Development of fuzzy rule-based parameters for urban object-oriented classification using very high resolution imagery

Urban areas consist of spectrally and spatially heterogeneous features. Advanced information extraction techniques are needed to handle high resolution imageries in providing detailed information for urban planning applications. This study was conducted to identify a technique that accurately maps impervious and pervious surfaces from WorldView-2 (WV-2) imagery. Supervised per-pixel classification algorithms including Maximum Likelihood and Support Vector Machine (SVM) were utilized to evaluate the capability of spectral-based classifiers to classify urban features. Object-oriented classification was performed using supervised SVM and fuzzy rule-based approach to add spatial and texture attributes to spectral information. Supervised object-oriented SVM achieved 82.80% overall accuracy which was the better accuracy compared to supervised per-pixel classifiers. Classification based on the proposed fuzzy rule-based system revealed satisfactory output compared to other classification techniques with an overall accuracy of 87.10% for pervious surfaces and an overall accuracy of 85.19% for impervious surfaces.     

拓扑插值与光谱特征结合的复杂城区边界提取

复杂城区边界通常存在建筑物大小差异较大、周边林区高低起伏、散点建筑成片出现的情况,对城区边界提取算法造成严重干扰。针对这一问题,本文提出一种基于拓扑插值和光谱特征的高分辨率遥感影像复杂城区边界提取方法。一方面,通过对大型建筑特征点进行拓扑插值,避免由于大型建筑特征点稀疏造成的城区边界缺失;另一方面,利用植被光谱特征来滤除城区周边高低起伏的林区和散点建筑带来的冗余特征点,从而有效抑制城区误提取。通过试验和对比分析表明,本文方法在提取复杂城区边界方面,具有较好的稳健性和较高的精度。     

Classification method,spectral diversity,band combination and accuracy assessment evaluation for urban feature detection

Automatic extraction of urban features from high resolution satellite images is one of the main applications in remote sensing. It is useful for wide scale applications, namely: urban planning, urban mapping, disaster management, GIS (geographic information systems) updating, and military target detection. One common approach to detecting urban features from high resolution images is to use automatic classification methods. This paper has four main objectives with respect to detecting buildings. The first objective is to compare the performance of the most notable supervised classification algorithms, including the maximum likelihood classifier (MLC) and the support vector machine (SVM). In this experiment the primary consideration is the impact of kernel configuration on the performance of the SVM. The second objective of the study is to explore the suitability of integrating additional bands, namely first principal component (1st PC) and the intensity image, for original data for multi classification approaches. The performance evaluation of classification results is done using two different accuracy assessment methods: pixel based and object based approaches, which reflect the third aim of the study. The objective here is to demonstrate the differences in the evaluation of accuracies of classification methods. Considering consistency, the same set of ground truth data which is produced by labeling the building boundaries in the GIS environment is used for accuracy assessment. Lastly, the fourth aim is to experimentally evaluate variation in the accuracy of classifiers for six different real situations in order to identify the impact of spatial and spectral diversity on results. The method is applied to Quickbird images for various urban complexity levels, extending from simple to complex urban patterns. The simple surface type includes a regular urban area with low density and systematic buildings with brick rooftops. The complex surface type involves almost all kinds of challenges, such as high dense build up areas, regions with bare soil, and small and large buildings with different rooftops, such as concrete, brick, and metal.Using the pixel based accuracy assessment it was shown that the percent building detection (PBD) and quality percent (QP) of the MLC and SVM depend on the complexity and texture variation of the region. Generally, PBD values range between 70% and 90% for the MLC and SVM, respectively. No substantial improvements were observed when the SVM and MLC classifications were developed by the addition of more variables, instead of the use of only four bands. In the evaluation of object based accuracy assessment, it was demonstrated that while MLC and SVM provide higher rates of correct detection, they also provide higher rates of false alarms.     

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.     

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.     

Evaluation of diverse classification approaches for land use/cover mapping in a Mediterranean region utilizing Hyperion data

Information on Earth's land surface cover is commonly obtained through digital image analysis of data acquired from remote sensing sensors. In this study, we evaluated the use of diverse classification techniques in discriminating land use/cover types in a typical Mediterranean setting using Hyperion imagery. For this purpose, the spectral angle mapper (SAM), the object-based and the non-linear spectral unmixing based on artificial neural networks (ANNs) techniques were applied. A further objective had been to investigate the effect of two approaches for training sites selection in the SAM classification, namely of the pixel purity index (PPI) and of the direct selection of training points from the Hyperion imagery assisted by a QuickBird imagery and field-based training sites. Object-based classification outperformed the other techniques with an overall accuracy of 83%. Sub-pixel classification based on the ANN showed an overall accuracy of 52%, very close to that of SAM (48%). SAM applied using the training sites selected directly from the Hyperion imagery supported by the QuickBird image and the field visits returned an increase accuracy by 16%. Yet, all techniques appeared to suffer from the relatively low spatial resolution of the Hyperion imagery, which affected the spectral separation among the land use/cover classes.     

Efficacy of multi-season Sentinel-2 imagery for compositional vegetation classification

Vegetation maps are essential tools for the conservation and management of landscapes as they contain essential information for informing conservation decisions. Traditionally, maps have been created using field-based approaches which, due to limitations in costs and time, restrict the size of the area for which they can be created and frequency at which they can be updated. With the increasing availability of satellite sensors providing multi-spectral imagery with high temporal frequency, new methods for efficient and accurate vegetation mapping have been developed. The objective of this study was to investigate to what extent multi-seasonal Sentinel-2 imagery can assist in mapping complex compositional classifications at fine spatial scales. We deliberately chose a challenging case study, namely a visually and structurally homogenous scrub vegetation (known as kwongan) of Western Australia. The classification scheme consists of 24 target classes and a random 60/40 split was used for model building and validation. We compared several multi-temporal (seasonal) feature sets, consisting of numerous combinations of spectral bands, vegetation indices as well as principal component and tasselled cap transformations, as input to four machine learning classifiers (Support Vector Machines; SVM, Nearest Neighbour; NN, Random Forests; RF, and Classification Trees; CT) to separate target classes. The results show that a multi-temporal feature set combining autumn and spring images sufficiently captured the phenological differences between the classes and produced the best results, with SVM (74%) and NN (72%) classifiers returning statistically superior results compared to RF (65%) and CT (50%). The SWIR spectral bands captured during spring, the greenness indices captured during spring and the tasselled cap transformations derived from the autumn image emerged as most informative, which suggests that ecological factors (e.g. shared species, patch dynamics) occurring at a sub-pixel level likely had the biggest impact on class confusion. However, despite these challenges, the results are auspicious and suggest that seasonal Sentinel-2 imagery has the potential to predict compositional vegetation classes with high accuracy. Further work is needed to determine whether these results are replicable in other vegetation types and regions.     

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。     

结合边界约束网络和分水岭分割算法的建筑物提取

城市作为高密度建筑区域,在较小范围内有大量结构相似的建筑紧密分布。当前从高分辨率图像中准确检测建筑仍然是一个挑战,本文受边缘检测网络启发,提出一种强化边界精度的建筑物提取新方案,根据建筑物及边界特点改进深度网络,结合自下而上分组的分水岭分割提高分类精度和建筑边界的准确度。首先对数据预处理,生成建筑边界和建筑分割线两类辅助标签;改进性能较优的建筑检测框架ICT-Net网络,修改网络结构和损失函数,针对两类辅助标签,强化边界影响,提高网络性能;最后对网络预测结果应用结合分水岭分割和梯度提升回归树的后处理,实现高精度的建筑提取。结果表明,数据预处理、改进深度学习算法可提高建筑检测像素精度IOU（Intersection over Union）约1%。后处理能充分利用网络输出的概率信息,有效优化建筑边界,在网络预测结果的基础上提高建筑实例召回率10.5%。本文方案与原始的ICT-Net网络相比,提高建筑实例召回率22.9%。     

高分辨率遥感影像城中村提取的景观语义指数方法

城中村是中国一类特殊的非正式居民区。本文从城中村的物理特点出发,采用景观语义指数描述复杂的城中村场景,提出基于景观语义指数的高分辨率遥感影像城中村提取方法,并采用“分类置信度-反馈”机制进行实际可操作的大范围城中村制图。以广州市核心城区为例,城中村检测的总体精度达到了90%以上。试验结果表明相对于传统的光谱、纹理特征,景观语义指数能够更好地描述城中村的根本形态特点,更准确的城中村提取。此外,“分类置信度-反馈”机制能够充分参考机器学习的分类概率,以有限的人工干预生产更加准确的城中村制图产品。因此,本文方法能够有效应用于大范围的城中村提取与制图。     

Evaluating the impact of red-edge band from Rapideye image for classifying insect defoliation levels

The prospect of regular assessments of insect defoliation using remote sensing technologies has increased in recent years through advances in the understanding of the spectral reflectance properties of vegetation. The aim of the present study was to evaluate the ability of the red edge channel of Rapideye imagery to discriminate different levels of insect defoliation in an African savanna by comparing the results of obtained from two classifiers. Random Forest and Support vector machine classification algorithms were applied using different sets of spectral analysis involving the red edge band. Results show that the integration of information from red edge increases classification accuracy of insect defoliation levels in all analysis performed in the study. For instance, when all the 5 bands of Rapideye imagery were used for classification, the overall accuracies increases about 19% and 21% for SVM and RF, respectively, as opposed to when the red edge channel was excluded. We also found out that the normalized difference red-edge index yielded a better accuracy result than normalized difference vegetation index. We conclude that the red-edge channel of relatively affordable and readily available high-resolution multispectral satellite data such as Rapideye has the potential to considerably improve insect defoliation classification especially in sub-Saharan Africa where data availability is limited.     

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.     

基于非正定 OCSVM 的高光谱影像地物异常检测

针对基于高斯径向基核函数的OCSVM等异常检测算法,对地物光谱变异极为敏感,导致算法异常检测性能不稳定的问题,根据光谱角度余弦测度对光谱形状相似性的描述不受地物光谱辐射强度变异影响的特性,将具有非正定核特性的光谱角度余弦核测度引入非正定SVM算法中,提出一种基于非正定OCSVM的高光谱影像地物异常检测算法。利用四组模拟数据进行目标异常检测实验,结果表明,该算法能够有效检测出高光谱影像数据中的目标地物,检测精度提升明显。     

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.     

Analyzing fine-scale wetland composition using high resolution imagery and texture features

In order to monitor natural and anthropogenic disturbance effects to wetland ecosystems, it is necessary to employ both accurate and rapid mapping of wet graminoid/sedge communities. Thus, it is desirable to utilize automated classification algorithms so that the monitoring can be done regularly and in an efficient manner. This study developed a classification and accuracy assessment method for wetland mapping of at-risk plant communities in marl prairie and marsh areas of the Everglades National Park. Maximum likelihood (ML) and Support Vector Machine (SVM) classifiers were tested using 30.5 cm aerial imagery, the normalized difference vegetation index (NDVI), first and second order texture features and ancillary data. Additionally, appropriate window sizes for different texture features were estimated using semivariogram analysis. Findings show that the addition of NDVI and texture features increased classification accuracy from 66.2% using the ML classifier (spectral bands only) to 83.71% using the SVM classifier (spectral bands, NDVI and first order texture features).     

Interference of Human Impacts in Urban Growth Modelling with Transition Rules of Cellular Automata, GIS and Multi-Temporal Satellite Imagery: A Case Study of Maraghe, Iran

Urban growth is the result of physical and human impacts. In this study Cellular Automata (CA) has been used to analyze physical suitability and human forces in urban growth modelling of Maraghe. The multi-temporal satellite imagery, physical suitability and human impacts Layers have been applied to the modelling. In order to evaluate the accuracy of the image classification methods, Fuzzy ARTMAP is compared with Maximum Likelihood Classification (MLC) and Minimum Distance Classification (MDC) methods. The image classification results showed an overall accuracy of 93 %. Therefore, it is employed for classification of multi-temporal satellite imagery. In order to weight physical suitability and human impacts layers or geographical transition rules in the modelling, regression analysis, the correlation coefficient, trial-and-error method and visual comparison used. The statistical methods are presented to validate neighbourhood scales in the urban growth modelling. The calibration of the model is in fact to the estimate value of the physical suitability and human impacts layer (combinatory layer of demand for urban land and the government facilities) in the modelling. The results obtained from the model calibration showed that human impacts have the highest influence in the urban growth among other factors. Also a small neighbourhood scale (25:5?×?5 cells) is more realistic in the modeling. The accuracy of final validation is 83 % and the final scenario is based on this validation. A fuzzy CA has been used in urban growth modeling of Maraghe. The final scenario shows that Maraghe will growth on the east side, where the land demand for built up area and government facilities plays the significant role.     

基于对象直方图G统计量的遥感影像道路提取

提出了一种基于对象直方图G统计量的遥感影像道路提取方法。首先基于标记分水岭算法分割高分辨率遥感影像获取对象像斑,提取对象光谱特征并利用SVM从影像中分离出光谱相似的建成区（道路、建筑物等）;然后从建成区选择合适的对象作为训练样本,采用G统计量度量测试样本与训练样本的LBP纹理直方图距离,以表达对象纹理特征的异质性,并利用最小距离分类器完成建成区内道路与建筑物等的分离;最后结合几何形状特征和数学形态学处理对提取的道路进行优化,获得最终的道路提取结果。试验结果表明：该方法能较好地提取出道路信息。     

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.     

Object-Based Rule Sets and Its Transferability for Building Extraction from High Resolution Satellite Imagery

With the advent of high spatial resolution satellite imagery, automatic and semiautomatic building extractions have turned into one of the outstanding research topics in the field of remote sensing and machine vision. To this date, various algorithms have been presented for extracting the buildings from satellite images. Such methods lend their bases to diverse criteria such as radiometric, geometric, edge detection, and shadow. In this paper, a novel object based approach has been proposed for automatic and robust detections as well as extraction of the building in high spatial resolution images. To fulfill this, we simultaneously made use of both stable and variable features. While the former can be derived from inherent characteristics of the buildings, the latter is extracted using a feature analysis tool. In addition, a novel perspective has been recommended to boost the automation degree of the segmentation part in the object based analysis of remote sensing imagery. The proposed method was applied to a QuickBird imagery of an urban area in Isfahan city and the results of the quantitative evaluation demonstrated that the proposed method could yield promising results. Moreover, in another section of this study, for assessing the algorithm transferability, the rule set was implemented to a part of the WorldView image of Yazd city, proving that the proposed approach is capable of transferability in different types of case studies.