were performed and compared. For the quality analyses, visual interpretation was applied as a qualitative analysis, and spectral quality metrics of the fused images, such as correlation coefficient (CC) and universal image quality index (UIQI) were applied as a quantitative analysis. Furthermore, multispectral SPOT image and SAR fused images were classified with Maximum Likelihood Classification (MLC) method for the evaluation of their efficiencies. Ehlers gave the best score in the quality analysis and for the accuracy of LULC on LULC mapping of PALSAR and RADARSAT images. The results showed that the HPF method is in the second place with an increased thematic mapping accuracy. IHS had the worse results in all analyses. Overall, it is indicated that Ehlers method is a powerful technique to improve the LULC classification.     

A variable precision rough set approach to knowledge discovery in land cover classification

This paper presents a granular computing approach to spatial classification and prediction of land cover classes using rough set variable precision methods. In particular, it presents an approach to characterizing large spatially clustered data sets to discover knowledge in multi-source supervised classification. The evidential structure of spatial classification is founded on the notions of equivalence relations of rough set theory. It allows expressing spatial concepts in terms of approximation space wherein a decision class can be approximated through the partition of boundary regions. The paper also identifies how approximate reasoning can be introduced by using variable precision rough sets in the context of land cover characterization. The rough set theory is applied to demonstrate an empirical application and the predictive performance is compared with popular baseline machine learning algorithms. A comparison shows that the predictive performance of the rough set rule induction is slightly higher than the decision tree and significantly outperforms the baseline models such as neural network, naïve Bayesian and support vector machine methods.     

Selection of spectral band combination for land cover/land use classification using a brightness value overlapping index (BVOI)

A simply defined, accurate and efficient criterion of selecting a spectral-band combination for improved land use/land cover classification using remote sensing data is discussed. Results indicate that Brightness Value Overlapping Index (BVOI) is very effective in measuring the degree of overlap in brightness values among land cover types and in selecting suitable spectral-band combination for landuse classification. The results of BVOI are also compared with the results of another band-combination selecting index - Optimum Index Factor (OIF).     

Suitable sampling technique in contextual fuzzy c-means classification of remotely sensed data for land cover mapping

In the past, researchers tried hard classification techniques with contextual information to improve classification results. While modelling the spatial contextual information for hard classifiers using Markov Random Field it has been found that the Metropolis algorithm is easier to program and it performs better when compared with the Gibbs sampler. In this study, it has been found that in the case of soft contextual classification, the Metropolis algorithm fails to sample from a random field efficiently and the Gibbs sampler performs better than the Metropolis algorithm, due to the high dimensionality of the soft classification outputs.     

An adaptive unimodal subclass decomposition (AUSD) learning system for land use and land cover classification using high-resolution remote sensing

Land use and land cover classification is an important application of remote-sensing images. The performances of most classification models are largely limited by the incompleteness of the calibration set and the complexity of spectral features. It is difficult for models to realize continuous learning when the study area is transferred or enlarged. This paper proposed an adaptive unimodal subclass decomposition (AUSD) learning system, which comprises two-level iterative learning controls: The inner loop separates each class into several unimodal Gaussian subclasses; the outer loop utilizes transfer learning to extend the model to adapt to supplementary calibration set collected from enlarged study areas. The proposed model can be efficiently adjusted according to the variability of spectral signatures caused by the increasingly high-resolution imagery. The classification result can be obtained using the Gaussian mixture model by Bayesian decision theory. This AUSD learning system was validated using simulated data with the Gaussian distribution and multi-area SPOT-5 high-resolution images with 2.5-m resolution. The experimental results on numerical data demonstrated the ability of continuous learning. The proposed method achieved an overall accuracy of over 90% in all the experiments, validating the effectiveness as well as its superiority over several widely used classification methods.     

Reducing landscape heterogeneity for improved land use and land cover (LULC) classification across the large and complex Ethiopian highlands

This paper presents a land use and land cover (LULC) classification approach that accounts landscape heterogeneity. We addressed this challenge by subdividing the study area into more homogeneous segments using several biophysical and socio-economic factors as well as spectral information. This was followed by unsupervised clustering within each homogeneous segment and supervised class assignment. Two classification schemes differing in their level of detail were successfully applied to four landscape types of distinct LULC composition. The resulting LULC map fulfills two major requirements: (1) differentiation and identification of several LULC classes that are of interest at the local, regional, and national scales, and (2) high accuracy of classification. The approach overcomes commonly encountered difficulties of classifying second-level classes in large and heterogeneous landscapes. The output of the study responds to the need for comprehensive LULC data to support ecosystem assessment, policy formulation, and decision-making towards sustainable land resources management.     

基于知识的分层综合分类法在土地利用/土地覆盖遥感信息提取中的应用

土地利用/土地覆盖数据的获取是研究LUCC的重要基础工作。随着遥感技术的飞速发展,通过遥感提取土地利用/土地覆盖专题信息已成为LUCC研究必不可少的一步。目前遥感专题信息提取水平相对滞后于遥感数据获取,为了提高遥感数据在土地利用/土地覆盖的应用,寻找一种较好的、具有相对适用性的方法是目前遥感应用的一个迫切要求。本文比较了目前比较常用的几种土地利用/土地覆盖遥感信息提取方法,分别以西部干旱区(柴达木盆地)和东部地区(鄱阳湖地区)为例,提出在GIS支持下基于知识的分层综合分类方法,并通过和其他几种常用方法进行比较分析,得到如下结果:在自然环境相差较大的柴达木盆地和鄱阳湖地区,采用了GIS支持下基于知识的分层综合分类方法的提取精度均要比单独采用最大似然法、纹理分析法、神经网络分类法等方法的总体精度高出25%,Kappa系数高出0.2。由此可以说明了该方法对于土地利用/土地覆盖专题信息的提取是可行的,同时它也具有一定的适用性。     

Fusion of HJ1B and ALOS PALSAR data for land cover classification using machine learning methods

Image classification from remote sensing is becoming increasingly urgent for monitoring environmental changes. Exploring effective algorithms to increase classification accuracy is critical. This paper explores the use of multispectral HJ1B and ALOS (Advanced Land Observing Satellite) PALSAR L-band (Phased Array type L-band Synthetic Aperture Radar) for land cover classification using learning-based algorithms. Pixel-based and object-based image analysis approaches for classifying HJ1B data and the HJ1B and ALOS/PALSAR fused-images were compared using two machine learning algorithms, support vector machine (SVM) and random forest (RF), to test which algorithm can achieve the best classification accuracy in arid and semiarid regions. The overall accuracies of the pixel-based (Fused data: 79.0%; HJ1B data: 81.46%) and object-based classifications (Fused data: 80.0%; HJ1B data: 76.9%) were relatively close when using the SVM classifier. The pixel-based classification achieved a high overall accuracy (85.5%) using the RF algorithm for classifying the fused data, whereas the RF classifier using the object-based image analysis produced a lower overall accuracy (70.2%). The study demonstrates that the pixel-based classification utilized fewer variables and performed relatively better than the object-based classification using HJ1B imagery and the fused data. Generally, the integration of the HJ1B and ALOS/PALSAR imagery can improve the overall accuracy of 5.7% using the pixel-based image analysis and RF classifier.