Crop classification from full-year fully-polarimetric L-band UAVSAR time-series using the Random Forest algorithm

Accurate and timely information on the distribution of crop types is vital to agricultural management, ecosystem services valuation and food security assessment. Synthetic Aperture Radar (SAR) systems have become increasingly popular in the field of crop monitoring and classification. However, the potential of time-series polarimetric SAR data has not been explored extensively, with several open scientific questions (e.g. the optimal combination of image dates for crop classification) that need to be answered. In this research, the usefulness of full year (both 2011 and 2014) L-band fully-polarimetric Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) data in crop classification was fully investigated over an agricultural region with a heterogeneous distribution of crop categories. In total, 11 crop classes including tree crops (almond and walnut), forage crops (grass, alfalfa, hay, and clover), a spring crop (winter wheat), and summer crops (corn, sunflower, tomato, and pepper), were discriminated using the Random Forest (RF) algorithm. The SAR input variables included raw linear polarization channels as well as polarimetric parameters derived from Cloude-Pottier (CP) and Freeman-Durden (FD) decompositions. Results showed clearly that the polarimetric parameters yielded much higher classification accuracies than linear polarizations. The combined use of all variables (linear polarizations and polarimetric parameters) produced the maximum overall accuracy of 90.50 % and 84.93 % for 2011 and 2014, respectively, with a significant increase of approximately 8 percentage points compared with linear polarizations alone. The variable importance provided by the RF illustrated that the polarimetric parameters had a far greater influence than linear polarizations, with the CP parameters being much more important than the FD parameters. The most important acquisitions were the images dated during the peak biomass stage (July and August) when the differences in structural characteristics between most crops were the largest. At the same time, the images in spring (April and May) and autumn (October) also contributed to the crop classification since they respectively provided unique information for discriminating fruit crops (almond and walnut) as well as summer crops (corn, sunflower, and tomato). As a result, the combined use of only four acquisitions (dated May, July, August, and October for 2011 and April, June, August, and October for 2014) was adequate to achieve a nearly-optimal overall accuracy. In light of the promising classification accuracies demonstrated in this research, it becomes increasingly viable to provide accurate and up-to-date crops inventories over large areas based solely on multitemporal polarimetric SAR.     

Mapping post-fire forest regeneration and vegetation recovery using a combination of very high spatial resolution and hyperspectral satellite imagery

Careful evaluation of forest regeneration and vegetation recovery after a fire event provides vital information useful in land management. The use of remotely sensed data is considered to be especially suitable for monitoring ecosystem dynamics after fire. The aim of this work was to map post-fire forest regeneration and vegetation recovery on the Mediterranean island of Thasos by using a combination of very high spatial (VHS) resolution (QuickBird) and hyperspectral (EO-1 Hyperion) imagery and by employing object-based image analysis. More specifically, the work focused on (1) the separation and mapping of three major post-fire classes (forest regeneration, other vegetation recovery, unburned vegetation) existing within the fire perimeter, and (2) the differentiation and mapping of the two main forest regeneration classes, namely, Pinus brutia regeneration, and Pinus nigra regeneration. The data used in this study consisted of satellite images and field observations of homogeneous regenerated and revegetated areas. The methodology followed two main steps: a three-level image segmentation, and, a classification of the segmented images. The process resulted in the separation of classes related to the aforementioned objectives. The overall accuracy assessment revealed very promising results (approximately 83.7% overall accuracy, with a Kappa Index of Agreement of 0.79). The achieved accuracy was 8% higher when compared to the results reported in a previous work in which only the EO-1 Hyperion image was employed in order to map the same classes. Some classification confusions involving the classes of P. brutia regeneration and P. nigra regeneration were observed. This could be attributed to the absence of large and dense homogeneous areas of regenerated pine trees in the study area.     

Spatial application of Random Forest models for fine-scale coastal vegetation classification using object based analysis of aerial orthophoto and DEM data

High spatial resolution mapping of natural resources is much needed for monitoring and management of species, habitats and landscapes. Generally, detailed surveillance has been conducted as fieldwork, numerical analysis of satellite images or manual interpretation of aerial images, but methods of object-based image analysis (OBIA) and machine learning have recently produced promising examples of automated classifications of aerial imagery. The spatial application potential of such models is however still questionable since the transferability has rarely been evaluated.We investigated the potential of mosaic aerial orthophoto red, green and blue (RGB)/near infrared (NIR) imagery and digital elevation model (DEM) data for mapping very fine-scale vegetation structure in semi-natural terrestrial coastal areas in Denmark. The Random Forest (RF) algorithm, with a wide range of object-derived image and DEM variables, was applied for classification of vegetation structure types using two hierarchical levels of complexity. Models were constructed and validated by cross-validation using three scenarios: (1) training and validation data without spatial separation, (2) training and validation data spatially separated within sites, and (3) training and validation data spatially separated between different sites.Without spatial separation of training and validation data, high classification accuracies of coastal structures of 92.1% and 91.8% were achieved on coarse and fine thematic levels, respectively. When models were applied to spatially separated observations within sites classification accuracies dropped to 85.8% accuracy at the coarse thematic level, and 81.9% at the fine thematic level. When the models were applied to observations from other sites than those trained upon the ability to discriminate vegetation structures was low, with 69.0% and 54.2% accuracy at the coarse and fine thematic levels, respectively.Evaluating classification models with different degrees of spatial correlation between training and validation data was shown to give highly different prediction accuracies, thereby highlighting model transferability and application potential. Aerial image and DEM-based RF models had low transferability to new areas due to lack of representation of aerial image, landscape and vegetation variation in training data. They do, however, show promise at local scale for supporting conservation and management with vegetation mappings of high spatial and thematic detail based on low-cost image data.     

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.     

面向对象的无人机遥感影像岩溶湿地植被遥感识别

以广西桂林会仙喀斯特国家湿地公园为研究区,以无人机航摄影像为数据源,综合利用面向对象的影像分析技术、随机森林算法、阈值分类方法和Boruta全相关特征变量选择算法进行岩溶湿地植被的遥感识别。结果表明:针对不同特征变量对岩溶湿地遥感识别的贡献率而言,光谱特征(DOM>DSM)>纹理特征(DOM>DSM)>几何特征>上下文变量;两个航摄影像数据集的总体分类精度都在85%以上,Kappa系数也高于0.85。本文研究结果对基于高空间分辨率无人机可见光影像的岩溶湿地植被遥感识别在特征变量选择、分割参数选择及方法选择方面具有一定的借鉴意义。     

The Rotation Forest algorithm and object-based classification method for land use mapping through UAV images

This study aims to test the performance of the Rotation Forest (RTF) algorithm in urban and rural areas that have similar characteristics using unmanned aerial vehicle (UAV) images to produce the most up-to-date and accurate land use maps. The performance of the RTF algorithm was compared to other ensemble methods such as Random Forest (RF) and Gentle AdaBoost (GAB) for object-based classification. RGB bands and other variables (i.e. ratio, mean, standard deviation, ... etc.) were also used in classification. The accuracy assessments showed that the RTF method, with 92.52 and 91.29% accuracies, performed better than the RF (2 and 4%) and GAB (5 and 8%) methods in urban and rural areas, respectively. The significance of differences in classification methods was also analysed using the McNemar test. Consequently, this study shows the success of the RTF algorithm in the object-based classification of UAV images for land use mapping.     

Individual tree crown segmentation in tropical peat swamp forest using airborne hyperspectral data

Abstract

Individual tree crown segmentation is important step for deriving various information for fine-scale analysis of ecological process. However, only several studies have applied tree crown segmentation in tropical forest ecosystems, especially in mixed peat swamp forests. In this study, hyperspectral data were used to detect changes in the biochemical and biophysical characteristics, which are important factors for tree crown segmentation. Principal Component Analysis method was performed to investigate its influence on crown segmentation. Visually Selected PCs, 160 PCs and 160 Spectral Bands image were used and two segmentation techniques; Watershed Transformation and Region Growing segmentation were applied on those images. The highest accuracy was achieved for the crown segmentation is using Region Growing segmentation, based on 1:1 measurement, D value and RMSE value. The results obtained from 160 PCs image using region growing algorithm shows better accuracy with D value of 0.2 (80% accuracy, 20% error) and RMSE of 9.9 m².     

Object-based crop classification using multi-temporal SPOT-5 imagery and textural features with a Random Forest classifier

In this study, an object-based image analysis (OBIA) approach was developed to classify field crops using multi-temporal SPOT-5 images with a random forest (RF) classifier. A wide range of features, including the spectral reflectance, vegetation indices (VIs), textural features based on the grey-level co-occurrence matrix (GLCM) and textural features based on geostatistical semivariogram (GST) were extracted for classification, and their performance was evaluated with the RF variable importance measures. Results showed that the best segmentation quality was achieved using the SPOT image acquired in September, with a scale parameter of 40. The spectral reflectance and the GST had a stronger contribution to crop classification than the VIs and GLCM textures. A subset of 60 features was selected using the RF-based feature selection (FS) method, and in this subset, the near-infrared reflectance and the image acquired in August (jointing and heading stages) were found to be the best for crop classification.     

Mapping the distributions of C3 and C4 grasses in the mixed-grass prairies of southwest Oklahoma using the Random Forest classification algorithm

The objective of this paper is to demonstrate a new method to map the distributions of C₃ and C₄ grasses at 30 m resolution and over a 25-year period of time (1988–2013) by combining the Random Forest (RF) classification algorithm and patch stable areas identified using the spatial pattern analysis software FRAGSTATS. Predictor variables for RF classifications consisted of ten spectral variables, four soil edaphic variables and three topographic variables. We provided a confidence score in terms of obtaining pure land cover at each pixel location by retrieving the classification tree votes. Classification accuracy assessments and predictor variable importance evaluations were conducted based on a repeated stratified sampling approach. Results show that patch stable areas obtained from larger patches are more appropriate to be used as sample data pools to train and validate RF classifiers for historical land cover mapping purposes and it is more reasonable to use patch stable areas as sample pools to map land cover in a year closer to the present rather than years further back in time. The percentage of obtained high confidence prediction pixels across the study area ranges from 71.18% in 1988 to 73.48% in 2013. The repeated stratified sampling approach is necessary in terms of reducing the positive bias in the estimated classification accuracy caused by the possible selections of training and validation pixels from the same patch stable areas. The RF classification algorithm was able to identify the important environmental factors affecting the distributions of C₃ and C₄ grasses in our study area such as elevation, soil pH, soil organic matter and soil texture.     

A support vector machine classifier based on a new kernel function model for hyperspectral data

The kernel function is a key factor to determine the performance of a support vector machine (SVM) classifier. Choosing and constructing appropriate kernel function models has been a hot topic in SVM studies. But so far, its implementation can only rely on the experience and the specific sample characteristics without a unified pattern. Thus, this article explored the related theories and research findings of kernel functions, analyzed the classification characteristics of EO-1 Hyperion hyperspectral imagery, and combined a polynomial kernel function with a radial basis kernel function to form a new kernel function model (PRBF). Then, a hyperspectral remote sensing imagery classifier was constructed based on the PRBF model, and a genetic algorithm (GA) was used to optimize the SVM parameters. On the basis of theoretical analysis, this article completed object classification experiments on the Hyperion hyperspectral imagery of experimental areas and verified the high classification accuracy of the model. The experimental results show that the effect of hyperspectral image classification based on this PRBF model is apparently better than the model established by a single global or local kernel function and thus can greatly improve the accuracy of object identification and classification. The highest overall classification accuracy and kappa coefficient reached 93.246% and 0.907, respectively, in all experiments.     

基于随机森林的地理要素面向对象自动解译方法

面向地理对象影像分析(GEOBIA)技术取得了显著的进展,代表了遥感影像解译的发展范式,其主要目标是发展智能化分析方法。随机森林机器学习方法是一种相对新的、数据驱动的非参数分类方法,具有自动特征优选、自动模型构建等优势,为智能化分析提供了有效手段。充分利用GEOBIA及随机森林机器学习的优势,提出了基于随机森林的地理要素面向对象自动解译方法,阐述了随机森林面向对象分类方法的技术流程,为设计和实现该方法提供了详细指导,有助于指导用户优选特征和构建分类模型。通过与支持向量机分类的对比实验证明,该方法可以自动进行特征优选及分类模型的构建,利用较少的特征得到较高的分类精度,在不损失性能的前提下减少了计算量和内存使用,能够为大范围、大区域地理要素自动解译提供先验知识及自动化的手段。     

面向对象规则和支持向量机的天宫一号高光谱影像分类

传统的高光谱分类方法通常基于单一像元的光谱或纹理特征,很少考虑地物空间结构信息与空间相关特征.本文将面向对象规则与基于像元的分类进行融合,利用对象的空间结构特征和光谱特征进行混合分类,旨在克服像元层次分类的不足.本文尝试性的提出了两种混合分类方法:(1)基于分形网络演化的多尺度分割支持向量机分类(2)基于多层分水岭分割的SVM分类,并将这两种方法应用到天宫一号高光谱数据上.结果表明:基于面向对象规则的混合分类方法有效地提高了分类精度,不仅能够改善同谱异物现象,而且解决分类结果中地物破碎的问题.     

Wetland classification in Newfoundland and Labrador using multi-source SAR and optical data integration

A vast portion of Newfoundland and Labrador (NL) is covered by wetland areas. Notably, it is the only province in Atlantic Canada that does not have a wetland inventory system. Wetlands are important areas of research because they play a pivotal role in ecological conservation and impact human activities in the province. Therefore, classifying wetland types and monitoring their changes are crucial tasks recommended for the province. In this study, wetlands in five pilot sites, distributed across NL, were classified using the integration of aerial imagery, Synthetic Aperture Radar, and optical satellite data. First, each study area was segmented using the object-based method, and then various spectral and polarimetric features were evaluated to select the best features for identifying wetland classes using the Random Forest algorithm. The accuracies of the classifications were assessed by the parameters obtained from confusion matrices, and the overall accuracies varied between 81% and 91%. Moreover, the average producer and user accuracies for wetland classes, considering all pilot sites, were 71% and 72%, respectively. Since the proposed methodology demonstrated high accuracies for wetland classification in different study areas with various ecological characteristics, the application of future classifications in other areas of interest is promising.     

结合深度学习的高光谱与多源遥感数据融合分类

高光谱数据具有丰富的光谱特征,但是其空间分辨率相对较低.一些遥感数据具有与高光谱数据互补的优势,例如提供更精细的空间信息的高空间分辨率数据和具有高度信息的激光雷达LiDAR(Light Detection and Ranging)数据.通过将高光谱数据与多源遥感数据进行融合,可以弥补高光谱数据空间分辨率相对较低,空间特...     

机载激光雷达及高光谱的森林乔木物种多样性遥感监测

利用机载LiDAR和高光谱数据并结合37个地面调查样本数据,基于结构差异与光谱变异理论,通过相关分析法分别筛选了3个最优林冠结构参数和6个最优光谱指数,在单木尺度上利用自适应C均值模糊聚类算法,在神农架国家自然保护区开展森林乔木物种多样性监测,实现了森林乔木物种多样性的区域成图。研究结果表明,(1)基于结合形态学冠层控制的分水岭算法可以获得较高精度的单木分割结果(R~2=0.88,RMSE=13.17,P0.001);(2)基于LiDAR数据提取的9个结构参数中,95%百分位高度、冠层盖度和植被穿透率为最优结构参数,与Shannon-Wiener指数的相关性达到R~2=0.39—0.42(P0.01);(3)基于机载高光谱数据筛选的16个常用的植被指数中,CRI、OSAVI、Narrow band NDVI、SR、Vogelmann index1、PRI与Shannon-Wiener指数的相关性最高(R~2=0.37—0.45,P0.01);(4)在研究区,利用以30 m×30 m为窗口的自适应模糊C均值聚类算法可预测的最大森林乔木物种数为20,物种丰富度的预测精度为R~2=0.69,RMSE=3.11,Shannon-Wiener指数的预测精度为R~2=0.70,RMSE=0.32。该研究在亚热带森林开展乔木物种多样性监测,是在区域尺度上进行物种多样性成图的重要实践,可有效补充森林生物多样性本底数据的调查手段,有助于实现生物多样性的长期动态监测及科学分析森林物种多样性的现状和变化趋势。     

高光谱-LiDAR多级融合城区地表覆盖分类

城市地区地表覆盖分类在城市研究中是一个十分重要的方向。遥感作为获取地物物理属性的一种重要技术手段,已初步应用于分类研究中。然而,随着城镇化的不断推进,城市内部地物类型越来越复杂,单一的遥感影像已无法满足城区地表覆盖分类中高精度的要求。高光谱影像和LiDAR数据能够分别表征地物的光谱信息及高程而被广泛应用。因此,根据两者之间互补的优势,本文提出了基于高光谱影像和LiDAR数据多级融合的城区地表覆盖分类方法。首先对两幅影像分别进行特征提取,将提取到的光谱、空间及高程信息进行层叠实现特征级融合。对得到的特征影像的所有像素点进行分类,然后利用LiDAR点云数据提取的建筑物掩膜,对非建筑物部分进行分类,再次实现特征级融合,以此改善建筑物区域与非建筑物区域的混淆。然后将未使用掩膜得到的分类结果与利用掩膜得到的分类结果进行投票实现决策级融合。最后利用条件随机场模型对分类结果进行后处理操作,达到平滑图像去除噪声点的目的。     

面向高光谱影像分类的显著性特征提取方法

针对高光谱影像分类问题,提出了一种显著性特征提取方法。首先,利用超像素分割算法将高光谱影像3个相邻波段分割为若干个小区域。然后,基于分割得到的小区域计算反映不同区域的显著性特征。最后,沿着光谱方向采用大小为3、步长为1的滑窗法获得所有波段的显著性特征。进一步将提取的显著性特征与光谱特征进行结合,并将结合后的特征输入到支持向量机中进行分类。利用Pavia大学、Indian Pines和Salinas 3组高光谱影像数据进行分类试验。试验结果表明,与传统的空间特征提取方法和基于卷积神经网络的高光谱影像分类方法相比,提取的显著性特征能够获得更高的高光谱影像分类精度,且结合光谱特征能够进一步提高分类精度。     

Segmentation-based classification of hyperspectral imagery using projected and correlation clustering techniques

A partitional clustering-based segmentation is used to carry out supervised classification for hyperspectral images. The main contribution of this study lies in the use of projected and correlation partitional clustering techniques to perform image segmentation. These types of clustering techniques have the capability to concurrently perform clustering and feature/band reduction, and are also able to identify different sets of relevant features for different clusters. Using these clustering techniques segmentation map is obtained, which is combined with the pixel-level support vector machines (SVM) classification result, using majority voting. Experiments are conducted over two hyperspectral images. Combination of pixel-level classification result with the segmentation maps leads to significant improvement of accuracies in both the images. Additionally, it is also observed that, classified maps obtained using SVM combined with projected and correlation clustering techniques results in higher accuracies as compared to classified maps obtained from SVM combined with other partitional clustering techniques.     

基于支持向量回归的高光谱影像目标探测

高光谱影像目标探测可视为一个分类问题,本文通过揭示支持向量回归(SVR)与支持向量分类(SVC)之间的关系,证明了SVR用于分类的可行性,并以此为根据提出了一种基于SVR的目标探测算法,该算法利用虚拟维数得到端元个数的估计,结合端元选择和线性混合模型生成训练样本替代从影像中选择的训练样本,因而减少了对影像先验知识的依赖。采用模拟数据和由AVIRIS获得的高光谱影像对本文算法进行了检验,结果令人满意。     

利用天宫一号高光谱数据识别植被类型的评估研究

天宫一号高光谱数据尚未得到普遍应用,其数据的质量和应用潜力仍在进一步实践求证和挖掘.See5.0数据挖掘工具是一种能够找出训练样本中模式类隐含特征,并可以自动建立决策规则的分类算法,可避免人为建立分类规则的主观性.本文首先通过光谱曲线分析,选择地物光谱分离性最好的波段组合,然后利用See5.0工具生成规则集,再利用规则集对同一幅天宫一号高光谱数据在不同分类级别上进行分类,并利用相同的验证样本进行精度验证.经过光谱分析发现分类不同森林类型的最佳谱段中心波长分别为:655 nm、673 nm、802 nm、866 nm、984 nm,See5.0分类结果表明在同一树种不同生长期及不同亚种的分类级别上,分类精度在45%以下,表现出了一定局限性,但在树种分类级别上,天宫一号数据表现出了高光谱的优越性,分类精度皆在80%以上,植被类型分类级别,分类精度可达到90%以上.