There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

On robust estimation of the location parameter

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

For 11 days in February 2000, the Shuttle Radar Topography Mission (SRTM) successfully recorded by interferometric synthetic aperture radar (InSAR) data of the entire land mass of the earth between 60°N and 57°S. The data acquired in C- and X-bands are processed into the first global digital elevation models (DEMs) at 1 arc sec resolution, by NASA-JPL and German aerospace center (DLR), respectively. From the perspective of the SRTM-X system, we give in this paper an overview of the mission and the DEM production, as well as an evaluation of the DEM product quality. Special emphasis is on challenges and peculiarities of the processing that arose from the unique design of the SRTM system, which has been the first single-pass interferometer in space.

The shuttle radar topography mission—a new class of digital elevation models acquired by spaceborne radar

Detecting and locating buildings in satellite images has various application areas. Unfortunately, manually detecting buildings is hard and very time consuming. Therefore, in the literature several methods are proposed to automatically detect buildings. These methods can be divided into two main groups. In the first group, researchers used panchromatic or multispectral information to detect buildings. In the second group, researchers used DSM data to detect buildings. In this study, we propose two novel methods to detect buildings by combining the panchromatic and DSM data. The first method uses corner points extracted by Harris corner detection method. These corner points are used jointly with DSM data. Using a kernel based density estimation method, possible building locations are detected. In the second method, shadow of buildings are used in a similar way. We tested both methods on WorldView-2 images and DSM data generated from them.

/pdf/building-detection-using-local-features-and-dsm-data-44qajy1vjs.pdf

Building detection using local features and DSM data

. Image registration is required for different remote sensing applications, like change detection or image fusion. Since research studies have shown the outstanding absolute geometric accuracy of high resolution radar satellites images like TerraSAR-X, the importance of SAR images as source for geolocation enhancement has increased. Due to this fact, multi-sensor image to image registration of optical and SAR images can be used for the improvement of the absolute geometric processing and accuracy of optical images with TerraSAR-X as reference. In comparison to the common optical and SAR image registration methods the proposed method is a combination of intensity-based and feature-based approaches. The proposed method avoids the direct and often difficult detection of features from the SAR images. SAR-like templates are generated from features detected from the optical image. These templates are used for an intensity-based matching with the SAR image. The results of the matching process are ground control points, which are used for the estimation of translation parameters followed by a subpixel translation of the optical image. The proposed image registration method is tested for two pairs of TerraSAR-X and QuickBird images and one pair of TerraSAR-X andWorldView-2 images of a suburban area. The results show that with the proposed method the geometric accuracy of optical images can be enhanced.

/pdf/registration-of-optical-and-sar-satellite-images-based-on-2gdqqusmlg.pdf

Registration of optical and sar satellite images based on geometric feature templates

In this paper, we propose a cloud removal algorithm for scenes within a satellite image time series based on synthetization of the affected areas via sparse reconstruction. The high spectrotemporal dimensionality of time series allows applying pixel-based sparse reconstruction techniques efficiently, estimating the values below a cloudy area by observing the spectral evolution in time of pixels in cloud-free areas. The process implicitly compensates the overall atmospheric interactions affecting a given image, and it is possible even if only one acquisition is available for a given period of time. The dictionary, on the basis of which the data are reconstructed, is selected randomly from the available image elements in the time series. This increases the degree of automation of the process, if the area containing clouds and their shadows is given. Favorable comparisons with similar methods and applications to supervised classification and change detection show that the proposed algorithm restores images locally contaminated by clouds and their shadows in a satisfactory and efficient way.

Cloud Removal in Image Time Series Through Sparse Reconstruction From Random Measurements

The field of human population mapping is constantly evolving, leveraging the increasing availability of high-resolution satellite imagery and the advancements in the field of machine learning. In recent years, the emergence of global built-area datasets that accurately describe the extent, location, and characteristics of human settlements has facilitated the production of new population grids, with improved quality, accuracy, and spatial resolution. In this research, we explore the capabilities of the novel World Settlement Footprint 2019 Imperviousness layer (WSF2019-Imp), as a single proxy in the production of a new high-resolution population distribution dataset for all of Africa—the WSF2019-Population dataset (WSF2019-Pop). Results of a comprehensive qualitative and quantitative assessment indicate that the WSF2019-Imp layer has the potential to overcome the complexities and limitations of top-down binary and multi-layer approaches of large-scale population mapping, by delivering a weighting framework which is spatially consistent and free of applicability restrictions. The increased thematic detail and spatial resolution (~10 m at the Equator) of the WSF2019-Imp layer improve the spatial distribution of populations at local scales, where fully built-up settlement pixels are clearly differentiated from settlement pixels that share a proportion of their area with green spaces, such as parks or gardens. Overall, eighty percent of the African countries reported estimation accuracies with percentage mean absolute errors between ~15% and ~32%, and 50% of the validation units in more than half of the countries reported relative errors below 20%. Here, the remaining lack of information on the vertical dimension and the functional characterisation of the built-up environment are still remaining limitations affecting the quality and accuracy of the final population datasets.

https://www.mdpi.com/2072-4292/13/6/1142/pdf

High-Resolution Gridded Population Datasets: Exploring the Capabilities of the World Settlement Footprint 2019 Imperviousness Layer for the African Continent

Due to the dense sampling of spectral signatures of land covers, hyperspectral images have a better discrimination among similar ground cover classes than traditional remote sensing data. However, these images are usually composed of tens or hundreds of spectrally close bands, which result in high redundancy and great amount of computation time in hyperspectral image classifi cation. In addition, the large number of spectral bands, but limited availability of training samples creates the problem of Hughes phenomenon. Consequently, traditional classifi cation strategies have often limited performance in classifi cation of hyperspectral imagery. Referring to the limitation of single classifi ers in these situations, classifi er ensemble system may exhibit better performance. This paper presents a method for classifi cation of hyperspectral data based on two concepts of Band Clustering (BC) and Band Grouping (BG) through a Support Vector machine (SVM) ensemble system. The proposed method uses the BC\BG strategies to split data into few band portions. After this step, we applied SVM on each band cluster\group that is produced in previous step. Finally, Naive Bayes as a classifi er fusion method combines the decisions of SVM classifi ers. Experimental results show that the proposed method improves the classification accuracy in comparison to the standard SVM and to feature selection methods.

Peter Reinartz

Papers

Building detection using local features and DSM data

Registration of optical and sar satellite images based on geometric feature templates

Cloud Removal in Image Time Series Through Sparse Reconstruction From Random Measurements

High-Resolution Gridded Population Datasets: Exploring the Capabilities of the World Settlement Footprint 2019 Imperviousness Layer for the African Continent

Band Grouping versus Band Clustering in SVM Ensemble Classification of Hyperspectral Imagery