Giovanna Trianni

Improved VHR Urban Area Mapping Exploiting Object Boundaries

In this paper, a mapping procedure exploiting object boundaries in very high-resolution (VHR) images is proposed. After discrimination between boundary and nonboundary pixel sets, each of the two sets is separately classified. The former are labeled using a neural network (NN), and the shape of the pixel set is finely tuned by enforcing a few geometrical constraints, while the latter are classified using an adaptive Markov random field (MRF) model. The two mapping outputs are finally combined through a decision fusion process. Experimental results on hyperspectral and satellite VHR imagery show the superior performance of this method over conventional NN and MRF classifiers.

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.

Semi-automatic choice of scale-dependent features for satellite SAR image classification

In this work we compare two different approaches to the use of multiple scales in the classification process of satellite SAR images. These are (I) the multi-scale co-occurrence texture analysis and (II) the semivariogram approach. Moreover, we propose a scheme for optimizing the co-occurrence window size and the semivariogram lag distances in terms of classification accuracy performance. To improve the results even further, we introduce a methodology to compute the co-occurrence features with a window consistent with the local scale, provided by the semivariogram analysis. Examples of satellite SAR image segmentation for urban area characterization are shown to validate the procedure.

Urban Mapping in Landsat Images Based on Normalized Difference Spectral Vector

In the last decades the number of natural and anthropic changes affecting population worldwide has raised dramatically. This fact, coupled with the increasing world population living in urban areas, requires the development of a detailed and reliable map of global urban extent. This letter reports on a new approach for urban mapping from Landsat images, based on the Normalized Difference Spectral Vector (NDSV). This spectral transformation allows the creation of a normalized signature that becomes peculiar of each land cover class within the scene. The urban extent classification is obtained by analyzing the NDSV data in conjunction with a Spectral Angle Mapper (SAM) based classifier. The experiments presented in this letter show the effectiveness of the proposed technique in detecting urban areas in extremely different environments. The results of the proposed methodology have been compared with the ones obtained by classifying the NDSV using other classifiers [namely, maximum likehood (ML) and support vector machines (SVM)], and also to the results obtained by classifying the calibrated data using the ML, SVM and SAM classifiers. The NDSV+SAM approach has provided the best results, with an overall accuracy of 97%.

Advanced processing of hyperspectral images

Hyperspectral imaging offers the possibility of characterizing materials and objects in the air, land and water on the basis of the unique reflectance patterns that result from the interaction of solar energy with the molecular structure of the material. In this paper, we provide a seminal view on recent advances in techniques for hyperspectral data processing. Our main focus is on the development of approaches able to naturally integrate the spatial and spectral information available from the data. Special attention is paid to techniques that circumvent the curse of dimensionality introduced by high-dimensional data spaces. Experimental results, focused in this work on a specific case-study of urban data analysis, demonstrate the success of the considered techniques. This paper represents a first step towards the development of a quantitative and comparative assessment of advances in hyperspectral data processing techniques.

Scaling up to National/Regional Urban Extent Mapping Using Landsat Data

This paper describes a methodology to extract a consistent human settlement extent layer using Landsat data and its implementation in the Google Earth Engine platform. The approach allows the extraction of human settlement extents by means of the existing Landsat 5 and 7 data sets, allowing to check their evolution at 30-m spatial resolution. Since human settlements are the main proxy to people geographical distribution and to building locations, this layer may serve as a mean to disaggregate people/building counts at the regional/national level. The approach is tested in several parts of the world against existing ground truth data at the same spatial resolution in Brazil and China, as well as against extents manually extracted from VHR data in three different geographical areas: 1) Brazil; 2) South East China; and 3) Indonesia.

Damage Detection from SAR Imagery: Application to the 2003 Algeria and 2007 Peru Earthquakes

This paper is focused on the improvement and further validation of a recently proposed approach for the joint use of radar satellite imagery of an area affected by a major disaster and ancillary data. The study was carried out at different sites on imagery of two different earthquakes occurred one in the Mediterranean coast of Algeria on May 21st, 2003, which severely affected the city of Boumerdes, and one in the Pacific Coast of Peru on August, 15th, 2007. The combination of different radar-extracted features results in very fuzzy classification of the damage patterns, far less detailed than what available using optical imagery. However, focused results using the above-mentioned ancillary data provide enough detail and precision to be comparable with them. In particular, quantized damage level at the block level is achieved at enough detail using ALOS/PALSAR data and thus validates the original idea.

Fast damage mapping in case of earthquakes using multitemporal SAR data

This work shows that earthquake damages in urban areas can be determined with an acceptable accuracy through the exploitation of multitemporal SAR data and ancillary information defining urban blocks. In this article, two different methodologies are presented: an unsupervised statistical analysis of the parameters of the models representing backscatterer intensity or coherence values for each block of the urban area under analysis, and a supervised approach which involves a multi-band/multi-temporal classification, performed using a Markov Random Field (MRF) classifier or a spatial Fuzzy ARTMAP (FA) classifier. The two procedures are compared by using ERS images acquired before and after the earthquake of Turkey in 1999.

Efficient Multi-Band Texture Analysis for Remotely Sensed Data Interpretation in Urban Areas

Texture analysis is a long-standing and important problem in image-based urban characterization. A variety of approaches and methods have been proposed in the past to deal with urban texture segmentation and classification. However, texture characterization is particularly complex when the image data is composed of several spectral bands at different wavelengths, as in the case of remotely sensed hyperspectral images, in which hundreds of spectral bands are often available. Such images have two domains which can be analyzed: the spectral domain and the spatial domain. In this paper, we develop a joint spatial/spectral classification approach for hyperspectral imagery which is shown to perform effectively in highly complex urban environments. Experimental results are provided using a hyperspectral scene with extensive ground-truth, collected over the town of Pavia in Italy. To address the high computational requirements of the algorithm, we also develop a parallel implementation which is tested in this work using a massively parallel supercomputer at NASAs Goddard Space Flight Center in Maryland.

Image interpretation through problem segmentation for very high resolution data

This paper is devoted to the definition of a methodology able to provide a rapid delineation of the contents of very high resolution scene of a large area. The steps in this procedure are aimed first at a simplification of the scene into areas of interest, and then to the recognition of the objects in these areas by means of their geometrical properties. Keywords-image interpretation, top-down segmentation, perceptual grouping.