Comparing object-based and pixel-based classifications for mapping savannas

The development of robust object-based classification methods suitable for medium to high resolution satellite imagery provides a valid alternative to ‘traditional’ pixel-based methods. This paper compares the results of an object-based classification to a supervised per-pixel classification for mapping land cover in the tropical north of the Northern Territory of Australia. The object-based approach involved segmentation of image data into objects at multiple scale levels. Objects were assigned classes using training objects and the Nearest Neighbour supervised and fuzzy classification algorithm. The supervised pixel-based classification involved the selection of training areas and a classification using the maximum likelihood classifier algorithm. Site-specific accuracy assessment using confusion matrices of both classifications were undertaken based on 256 reference sites. A comparison of the results shows a statistically significant higher overall accuracy of the object-based classification over the pixel-based classification. The incorporation of a digital elevation model (DEM) layer and associated class rules into the object-based classification produced slightly higher accuracies overall and for certain classes; however this was not statistically significant over the object-based using spectral information solely. The results indicate object-based analysis has good potential for extracting land cover information from satellite imagery captured over spatially heterogeneous land covers of tropical Australia.     

Pixel-based and object-based classifications using high- and medium-spatial-resolution imageries in the urban and suburban landscapes

With the increasing availability of high-spatial-resolution remote sensing imageries and with the observed limitations of pixel-based techniques, the development and testing of geographic object-based image analysis (GEOBIA) techniques for image classification have become one of the main research areas in geospatial science. This paper examines and compares the classification performance of a pixel-based method and an object-based method as applied to high- (QuickBird satellite image) and medium- (Landsat TM image) spatial-resolution imageries in the context of urban and suburban landscapes. For the pixel-based classification, the maximum-likelihood supervised classification approach was employed. And for the object-based classification, the pixel-based classified maps were integrated with a set of image segments produced using various calibrations. The results show evidence that the object-based method can produce classifications that are more accurate for both high- and medium-spatial- resolution imageries in the context of urban and suburban landscapes.     

Mediterranean forest species mapping using classification of Hyperion imagery

Regional operational forest species mapping is an active research topic that aims to provide the systematic and updatable information necessary for understanding and monitoring the rapidly changing forest environment. In this study, we investigated the potential of satellite hyperspectral imagery in regional forest species mapping by employing a pixel-based and an object-based nearest neighbour classifier in two different Mediterranean study areas. The overall thematic accuracy of the produced maps was assessed using reference data collected in the field and ranged between 0.72 and 0.83. No approach was found to be superior for the study areas. The McNemar test showed no statistically significant difference at the 95% confidence level in the classification accuracies achieved by the two approaches. Both pixel- and object-based approaches provide useful maps, suggesting that regional forest species mapping from space has much potential.     

Effects of Training Samples and Classifiers on Classification of Landsat-8 Imagery

In this study, we used Landsat-8 imagery to test object- and pixel-based image classification approaches in an urban fringe area. For object-based classification, we applied four machine learning classifiers: decision tree (DT), naive Bayes (NB), random trees (RT), and support vector machine (SVM). For pixel-based classification, we utilized the maximum likelihood classifier (MLC). Specifically, we explored the influence of repeated sampling on classification results with different training sample sizes. We found that (1) except the overall accuracy of NB, those of the other four classifiers increased as the training sample size increased; (2) repeated sampling had a significant effect on classification accuracy, especially for the DT and NB classifiers; and (3) SVM achieved the best classification accuracy. In addition, the performance of the object-based classifiers was superior to that of the pixel-based classifier. The results of this study can provide guidance on the training sample size and classifier selection.     

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.     

多尺度分割的高分辨率遥感影像变化检测

针对高空间分辨率的遥感影像,提出了一种基于多尺度分割的变化检测算法。采用Mean-Shift分割算法对影像进行多尺度分割,构建了不同尺度上的地理对象,以不同尺度上的地理对象灰度均值构建了变化检测的多尺度特征向量,采用变化矢量分析法获得最后的变化检测结果。以城镇区和农田区的Quick Bird影像对本文算法进行了检验,从精度评价的效果来看,无论城镇区还是农田区,采用面向对象的变化检测方法精度都高于基于单像素的检测方法,且当尺度层数固定时,多尺度组合的变化检测结果优于单一尺度的变化检测结果,对城镇、农田区域的变化检测的精度分别达到87.57%和81.55%。本文算法既可以顾及大面积同质区域变化,又可以反映小的地物目标及边缘部分的变化,能够很好地满足城镇、农田等不同环境背景下的变化检测需求,在国土资源监测中具有一定的应用价值。     

Object-based classification of hyperspectral data using Random Forest algorithm

This paper presents a new framework for object-based classification of high-resolution hyperspectral data. This multi-step framework is based on multi-resolution segmentation (MRS) and Random Forest classifier (RFC) algorithms. The first step is to determine of weights of the input features while using the object-based approach with MRS to processing such images. Given the high number of input features, an automatic method is needed for estimation of this parameter. Moreover, we used the Variable Importance (VI), one of the outputs of the RFC, to determine the importance of each image band. Then, based on this parameter and other required parameters, the image is segmented into some homogenous regions. Finally, the RFC is carried out based on the characteristics of segments for converting them into meaningful objects. The proposed method, as well as, the conventional pixel-based RFC and Support Vector Machine (SVM) method was applied to three different hyperspectral data-sets with various spectral and spatial characteristics. These data were acquired by the HyMap, the Airborne Prism Experiment (APEX), and the Compact Airborne Spectrographic Imager (CASI) hyperspectral sensors. The experimental results show that the proposed method is more consistent for land cover mapping in various areas. The overall classification accuracy (OA), obtained by the proposed method was 95.48, 86.57, and 84.29% for the HyMap, the APEX, and the CASI data-sets, respectively. Moreover, this method showed better efficiency in comparison to the spectral-based classifications because the OAs of the proposed method was 5.67 and 3.75% higher than the conventional RFC and SVM classifiers, respectively.     

A comparative assessment between object and pixel-based classification approaches for land use/land cover mapping using SPOT 5 imagery

Abstract

Land use/land cover (LULC) classification with high accuracy is necessary, especially in eco-environment research, urban planning, vegetation condition study and soil management. Over the last decade a number of classification algorithms have been developed for the analysis of remotely sensed data. The most notable algorithms are the object-oriented K-Nearest Neighbour (K-NN), Support Vector Machines (SVMs) and the Decision Trees (DTs) amongst many others. In this study, LULC types of Selangor area were analyzed on the basis of the classification results acquired using the pixel-based and object-based image analysis approaches. SPOT 5 satellite images with four spectral bands from 2003 and 2010 were used to carry out the image classification and ground truth data were collected from Google Earth and field trips. In pixel-based image analysis, a supervised classification was performed using the DT classifier. On the other hand, object-oriented (K-NN) image analysis was evaluated using standard nearest neighbour as classifier. Subsequently SVM object-based classification was performed. Five LULC categories were extracted and the results were compared between them. The overall classification accuracies for 2003 and 2010 showed that the object-oriented (K-NN) (90.5% and 91%) performed better results than the pixel-based DT (68.6% and 68.4%) and object-based SVM (80.6% and 78.15%). In general, the object-oriented (K-NN) performed better than both DTs and SVMs. The obtained LULC classification maps can be used to improve various applications such as change detection, urban design, environmental management and zooning.     

Dimensionality Reduction and Classification of Hyperspectral Images Using Object-Based Image Analysis

Object-based image analysis (OBIA) has attained great importance for the delineation of landscape features, particularly with the accessibility to satellite images with high spatial resolution acquired by recent sensors. Statistical parametric classifiers have become ineffective mainly due to their assumption of normal distribution, vast increase in the dimensions of the data and availability of limited ground sample data. Despite pixel-based approaches, OBIA takes semantic information of extracted image objects into consideration, and thus provides more comprehensive image analysis. In this study, Indian Pines hyperspectral data set, which was recorded by the AVIRIS hyperspectral sensor, was used to analyse the effects of high dimensional data with limited ground reference data. To avoid the dimensionality curse, principal component analysis (PCA) and feature selection based on Jeffries–Matusita (JM) distance were utilized. First 19 principal components representing 98.5% of the image were selected using the PCA technique whilst 30 spectral bands of the image were determined using JM distance. Nearest neighbour (NN) and random forest (RF) classifiers were employed to test the performances of pixel- and object-based classification using conventional accuracy metrics. It was found that object-based approach outperformed the traditional pixel-based approach for all cases (up to 18% improvement). Also, the RF classifier produced significantly more accurate results (up to 10%) than the NN classifier.     

Object-oriented and pixel-based classification approaches to classify tropical successional stages using airborne high–spatial resolution images

Airborne high–spatial resolution images were evaluated for mapping purposes in a complex Atlantic rainforest environment in southern Brazil. Two study sites, covered predominantly by secondary evergreen rainforest, were surveyed by airborne multispectral high-resolution imagery. These aerophotogrammetric images were acquired at four spectral bands (visible to near-infrared) with spatial resolution of 0.39 m. We evaluated different data input scenarios to suit the object-oriented classification approach. In addition to the four spectral bands, auxiliary products such as band ratios and digital elevation models were considered. Comparisons with traditional pixel-based classifiers were also performed. The results showed that the object-based classification approach yielded a better overall accuracy, ranging from 89% to 91%, than the pixel-based classifications, which ranged from 62% to 63%. The individual classification accuracy of forest-related classes, such as young successional forest stages, benefits the object-based approach. These classes have been reported in the literature as the most difficult to map in tropical environments. The results confirm the potential of object-based classification for mapping procedures and discrimination of successional forest stages and other related land use and land cover classes in complex Atlantic rainforest environments. The methodology is suggested for further SAAPI acquisitions in order to monitor such endangered environment as well as to support National Land and Environmental Management Protocols.     

面向对象方法的时间序列MODIS数据湿地信息提取——以洞庭湖流域为例

以洞庭湖流域为研究区,对大范围湿地信息遥感提取方法进行了研究。先基于时间序列MODIS EVI及物候特征参数,通过J-M(Jeffries-Matusita distance)距离分析,构建了MODIS(250 m)最佳时序组合分类数据;其次,通过Johnson指数确定了最佳分割尺度,采用面向对象的遥感分类方法(Random tree分类器)提取了洞庭湖流域的湿地信息,并验证该方法的适用性。研究结果表明,基于时序数据与面向对象的Random tree分类的总体精度和Kappa系数分别为78.84%和0.71,较之基于像元的相同算法的总体分类精度和Kappa系数分别提高了5.79%和0.04。同时,基于面向对象方法的湿地整体的用户精度与生产者精度较基于像元方法分别提高了4.56%和6.21%,可有效提高大区域湿地信息提取的精度。     

Object-based classification with features extracted by a semi-automatic feature extraction algorithm – SEaTH

Object-based image analysis (OBIA) uses object features (or attributes) that relateto the pixels contained by the image object to assist in image classification. These object features include spectral, shape, texture and context features. With hundreds of available features, the identification of those that can improve separability between classes is critical for OBIA. The Separability and Thresholds (SEaTH) algorithm calculates the SEaTH of object–classes for the given features. The SEaTH algorithm avoids time-consuming trial-and-error practice for seeking important features and thresholds. This article tests the SEaTH algorithm on Landsat-7 Enhanced Thematic Mapper (ETM+) imagery in a heterogeneous landscape with multiple land cover classes. The results suggest SEaTH is a strong alternative to other automated approaches, yielding an agreement of 79% with reference data. In comparison, an object-based nearest neighbour classifier yielded 66% agreement and a pixel-based maximum likelihood classifier yielded 69% agreement.     

Assessment of Nigeriasat-1 satellite data for urban land use/land cover analysis using object-based image analysis in Abuja,Nigeria

This study assesses the usefulness of Nigeriasat-1 satellite data for urban land cover analysis by comparing it with Landsat and SPOT data. The data-sets for Abuja were classified with pixel- and object-based methods. While the pixel-based method was classified with the spectral properties of the images, the object-based approach included an extra layer of land use cadastre data. The classification accuracy results for OBIA show that Landsat 7 ETM, Nigeriasat-1 SLIM and SPOT 5 HRG had overall accuracies of 92, 89 and 96%, respectively, while the classification accuracy for pixel-based classification were 88% for Landsat 7 ETM, 63% for Nigeriasat-1 SLIM and 89% for SPOT 5 HRG. The results indicate that given the right classification tools, the analysis of Nigeriasat-1 data can be compared with Landsat and SPOT data which are widely used for urban land use and land cover analysis.     

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.     

Multiscale quantification of urban composition from EO-1/Hyperion data using object-based spectral unmixing

Quantification of the urban composition is important in urban planning and management. Previous research has primarily focused on unmixing medium-spatial resolution multispectral imagery using spectral mixture analysis (SMA) in order to estimate the abundance of urban components. For this study an object-based multiple endmember spectral mixture analysis (MESMA) approach was applied to unmix the 30-m Earth Observing-1 (EO-1)/Hyperion hyperspectral imagery. The abundance of two physical urban components (vegetation and impervious surface) was estimated and mapped at multiple scales and two defined geographic zones. The estimation results were validated by a reference dataset generated from fine spatial resolution aerial photography. The object-based MESMA approach was compared with its corresponding pixel-based one, and EO-1/Hyperion hyperspectral data was compared with the simulated EO-1/Advanced Land Imager (ALI) multispectral data in the unmixing modeling. The pros and cons of the object-based MESMA were evaluated. The result illustrates that the object-based MESMA is promising for unmixing the medium-spatial resolution hyperspectral imagery to quantify the urban composition, and it is an attractive alternative to the traditional pixel-based mixture analysis for various applications.     

Identifying a suitable combination of classification technique and bandwidth(s) for burned area mapping in tallgrass prairie with MODIS imagery

Prescribed fire is crucial to the ecology and maintenance of tallgrass prairie, and its application affects a variety of human and natural systems. Consequently, maps showing the location and extent of these fires are critical to managing tallgrass prairies in a manner that balances the needs of all stakeholders. Satellite-based optical remote sensing can provide the necessary input for this mapping, but it requires the development mapping methods that are specific to tallgrass prairie. In this research, we devise and test a suitable mapping method by comparing the efficacy of seven combinations of bands and indices from the MODIS sensor using both pixel and object-based classification methods. Due to the relatively small size of many prescribed fires in tallgrass prairie, scenarios based on the 250 m spatial resolution red and NIR bands outperformed those based on the coarser 500 m spatial resolution bands, and a combination of both red and NIR performed better than each 250 m band individually. Object-based classification offered no improvement over pixel-based classification, and performed poorer in some cases. Our results suggest that mapping burned areas in tallgrass prairie should be done at a minimum of 250 m spatial resolution, should used a pixel-based classification technique, and should use a combination of red and NIR.     

Landsat 8 vs. Landsat 5: A comparison based on urban and peri-urban land cover mapping

An image dataset from the Landsat OLI spaceborne sensor is compared with the Landsat TM in order to evaluate the excellence of the new imagery in urban landcover classification. Widely known pixel-based and object-based image analysis methods have been implemented in this work like Maximum Likelihood, Support Vector Machine, k-Nearest Neighbor, Feature Analyst and Sub-pixel. Classification results from Landsat OLI provide more accurate results comparing to the Landsat TM. Object-based classifications produced a more uniform result, but suffer from the absorption of small rare classes into large homogenous areas, as a consequence of the segmentation, merging and the spatial parameters in the spatial resolution (30 m) of Landsat images. Based exclusively on the overall accuracy reports, the SVM pixel-based classification from Landsat 8 proved to be the most accurate for the purpose of mapping urban land cover, using medium spatial resolution imagery.     

Fusion of RADARSAT-2 and multispectral optical remote sensing data for LULC extraction in a tropical agricultural area

In this study, we investigated the performance of different fusion and classification techniques for land cover mapping in Hilir Perak, Peninsula Malaysia using RADAR and Landsat-8 images in a predominantly agricultural area. The fusion methods used are Brovey Transform, Wavelet Transform, Ehlers and Layer Stacking and their results classified into seven different land cover classes which include (1) pixel-based classifiers (spectral angle mapper (SAM), maximum likelihood (ML), support vector machine (SVM)) and (2) Object-based (rule-based and standard nearest neighbour (NN)) classifiers. The result shows that pixel-based classification achieved maximum accuracy of the optical data classification using SVM in Landsat-8 with 74.96% accuracy compared to SAM and ML. For multisource data classification, the highest overall accuracy recorded for layer stacking (SVM) was 79.78%, Ehlers fusion (SVM) with 45.57%, Brovey fusion (SVM) with 63.70% and Wavelet fusion (SVM) 61.16%. And for object-based classifiers, the overall classification accuracy is 95.35% for rule-based and 76.33% for NN classifier, respectively. Based on the analysis of their performances, object-based and the rule-based classifiers produced the best classification accuracy from the fused images.     

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.     

面向对象的遥感影像模糊分类方法研究

传统的基于像素的遥感影像处理方法都是基于遥感影像光谱信息极其丰富,地物间光谱差异较为明显的基础上进行的。对于只含有较少波段的高分辨率遥感影像,传统的分类方法,就会造成分类精度降低,空间数据的大量冗余,并且其分类结果常常是椒盐图像,不利于进行空间分析。本文采用面向对象的影像分类方法,考虑了对象的不同特征值,例如光谱值,形状和纹理,结合上下文关系和语义的信息,这种分类技术不仅能够使用影像属性,而且能够利用不同影像对象之间的空间关系。在对诸多对象进行分类后,再进行精度分析。在此研究提出了一种面向对象的方法结合模糊理论把许多的对象块分成不同的类别。这一过程主要有两个步骤：第一个步骤是分割。图像分割将整个图像分割成若干个对象,在这个过程中,分割尺度的选择会影响到后续的分类结果和精度。第二个步骤是分类。在这个步骤中,特征值的选择和隶属度函数的选择都对分类结果有着至关重要的影响。