Urban Area Extraction Research Articles

Urban areas extraction from multi sensor data based on machine learning and data fusion

Accurate urban areas information is important for a variety of applications, especially city planning and natural disaster prediction and management. In recent years, extraction of urban structures from remotely sensed images has been extensively explored. The key advantages of this imaging modality are reduction of surveying expense and time. It also elevates restrictions on ground surveys. Thus far, much research typically extracts these structures from very high resolution satellite imagery, which are unfortunately of relatively poor spectral resolution, resulting in good precision yet moderate accuracy. Therefore, this paper investigates extraction of buildings from middle and high resolution satellite images by using spectral indices (Normalized Difference Building Index: NDBI, Normalized Difference Vegetation Index: NDVI, Soil Adjustment Vegetation Index: SAVI, Modified Normalized Difference Index: MNDWI, and Global Environment Monitoring Index: GEMI) by means of various Machine Learning methods (Artificial Neural Network: ANN, K-Nearest Neighbor: KNN, and Support Vector Machine: SVM) and Data Fusion (i.e., Majority Voting). Herein empirical results suggested that suitable learning methods for urban areas extraction are in preferring order Data Fusion, SVM, KNN, and ANN. Their accuracies were 85.46, 84.86, 84.66, and 84.91%, respectively.

Adaptive Neighborhood Selection Semi-supervised Discriminative Locality Alignment Based Urban Building Areas Extraction from High-Resolution SAR Image

Adaptive Neighborhood Selection Semi-supervised Discriminative Locality Alignment Based Urban Building Areas Extraction from High-Resolution SAR Image

Urban Land Extraction Using VIIRS Nighttime Light Data: An Evaluation of Three Popular Methods

Timely and accurate extraction of urban land area using the Suomi National Polar-orbiting Partnership Visible Infrared Imaging Radiometer Suite (VIIRS) nighttime light data is important for urban studies. However, a comprehensive assessment of the existing methods for extracting urban land using VIIRS nighttime light data remains inadequate. Therefore, we first reviewed the relevant methods and selected three popular methods for extracting urban land area using nighttime light data. These methods included local-optimized thresholding (LOT), vegetation-adjusted nighttime light urban index (VANUI), integrated nighttime lights, normalized difference vegetation index, and land surface temperature support vector machine classification (INNL-SVM). Then, we assessed the performance of these methods for extracting urban land area based on the VIIRS nighttime light data in seven evaluation areas with various natural and socioeconomic conditions in China. We found that INNL-SVM had the best performance with an average kappa of 0.80, which was 6.67% higher than the LOT and 2.56% higher than the VANUI. The superior performance of INNL-SVM was mainly attributed to the integration of information on nighttime light, vegetation cover, and land surface temperature. This integration effectively reduced the commission and omission errors arising from the overflow effect and low light brightness of the VIIRS nighttime light data. Additionally, INNL-SVM can extract urban land area more easily. Thus, we suggest that INNL-SVM has great potential for effectively extracting urban land with VIIRS nighttime light data at large scales.

Monitoring Annual Urban Changes in a Rapidly Growing Portion of Northwest Arkansas with a 20-Year Landsat Record

Northwest Arkansas has undergone a significant urban transformation in the past several decades and is considered to be one of the fastest growing regions in the United States. The urban area expansion and the associated demographic increases bring unprecedented pressure to the environment and natural resources. To better understand the consequences of urbanization, accurate and long-term depiction on urban dynamics is critical. Although urban mapping activities using remote sensing have been widely conducted, long-term urban growth mapping at an annual pace is rare and the low accuracy of change detection remains a challenge. In this study, a time series Landsat stack covering the period from 1995 to 2015 was employed to detect the urban dynamics in Northwest Arkansas via a two-stage classification approach. A set of spectral indices that have been proven to be useful in urban area extraction together with the original Landsat spectral bands were used in the maximum likelihood classifier and random forest classifier to distinguish urban from non-urban pixels for each year. A temporal trajectory polishing method, involving temporal filtering and heuristic reasoning, was then applied to the sequence of classified urban maps for further improvement. Based on a set of validation samples selected for five distinct years, the average overall accuracy of the final polished maps was 91%, which improved the preliminary classifications by over 10%. Moreover, results from this study also indicated that the temporal trajectory polishing method was most effective with initial low accuracy classifications. The resulting urban dynamic map is expected to provide unprecedented details about the area, spatial configuration, and growing trends of urban land-cover in Northwest Arkansas.

A Multi-Objective TRIBES/OC-SVM Approach for the Extraction of Areas of Interest from Satellite Images

In this work, we are interested in the extraction of areas of interest from satellite images by introducing a MOTRIBES/ OC-SVM approach. The One-Class Support Vector Machine (OC-SVM) is based on the estimation of a support that includes training data. It identifies areas of interest without including other classes from the scene. We propose generating optimal training data using the Multi-Objective TRIBES (MO-TRIBES) to improve the performances of the OC-SVM. The MO-TRIBES is a parameter-free optimization technique that manages the search space in tribes composed of agents. It makes different behavioral and structural adaptations to minimize the false positive and false negative rates of the OC-SVM. We have applied our proposed approach for the extraction of earthquakes and urban areas. The experimental results and comparisons with different state-of-the-art classifiers confirm the efficiency and the robustness of the proposed approach.

Urban Damage Level Mapping Based on Scattering Mechanism Investigation Using Fully Polarimetric SAR Data for the 3.11 East Japan Earthquake

A quick response to a large-scale natural disaster such as earthquake and tsunami is vital to mitigate further loss. Remote sensing, especially the spaceborne sensors, provides the possibility to monitor a very large scale area in a short time and with regular revisit circle. Damage ranges and damage levels of the destructed urban areas are extremely important information for rescue planning after an event. Rapid mapping of the urban damage levels with synthetic aperture radar (SAR) is still challenging. Compared with single-polarization SAR, fully polarimetric SAR (PolSAR) has a better potential to understand the urban damage from the viewpoint of scattering mechanism investigation. In radar polarimetry, the dominant double-bounce scattering mechanism in an urban area is primarily induced by the ground-wall structures and can reflect the changes of these structures. In this sense, urban damage level in terms of destroyed ground-wall structures can be indicated by the reduction of the dominant double-bounce scattering mechanism, which is the basis of this study. This work first establishes and validates the linear relationship between the urban damage level and the proposed polarimetric damage index using polarimetric model-based decomposition. Then, efforts are focused on the development of a rapid urban damage level mapping technique which mainly includes two steps of urban area extraction and polarimetric damage level estimation. The 3.11 East Japan earthquake and tsunami inducing great-scale destruction are adopted for study using L-band multitemporal spaceborne PolSAR data. Experimental studies demonstrate that the estimated damage levels are closely consistent to the ground-truth. The final urban damage level map for the full scene is generated thereafter. Results achieved in this study further validate the necessity of exploring fully polarimetric technique for damage assessment.

A study of urban area extraction with the modified human settlement index

A study of urban area extraction with the modified human settlement index

Urban Built-up Area Extraction and Change Detection of Adama Municipal Area using Time-Series Landsat Images

Urban built-up area information is required in various applications of land use planning and management. However, urban built-up area extraction from moderate spatial resolution Landsat time-series data is challenging because of significant intra-urban heterogeneity and spectral confusion between other landcover types. This paper proposes a technique to extract urban built-up area from time-series Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) imageries and determines urban area changes between 1984 to 2015 of Adama Municipal Area of Ethiopia. The study selected three indices, the Enhanced Built-Up and Bareness Index (EBBI), Soil Adjusted Vegetation Index (SAVI) and Modified Normalized Difference Water Index (MNDWI), to represent three major urban land-use classes: built-up and barren/bare land, open waterbody, and vegetation, respectively. The built-up area was extracted by taking the difference between EBBI, SAVI and MNDWI to remove the vegetation and water noises, and the resulted index image was spectrally segmented to separate built-up area from the non-urban built-up lands. The derived index was used to map built-up area for 1984, 1995, 2005 and 2015 periods. The expansion of the built-up area has been revealed as a major change in the area when city area expanded substantially by 293% between 1984 to 2015 periods. The advantage of the method was to use almost the entire spectral range of Landsat imageries which cause less spectral confusion between land cover classes and hence resulted in higher accuracies compared to other indices. The method was effective and simple to implement, and can be used for built-up extraction in other areas.

Urban Areas Enhancement in Multitemporal SAR RGB Images Using Adaptive Coherence Window and Texture Information

In this paper, we present a technique for improving the representation of built-up features in model-based multitemporal synthetic aperture radar (SAR) RGB composites. The proposed technique exploits the multitemporal adaptive processing (MAP3) framework to generate an a priori information which is used to implement an adaptive selection of the coherence window size. Image texture is used to support the coherence information in case of decorrelation. The coherence information, powered by texture analysis, and combined with backscattering amplitude, provides a unique representation of built-up features. This allows for an immediate detection of urban agglomerates by human operators, and is an advantaged starting point for urban area extraction algorithms.

Comprehensive urban area extraction from multispectral medium spatial resolution remote-sensing imagery based on a novel structural feature

ABSTRACTOne of the most important applications of remote sensing is urban area analysis in multispectral images. This article addresses a comprehensive method for urban area extraction in the mentioned images using a combination of classic spectral features and a new structural feature. The spectral features are used for eliminating the non-urban land covers including vegetation, water, shadows, and bright soil. Then the proposed structural feature based on the density of the spectral gradient is utilized for the final separation of urban points (UPs) from non-urban points (NUPs). The proposed method is insensitive to the spectral variation of urban areas caused by variant geographical conditions and coordinates. The proposed approach is applied to a wide variety of geographical areas from Landsat 7 Enhanced Thematic Mapper Plus (ETM+) multispectral data including arid and desert land, mountainous land, and plain area. Furthermore, a reference land-cover map from National Land Cover Data 2001 of USA is used as the ground reference for the accuracy assessment of the proposed method. Results analysis shows better performance of the proposed method in all study sites compared with the other spectral indices and the other methods. In addition, the proposed structural feature has shown promising results compared with the spectral indices when used in its own.

Extraction of Urban Areas From Polarimetric SAR Imagery

Polarimetric synthetic aperture radar (PolSAR) images are extensively used for land-use/land-cover (LULC) classification. One of the important issues in radar remote sensing is urban area detection, where difficulties are found because of its heterogeneity. In this paper, we are interested in urban area detection using PolSAR images which allow us detecting the scattering mechanisms by the use of polarimetric target decompositions methods. We propose in this paper two methods: in the first one, we use the powers of Yamaguchi four-component decomposition and in the second method, we use the coefficients of PolSAR covariance matrix calculated in the circular polarization basis. We added in each method the complex Wishart maximum likelihood (ML) classifier to refine the classification results. To validate both methods, we used two PolSAR images acquired in C-band by RADARSAT-2 satellite over the El Hamiz city in Algeria and San Francisco Bay. The two proposed algorithms give accurate results in both test sites, with superiority of the circular condition method.

A General Framework for Urban Area Extraction Exploiting Multiresolution SAR Data Fusion

This work is devoted to the presentation of a general framework for multiresolution synthetic aperture radar (SAR) data fusion for the purpose of urban area extraction. Within this framework, prerequisites for a reasonable analysis of SAR data from different sensors and spatial resolutions as well as the state of the art of fusion techniques are discussed. Furthermore, several fusion approaches on the pixel, feature, and decision level are applied on multiscale SAR data sets in a uniform experimental setup over four test sites: 1) Sao Paulo (Brazil); 2) Beijing; 3) Guangzhou; and 4) Shanghai (People’s Republic of China). The accuracy of the resulting urban maps is assessed quantitatively via comparison against manually generated reference data sets. Furthermore, advantages and drawbacks of the applied fusion methods are evaluated.

Global mapping of urban built-up areas of year 2014 by combining MODIS multispectral data with VIIRS nighttime light data

ABSTRACTAn improved methodology for the extraction and mapping of urban built-up areas at a global scale is presented in this study. The Moderate Resolution Imaging Spectroradiometer (MODIS)-based multispectral data were combined with the Visible Infrared Imager Radiometer Suite (VIIRS)-based nighttime light (NTL) data for robust extraction and mapping of urban built-up areas. The MODIS-based newly proposed Urban Built-up Index (UBI) was combined with NTL data, and the resulting Enhanced UBI (EUBI) was used as a single master image for global extraction of urban built-up areas. Due to higher variation of the EUBI with respect to geographical regions, a region-specific threshold approach was used to extract urban built-up areas. This research provided 500-m-resolution global urban built-up map of year 2014. The resulted map was compared with three existing moderate-resolution global maps and one high-resolution map in the United States. The comparative analysis demonstrated finer details of the urban built-up cover estimated by the resultant map.

Use of an inside buffer method to extract the extent of urban areas from DMSP/OLS nighttime light data in North China

Defense Meteorological Satellite Program (DMSP)/Operational Linescan System (OLS) nighttime imagery provides a valuable data source for mapping urban areas. However, the spatial extents of large cities are often overestimated because of the effect of over-glow from nighttime light if a fixed thresholding technique is used. In the work reported here, an inside buffer method was developed to solve this issue. The method is based on the fact that the area overestimated is proportional to the extent of the lit area if a fixed threshold is used to extract urban areas in a region/county. Using this method, the extents of urban areas in North China were extracted and validated by interpretations from Landsat Thematic Mapper images. The results showed that the lit areas had a significant linear relationship with the urban areas for 120 representative cities in North China in 2000, with an R2 value of over 0.95. This demonstrates that the inside buffer method can be used to extract urban areas. The validation results showed that the inside buffer model developed in 2000 can be directly used to extract the extent of urban areas using more recent nighttime light imagery. This is of great value for the timely updating of urban area databases in large regions or countries.

Analysis on the optimal system parameters of space-borne SAR for urban areas extraction

With rapid development, synthetic aperture radar (SAR), such as ERS (C-band), PALSAR (L-band), Cosmo-SkyMed (X-band) and TerraSAR (X-band), has offered abundant data source for urban environment research. The gray level co-occurrence matrix (GLCM) is used in this paper to extract urban areas texture features, and the performance of images with different band frequencies (C-band, L-band and X-band), different polarization modes (HH, HV, VH and VV) and different spatial resolutions (1m, 5m and 12m) are analyzed and compared. The results indicate that for different band frequencies, images in X-band perform better than C- and L-band. While for images with the same band frequency, polarization and spatial resolution play significant roles in urban areas extraction. Furthermore, we consider the sensitivity of GLCM method with respect to texture window size and to image resolution, and the conclusion can be drawn that high resolution images need large window sizes.

URBAN AREA EXTRACTION USING AIRBORNE X-BAND FULLY POLARIMETRIC PI-SAR2 IMAGERY

Abstract. In this paper, we present a method to extract urban areas from X-band fully polarimetric synthetic aperture radar (SAR) data. It is known that very high resolution (VHR) SAR can extract buildings, but it requires more processes to map urban areas that should include other objects. The proposed method is mainly composed of two classifications. One classification uses total power of scattering and volume scattering derived by using four component decomposition method with correction of the polarization orientation angle (POA) effect. The other classification uses polarimetric coherency between SHH and SVV . The two results are intersected and final urban areas are extracted after post-classification processing. We applied the proposed method to airborne X-band fully polarimetric SAR data of Polarimetric and Interferometric Airborne Synthetic Aperture Radar System (Pi-SAR2), developed by the National Institute of Information and Communications Technology (NICT), Japan. The validation show that the results of the proposed method were acceptable, with an overall accuracy of approximately 80 to 90% at 100-m spatial scale.

Application of a normalized difference impervious index (NDII) to extract urban impervious surface features based on Landsat TM images

The ecological conditions of urban areas have been deteriorating in some aspects due to population growth and increasing expansion, with significant effects on human health. Impervious surface areas are an important indicator of urban ecological environmental change, therefore quickly and accurately estimating impervious surface areas is essential to monitoring the urban dynamics of change and human activities and their effects on urban environmental quality. Currently, few methods that are applied in estimating urban impervious surfaces are capable of providing results quickly and accurately. Accordingly, this study proposes a new index, named the normalized difference impervious index (NDII), based on Landsat TM images, which uses the visible (red, green, and blue) and thermal bands. The index was used to extract the impervious surface areas of Nanjing city, Jiangsu Province, China, and we assume that the average value of five times strict supervised classification is the true value of impervious surfaces. A combination of red and thermal bands extracted the impervious surfaces with a producer’s accuracy of 86.9%, a user’s accuracy of 84.6%, an overall accuracy of 91.4%, and a kappa coefficient of 0.8. The accuracy is 87.7% validated by high-resolution images. This method can rapidly extract urban impervious surface areas with promising accuracy.

Multitemporal settlement and population mapping from Landsat using Google Earth Engine

As countries become increasingly urbanized, understanding how urban areas are changing within the landscape becomes increasingly important. Urbanized areas are often the strongest indicators of human interaction with the environment, and understanding how urban areas develop through remotely sensed data allows for more sustainable practices. The Google Earth Engine (GEE) leverages cloud computing services to provide analysis capabilities on over 40 years of Landsat data. As a remote sensing platform, its ability to analyze global data rapidly lends itself to being an invaluable tool for studying the growth of urban areas. Here we present (i) An approach for the automated extraction of urban areas from Landsat imagery using GEE, validated using higher resolution images, (ii) a novel method of validation of the extracted urban extents using changes in the statistical performance of a high resolution population mapping method. Temporally distinct urban extractions were classified from the GEE catalog of Landsat 5 and 7 data over the Indonesian island of Java by using a Normalized Difference Spectral Vector (NDSV) method. Statistical evaluation of all of the tests was performed, and the value of population mapping methods in validating these urban extents was also examined. Results showed that the automated classification from GEE produced accurate urban extent maps, and that the integration of GEE-derived urban extents also improved the quality of the population mapping outputs.

Urban Built-Up Area Extraction from Landsat TM/ETM+ Images Using Spectral Information and Multivariate Texture

Urban built-up area information is required by various applications. However, urban built-up area extraction using moderate resolution satellite data, such as Landsat series data, is still a challenging task due to significant intra-urban heterogeneity and spectral confusion with other land cover types. In this paper, a new method that combines spectral information and multivariate texture is proposed. The multivariate textures are separately extracted from multispectral data using a multivariate variogram with different distance measures, i.e., Euclidean, Mahalanobis and spectral angle distances. The multivariate textures and the spectral bands are then combined for urban built-up area extraction. Because the urban built-up area is the only target class, a one-class classifier, one-class support vector machine, is used. For comparison, the classical gray-level co-occurrence matrix (GLCM) is also used to extract image texture. The proposed method was evaluated using bi-temporal Landsat TM/ETM+ data of two megacity areas in China. Results demonstrated that the proposed method outperformed the use of spectral information alone and the joint use of the spectral information and the GLCM texture. In particular, the inclusion of multivariate variogram textures with spectral angle distance achieved the best results. The proposed method provides an effective way of extracting urban built-up areas from Landsat series images and could be applicable to other applications.

Normalization of time series DMSP-OLS nighttime light images for urban growth analysis with Pseudo Invariant Features

Previous studies demonstrated that DMSP-OLS stable nighttime light data are useful data source for delineating urban areas. However, the nighttime light data acquired in different years are not directly comparable, due to the variations in atmospheric condition from year to year and the periodic change in satellite sensor. This makes it difficult to use the time series nighttime light data for urban growth analysis. This paper presents a novel technique for normalizing time series DMSP/OLS nighttime light data and deriving urban detection threshold using Pseudo Invariant Features (PIFs). Our technique consists of three steps: (1) estimate an optimal threshold value for urban area detection for a reference year, when high resolution image data are available for some local areas. (2) Based on the irreversible nature of urbanization process, determine a set of PIFs, which are deemed as urban areas and did not exhibit significant change in nighttime light condition during the study period. (3) Normalize the time series DMSP-OLS data sets based on the PIFs and linear regression, determine optimal threshold values for urban area detection for all years based on the reference year threshold value, and extract urban areas accordingly. This technique was successfully applied to time series DMSP-OLS nighttime light images of the Central Liaoning region in China. Patterns of this urban agglomeration's spatial–temporal evolution from 2000 to 2010 were mapped and analyzed. The reliability and spatial accuracy of this technique were evaluated with multitemporal Landsat TM images. The technique was proved accurate and effective.