Large-scale urban functional zone mapping by integrating remote sensing images and open social data

ABSTRACT

Urban functional zones (UFZs) are important for urban sustainability and urban planning and management, but UFZ maps are rarely available and up-to-date in developing countries due to frequent economic and human activities and rapid changes in UFZs. Current methods have focused on mapping UFZs in a small area with either remote sensing images or open social data, but large-scale UFZ mapping integrating these two types of data is still not be applied. In this study, a novel approach to mapping large-scale UFZs by integrating remote sensing images (RSIs) and open social data is proposed. First, a context-enabled image segmentation method is improved to generate UFZ units by incorporating road vectors. Second, the segmented UFZs are classified by coupling Latent Dirichlet Allocation (LDA) and Support Vector Machine (SVM). In the classification framework, physical features from RSIs and social attributes from POI (Point of Interest) data are integrated. A case study of Beijing was performed to evaluate the proposed method, and an overall accuracy of 85.9% was achieved. The experimental results demonstrate that the presented method can provide fine-grained UFZs, and the fusion strategy of RSIs and POI data can distinguish urban functions accurately. The proposed method appears to be promising and practical for large-scale UFZ mapping.     

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。     

Improving Spectral–spatial Classification of Hyperspectral Imagery Using Spectral Dimensionality Reduction Based on Weighted Genetic Algorithm

This paper aims to improve the accuracy and the efficiency of high resolution land cover mapping in urban area. To this end, an improved approach for classification of hyperspectral imagery is proposed and evaluated. This approach benefits from both inherent spectral and spatial information of an image. The weighted genetic (WG) algorithm is first used to obtain the subspace of hyperspectral data. The obtained features are then fed into the enhanced marker-based minimum spanning forest (EMSF) classification algorithm. In this algorithm, the markers are extracted from the classification maps obtained by both support vector machine and watershed segmentation algorithm classifiers. For this purpose, the class’s pixels with the largest population in the classification map are kept for each region of the segmentation map. Then, the most reliable classified pixels are chosen from among the exiting pixels as markers. To evaluate the efficiency of the proposed approach, three hyperspectral data sets acquired by ROSIS-03, Hymap and Hyper-Cam LWIR are used. Experimental results showed that the proposed WG–EMSF approach achieves approximately 9, 8 and 6% better overall accuracy than the original MSF-based algorithm for these data sets respectively.     

Hierarchical extraction of landslides from multiresolution remotely sensed optical images

The automated detection and mapping of landslides from Very High Resolution (VHR) images present several challenges related to the heterogeneity of landslide sizes, shapes and soil surface characteristics. However, a common geomorphological characteristic of landslides is to be organized with a series of embedded and scaled features. These properties motivated the use of a multiresolution image analysis approach for their detection. In this work, we propose a hybrid segmentation/classification region-based method, devoted to this specific issue. The method, which uses images of the same area at various spatial resolutions (Medium to Very High Resolution), relies on a recently introduced top-down hierarchical framework. In the specific context of landslide analysis, two main novelties are introduced to enrich this framework. The first novelty consists of using non-spectral information, obtained from Digital Terrain Model (DTM), as a priori knowledge for the guidance of the segmentation/classification process. The second novelty consists of using a new domain adaptation strategy, that allows to reduce the expert’s interaction when handling large image datasets. Experiments performed on satellite images acquired over terrains affected by landslides demonstrate the efficiency of the proposed method with different hierarchical levels of detail addressing various operational needs.     

A novel confidence estimation method for neural networks in multispectral image classification

Abstract

The Digital Earth concept has attracted much attention recently and this approach uses a variety of earth observation data from the global to the local scale. Imaging techniques have made much progress technically and the methods used for automatic extraction of geo-ralated information are of importance in Digital Earth science. One of these methods, artificial neural networks (ANN) techniques, have been effectively used in classification of remotely sensed images. Generally image classification with ANN has been producing higher or equal mapping accuracies than parametric methods. Comparative studies have, in fact, shown that there is no discernible difference in classification accuracies between neural and conventional statistical approaches. Only well designed and trained neural networks can present a better performance than the standard statistical approaches. There are, as yet, no widely recognised standard methods to implement an optimum network. From this point of view it might be beneficial to quantify ANN's reliability in classification problems. To measure the reliability of the neural network might be a way of developing to determine suitable network structures. To date, the problem of confidence estimation of ANN has not been studied in remote sensing studies. A statistical method for quantifying the reliability of a neural network that can be used in image classification is investigated in this paper. For this purpose the method is to be based on a binomial experimentation concept to establish confidence intervals. This novel method can also be used for the selection of an appropriate network structure for the classification of multispectral imagery. Although the main focus of the research is to estimate confidence in ANN, the approach might also be applicable and relevant to Digital Earth technologies.     

A Robust Texture Analysis and Classification Approach for Urban Land‐Use and Land‐Cover Feature Discrimination

Abstract

Attempts to analyze urban features and to classify land use and land cover directly from high‐resolution satellite data with traditional computer classification techniques have proven to be inefficient for two primary reasons. First, urban landscapes are composed of complex features. Second, traditional classifiers employ spectral information based on single pixel value and ignore a great amount of spatial information. Texture plays an important role in image segmentation and object recognition, as well as in interpretation of images in a variety of applications. This study analyzes urban texture features in multi‐spectral image data. Recent developments in the very powerful mathematical theory of wavelet transforms have received overwhelming attention by image analysts. An evaluation of the ability of wavelet transform in urban feature extraction and classification was performed in this study, with six types of urban land cover features classified. The preliminary results of this research indicate that the accuracy of texture analysis in classifying urban features in fine resolution image data could be significantly improved with the use of wavelet transform approach.     

Derivation of an urban materials spectral library through emittance and reflectance spectroscopy

Recent advances in thermal infrared remote sensing include the increased availability of airborne hyperspectral imagers (such as the Hyperspectral Thermal Emission Spectrometer, HyTES, or the Telops HyperCam and the Specim aisaOWL), and it is planned that an increased number spectral bands in the long-wave infrared (LWIR) region will soon be measured from space at reasonably high spatial resolution (by imagers such as HyspIRI). Detailed LWIR emissivity spectra are required to best interpret the observations from such systems. This includes the highly heterogeneous urban environment, whose construction materials are not yet particularly well represented in spectral libraries. Here, we present a new online spectral library of urban construction materials including LWIR emissivity spectra of 74 samples of impervious surfaces derived using measurements made by a portable Fourier Transform InfraRed (FTIR) spectrometer. FTIR emissivity measurements need to be carefully made, else they are prone to a series of errors relating to instrumental setup and radiometric calibration, which here relies on external blackbody sources. The performance of the laboratory-based emissivity measurement approach applied here, that in future can also be deployed in the field (e.g. to examine urban materials in situ), is evaluated herein. Our spectral library also contains matching short-wave (VIS–SWIR) reflectance spectra observed for each urban sample. This allows us to examine which characteristic (LWIR and) spectral signatures may in future best allow for the identification and discrimination of the various urban construction materials, that often overlap with respect to their chemical/mineralogical constituents. Hyperspectral or even strongly multi-spectral LWIR information appears especially useful, given that many urban materials are composed of minerals exhibiting notable reststrahlen/absorption effects in this spectral region. The final spectra and interpretations are included in the London Urban Micromet data Archive (LUMA; http://LondonClimate.info/LUMA/SLUM.html).     

Production of global land cover data – GLCNMO

Abstract

Global land cover is one of the fundamental contents of Digital Earth. The Global Mapping project coordinated by the International Steering Committee for Global Mapping has produced a 1-km global land cover dataset – Global Land Cover by National Mapping Organizations. It has 20 land cover classes defined using the Land Cover Classification System. Of them, 14 classes were derived using supervised classification. The remaining six were classified independently: urban, tree open, mangrove, wetland, snow/ice, and water. Primary source data of this land cover mapping were eight periods of 16-day composite 7-band 1-km MODIS data of 2003. Training data for supervised classification were collected using Landsat images, MODIS NDVI seasonal change patterns, Google Earth, Virtual Earth, existing regional maps, and expert's comments. The overall accuracy is 76.5% and the overall accuracy with the weight of the mapped area coverage is 81.2%. The data are available from the Global Mapping project website (http://www.iscgm.org/). The MODIS data used, land cover training data, and a list of existing regional maps are also available from the CEReS website. This mapping attempt demonstrates that training/validation data accumulation from different mapping projects must be promoted to support future global land cover mapping.     

Object-based urban land cover classification using rule inheritance over very high-resolution multisensor and multitemporal data

Very high spatial and temporal resolution remote sensing data facilitate mapping highly complex and diverse urban environments. This study analyzed and demonstrated the usefulness of combined high-resolution aerial digital images and elevation data, and its processing using object-based image analysis for mapping urban land covers and quantifying buildings. It is observed that mapping heterogeneous features across large urban areas is time consuming and challenging. This study presents and demonstrates an approach for formulating an optimal land cover classification rule set over small representative training urban area image, and its subsequent transfer to the multisensor, multitemporal images. The classification results over the training area showed an overall accuracy of 96%, and the application of rule set to different sensor images of other test areas resulted in reduced accuracies of 91% for the same sensor, 90% and 86% for the different sensors temporal data. The comparison of reference and classified buildings showed ±4% detection errors. Classification through a transferred rule set reduced the classification accuracy by about 5%–10%. However, the trade-off for this accuracy drop was about a 75% reduction in processing time for performing classification in the training area. The factors influencing the classification accuracies were mainly the shadow and temporal changes in the class characteristics.     

Assessing environmental impacts of urban growth using remote sensing

ABSTRACT

This paper provides a study of the changes in land use in urban environments in two cities, Wuhan, China and western Sydney in Australia. Since mixed pixels are a characteristic of medium resolution images such as Landsat, when used for the classification of urban areas, due to changes in urban ground cover within a pixel, Multiple Endmember Spectral Mixture Analysis (MESMA) together with Super-Resolution Mapping (SRM) are employed to derive class fractions to generate classification maps at a higher spatial resolution using an Artificial Neural Network (ANN) predicted Wavelet method. Landsat images over the two cities for a 30-year period, are classified in terms of vegetation, buildings, soil and water. The classifications are then processed using Indifrag software to assess the levels of fragmentation caused by changes in the areas of buildings, vegetation, water and soil over the 30 years. The extents of fragmentation of vegetation, buildings, water and soil for the two cities are compared, while the percentages of vegetation are compared with recommended percentages of green space for urban areas for the benefit of health and well-being of inhabitants. Changes in Ecosystem Service Values (ESVs) resulting from the urbanization have been assessed for Wuhan and Sydney. The UN Sustainable Development Goals (SDG) for urban areas are being assessed by researchers to better understand how to achieve the sustainability of cities.     

Impact of discretization methods on the rough set-based classification of remotely sensed images

Abstract

In recent years, the rough set (RS) method has been in common use for remote-sensing classification, which provides one of the techniques of information extraction for Digital Earth. The discretization of remotely sensed data is an important data preprocessing approach in classical RS-based remote-sensing classification. Appropriate discretization methods can improve the adaptability of the classification rules and increase the accuracy of the remote-sensing classification. To assess the performance of discretization methods this article adopts three indicators, which are the compression capability indicator (CCI), consistency indicator (CI), and number of the cut points (NCP). An appropriate discretization method for the RS-based classification of a given remotely sensed image can be found by comparing the values of the three indicators and the classification accuracies of the discretized remotely sensed images obtained with the different discretization methods. To investigate the effectiveness of our method, this article applies three discretization methods of the Entropy/MDL, Naive, and SemiNaive to a TM image and three indicators for these discretization methods are then calculated. After comparing the three indicators and the classification accuracies of the discretized remotely sensed images, it has been found that the SemiNaive method significantly reduces large quantities of data and also keeps satisfactory classification accuracy.     

The improvement of an object-oriented classification using multi-temporal MODIS EVI satellite data

Abstract

This paper investigates the contribution of multi-temporal enhanced vegetation index (EVI) data to the improvement of object-based classification accuracy using multi-spectral moderate resolution imaging spectral-radiometer (MODIS) imagery. In object-oriented classification, similar pixels are firstly grouped together and then classified; the produced result does not suffer the speckled appearance and closer to human vision. EVI data are from the MODIS sensor aboard Terra spacecraft. 69 EVI data (scenes) were collected during the period of three years (2001–2003) in a mountainous vegetated area. These data sets were used to study the phenology of the land cover types. Different land cover types show distinct fluctuations over time in EVI values and this information might be used to improve object-oriented land cover classification. Two experiments were carried out: one was only with single date MODIS multispectral data, and the other one including also the 69 EVI images. Eight classes were distinguished: temperate forest, tropical dry forest, grassland, irrigated agriculture, rain-fed agriculture, orchards, lava flows and human settlement. The two classifications were evaluated with independent verification data, and the results showed that with multi-temporal EVI data, the classification accuracy was improved 5.2%. Evaluated by McNemar's test, this improved was significant, with significance level p=0.01.     

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

Abstract

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

A modified stochastic neighbor embedding for multi-feature dimension reduction of remote sensing images

In automated remote sensing based image analysis, it is important to consider the multiple features of a certain pixel, such as the spectral signature, morphological property, and shape feature, in both the spatial and spectral domains, to improve the classification accuracy. Therefore, it is essential to consider the complementary properties of the different features and combine them in order to obtain an accurate classification rate. In this paper, we introduce a modified stochastic neighbor embedding (MSNE) algorithm for multiple features dimension reduction (DR) under a probability preserving projection framework. For each feature, a probability distribution is constructed based on t-distributed stochastic neighbor embedding (t-SNE), and we then alternately solve t-SNE and learn the optimal combination coefficients for different features in the proposed multiple features DR optimization. Compared with conventional remote sensing image DR strategies, the suggested algorithm utilizes both the spatial and spectral features of a pixel to achieve a physically meaningful low-dimensional feature representation for the subsequent classification, by automatically learning a combination coefficient for each feature. The classification results using hyperspectral remote sensing images (HSI) show that MSNE can effectively improve RS image classification performance.     

Assessing the performance of two unsupervised dimensionality reduction techniques on hyperspectral APEX data for high resolution urban land-cover mapping

Despite the high richness of information content provided by airborne hyperspectral data, detailed urban land-cover mapping is still a challenging task. An important topic in hyperspectral remote sensing is the issue of high dimensionality, which is commonly addressed by dimensionality reduction techniques. While many studies focus on methodological developments in data reduction, less attention is paid to the assessment of the proposed methods in detailed urban hyperspectral land-cover mapping, using state-of-the-art image classification approaches. In this study we evaluate the potential of two unsupervised data reduction techniques, the Autoassociative Neural Network (AANN) and the BandClust method – the first a transformation based approach, the second a feature-selection based approach – for mapping of urban land cover at a high level of thematic detail, using an APEX 288-band hyperspectral dataset. Both methods were tested in combination with four state-of-the-art machine learning classifiers: Random Forest (RF), AdaBoost (ADB), the multiple layer perceptron (MLP), and support vector machines (SVM). When used in combination with a strong learner (MLP, SVM) BandClust produces classification accuracies similar to or higher than obtained with the full dataset, demonstrating the method’s capability of preserving critical spectral information, required for the classifier to successfully distinguish between the 22 urban land-cover classes defined in this study. In the AANN data reduction process, on the other hand, important spectral information seems to be compromised or lost, resulting in lower accuracies for three of the four classifiers tested. Detailed analysis of accuracies at class level confirms the superiority of the SVM/Bandclust combination for accurate urban land-cover mapping using a reduced hyperspectral dataset. This study also demonstrates the potential of the new APEX sensor data for detailed mapping of land cover in spatially and spectrally complex urban areas.     

UAV navigation system using line-based sensor pose estimation

Abstract

This work presents a mapping and tracking system based on images to enable a small Unmanned Aerial Vehicle (UAV) to accurately navigate in indoor and GPS-denied outdoor environments. A method is proposed to estimate the UAV’s pose (i.e., the 3D position and orientation of the camera sensor) in real-time using only the on-board RGB camera as the UAV travels through a known 3D environment (i.e., a 3D CAD model). Linear features are extracted and automatically matched between images collected by the UAV’s onboard RGB camera and the 3D object model. The matched lines from the 3D model serve as ground control to estimate the camera pose in real-time via line-based space resection. The results demonstrate that the proposed model-based pose estimation algorithm provides sub-meter positioning accuracies in both indoor and outdoor environments. It is also that shown the proposed method can provide sparse updates to correct the drift from complementary simultaneous localization and mapping (SLAM)-derived pose estimates.     

FORSAT: a 3D forest monitoring system for cover mapping and volumetric 3D change detection

ABSTRACT

A 3D forest monitoring system, called FORSAT (a satellite very high resolution image processing platform for forest assessment), was developed for the extraction of 3D geometric forest information from very high resolution (VHR) satellite imagery and the automatic 3D change detection. FORSAT is composed of two complementary tasks: (1) the geometric and radiometric processing of satellite optical imagery and digital surface model (DSM) reconstruction by using a precise and robust image matching approach specially designed for VHR satellite imagery, (2) 3D surface comparison for change detection. It allows the users to import DSMs, align them using an advanced 3D surface matching approach and calculate the 3D differences and volume changes (together with precision values) between epochs. FORSAT is a single source and flexible forest information solution, allowing expert and non-expert remote sensing users to monitor forests in three and four (time) dimensions. The geometric resolution and thematic content of VHR optical imagery are sufficient for many forest information needs such as deforestation, clear-cut and fire severity mapping. The capacity and benefits of FORSAT, as a forest information system contributing to the sustainable forest management, have been tested and validated in case studies located in Austria, Switzerland and Spain.     

Satellite image analysis using crowdsourcing data for collaborative mapping: current and opportunities

ABSTRACT

Researchers are continually finding new applications of satellite images because of the growing number of high-resolution images with wide spatial coverage. However, the cost of these images is sometimes high, and their temporal resolution is relatively coarse. Crowdsourcing is an increasingly common source of data that takes advantage of local stakeholder knowledge and that provides a higher frequency of data. The complementarity of these two data sources suggests there is great potential for mutually beneficial integration. Unfortunately, there are still important gaps in crowdsourced satellite image analysis by means of crowdsourcing in areas such as land cover classification and emergency management. In this paper, we summarize recent efforts, and discuss the challenges and prospects of satellite image analysis for geospatial applications using crowdsourcing. Crowdsourcing can be used to improve satellite image analysis and satellite images can be used to organize crowdsourced efforts for collaborative mapping.