José A. Malpica

Dempster–Shafer Theory in geographic information systems: A survey

Abstract Since the information used in a Geographic Information System has a certain degree of uncertainly, in general classical mathematics models should not be applied to solve geographical problems computationally. Therefore, probabilistic or fuzzy-related methods should be considered, in order to model the behaviour of real problems that have to be solved by or with a Geographic Information System. In this paper, a review of the application of Dempster–Shafer Theory of Evidence—also called “belief functions”—in relation to Geographic Information System is given. The review will focus on classification as a way of fusing information in a Geographic Information System. Information fusion, for classification, represents the first step in the abstraction of information and a means of data mining, and both the advantages and limitations of the technique of the Theory of Evidence in comparison to other techniques are analysed.

A projection pursuit algorithm for anomaly detection in hyperspectral imagery

The main goal of this paper is to propose an innovative technique for anomaly detection in hyperspectral imageries. This technique allows anomalies to be identified whose signatures are spectrally distinct from their surroundings, without any a priori knowledge of the target spectral signature. It is based on an one-dimensional projection pursuit with the Legendre index as the measure of interest. The index optimization is performed with a simulated annealing over a simplex in order to bypass local optima which could be sub-optimal in certain cases. It is argued that the proposed technique could be considered as seeking a projection to depart from the normal distribution, and unfolding the outliers as a consequence. The algorithm is tested with AHS and HYDICE hyperspectral imageries, where the results show the benefits of the approach in detecting a great variety of objects whose spectral signatures have sufficient deviation from the background. The technique proves to be automatic in the sense that there is no need for parameter tuning, giving meaningful results in all cases. Even objects of sub-pixel size, which cannot be made out by the human naked eye in the original image, can be detected as anomalies. Furthermore, a comparison between the proposed approach and the popular RX technique is given. The former outperforms the latter demonstrating its ability to reduce the proportion of false alarms.

Hue Adjustment to IHS Pan-Sharpened IKONOS Imagery for Vegetation Enhancement

Fused or pan-sharpened IKONOS images are invaluable to the visual interpretation of large-area-scale applications. Frequently, the paramount objective is merely to obtain an image for visualization purposes, with no further image processing or analysis in mind. In such cases, the fused image should resemble reality as much as possible, with objects represented by their true colors at surface reflectance. In this letter, a technique for image fusion of IKONOS, or similar imagery, is proposed for when the main purpose of a specific image is vegetation visualization. The technique consists of a hue spectral adjustment scheme integrated with an intensity-hue-saturation transformation. Experimental evidence to support the technique is provided with a subset of IKONOS data available from the University of Alcalaacute campus. In the final fused image, deciduous and evergreen vegetation can be clearly differentiated. The high quality of the fused image can also be appreciated in relation to other types of cartographic objects; the quantitative evaluation of spectral and spatial information results in a high color correlation and excellent spatial information quality

Change detection of buildings from satellite imagery and lidar data

Geospatial objects change over time and this necessitates periodic updating of the cartography that represents them. Currently, this updating is done manually, by interpreting aerial photographs, but this is an expensive and time-consuming process. While several kinds of geospatial objects are recognized, this article focuses on buildings. Specifically, we propose a novel automatic approach for detecting buildings that uses satellite imagery and laser scanner data as a tool for updating buildings for a vector geospatial database. We apply the support vector machine (SVM) classification algorithm to a joint satellite and laser data set for the extraction of buildings. SVM training is automatically carried out from the vector geospatial database. For visualization purposes, the changes are presented using a variation of the traffic-light map. The different colours assist human operators in performing the final cartographic updating. Most of the important changes were detected by the proposed method. The method not only detects changes, but also identifies inaccuracies in the cartography of the vector database. Small houses and low buildings surrounded by high trees present significant problems with regard to automatic detection compared to large houses and taller buildings. In addition to visual evaluation, this study was checked for completeness and correctness using numerical evaluation and receiver operating characteristic curves. The high values obtained for these parameters confirmed the efficacy of the method.

Classification of Multispectral High-Resolution Satellite Imagery Using LIDAR Elevation Data

This paper studies the influence of airborne LIDAR elevation data on the classification of multispectral SPOT5 imagery over a semi-urban area; to do this, multispectral and LIDAR elevation data are integrated in a single imagery file composed of independent multiple bands. The Support Vector Machine is used to classify the imagery. A scheme of five classes was chosen; ground truth samples were then collected in two sets, one for training the classifier and the other for checking its quality after classification. The results show that the integration of LIDAR elevation data improves the classification of multispectral bands; the assessment and comparison of the classification results have been carried out using complete confusion matrices. Improvements are evident in classes with similar spectral characteristics but for which altitude is a relevant discrimination factor. An overall improvement of 28.3% was obtained, when LIDAR was included.

A Spatial Contextual Postclassification Method for Preserving Linear Objects in Multispectral Imagery

Classification of remote sensing multispectral data is important for segmenting images and thematic mapping and is generally the first step in feature extraction. Per-pixel classification, based on spectral information alone, generally produces noisy classification results. The introduction of spatial information has been shown to be beneficial in removing most of this noise. Probabilistic label relaxation (PLR) has proved to be advantageous using second-order statistics; here, we present a modified contextual probabilistic relaxation method based on imposing directional information in the joint probability with third-order statistics. The proposed method was tested in synthetic images and real images; the results are compared with a “Majority” algorithm and the classical PLR method. The proposed third-order method gives the best results, both visually and numerically.

The Combination of Three Statistical Methods for Visual Inspection of Anomalies in Hyperspectral Imageries

Outliers are important features that are of special interest to image analysts in their work. The objective of this paper is to show how several statistical techniques with different theoretical foundations can be successfully applied complementarily to detect anomalies in hyperspectral imageries. The methodology is shown in airborne hyperspectral imagery with 60 bands. The visual inspection of the last components of Principal Component Analysis (PCA), together with the analysis of the images provided by the Reed and Xiaoli Yu algorithm and projection pursuit algorithm, allows clear extraction of most of the anomalies, such as synthetic material of tennis court floors or metallic roofs of buildings. A discussion and comparison of the three methods is given.

Splines interpolation in high resolution satellite imagery

In this paper some insights into the behavior of interpolation functions for resampling high resolution satellite images are presented. Using spatial and frequency domain characteristics, splines interpolation performance is compared to nearest-neighbor, linear and cubic interpolation. It is shown that splines interpolation injects spatial information into the final resample image better than the other three methods. Splines interpolation is also shown to be faster than cubic interpolation when the former is implemented with the LU decomposition algorithm for its tridiagonal system of linear equations. Therefore, if the main purpose for high resolution satellite resampling is to obtain an optimal smooth final image, intuitive and experimental justifications are provided for preferring splines interpolation to nearest-neighbor, linear and cubic interpolation.

Region-growing segmentation of multispectral high-resolution space images with open software

Most cartographic work is made extracting features from aerial or space images. A first step in this work is segmenting the images in regions that represent, as close as possible, cartographic entities (e.g., roads, buildings, vegetation). Region-Growing segmentation is implemented in a multispectral image using an open source programming language. This segmentation method is analyzed for land used and land cover applications, and it is compared with classification-based segmentation, known as Fuzzy K-Means. Both algorithms, Region Growing and Fuzzy K-Means, are run in an aerial image with four spectral bands (red, green, blue, and near infrared). Depending on the scale, the values of the parameters of the algorithms can yield an under segmentation or over segmentation results. Advantages and disadvantages of both segmentation methods are provided.

Obtaining industrial experimental designs using a heuristic technique

There are several methods of obtaining orthogonal fractions of symmetrical and asymmetrical factorials, including Hadamard matrices, collapsing and replacing, and orthogonal arrays. The objective is to find the right permutations of levels of each factor in order to obtain uncorrelated main effects with a minimum number of runs. This leads to a combinatorial optimization problem. Simulated annealing is an optimization technique that has been successfully used to find a good solution for combinatorial optimization problems. By applying the computational technique of simulated annealing to orthogonal fractional factorial designs, we provide a method to obtain uncorrelated main effects for symmetrical and asymmetrical factorials.