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

One of the most sophisticated recent data fusions in remote sensing has involved the use of LiDAR and hyperspectral data. Feature-level fusion strategy is applied based on extraction of several recent proposed spectral and structural features from hyperspectral and LiDAR data, respectively. In order to optimize classification performance, feature selection and determination of classifier parameters are carried out simultaneously. Referring to complexity of search space, cuckoo search as a powerful metaheuristic optimization algorithm is applied. Experiments show that the proposed method can improve the overall classification accuracy up to 6% with respect to only hyperspectral imagery. The obtained results show the classification improvement for the tree, residential and commercial classes is about 4%, 21% and 35%, respectively.

https://tandfonline.com/doi/pdf/10.1080/22797254.2017.1314179

A metaheuristic feature-level fusion strategy in classification of urban area using hyperspectral imagery and LiDAR data

IRS-P5 Cartosat-1 high resolution stereo satellite imagery is well suited for the creation of digital surface models (DSM). A system for highly automated and operational DSM and orthoimage generation based on IRS-P5 Cartosat-1 imagery is presented, with an emphasis on automated processing and product quality. The proposed system processes IRS-P5 level-1 stereo scenes using the rational polynomial coefficients (RPC) universal sensor model. The described method uses an RPC correction based on DSM alignment instead of using reference images with a lower lateral accuracy, this results in improved geolocation of the DSMs and orthoimages. Following RPC correction, highly detailed DSMs with 5 m grid spacing are derived using Semiglobal Matching. The proposed method is part of an operational Cartosat-1 processor for the generation of a high resolution DSM.
Evaluation of 18 scenes against independent ground truth measurements indicates a mean lateral error (CE90) of 6.7 meters and a mean vertical accuracy (LE90) of 5.1 meters.

/pdf/automatic-generation-of-high-quality-dsm-based-on-irs-p5-4mvhez4gcl.pdf

Automatic Generation of High Quality DSM Based on IRS-P5 Cartosat-1 Stereo Data

Accurate monitoring of urban areas using remote sensing data requires reliable change detection techniques. Nevertheless, while most of the changes are optically visible and easily detectable by an expert user, automatic processes are quite difficult to develop. That is why, the interpretation of changes has remained up-to-now visual in most operational applications in remote sensing. This paper provides an automatic approach for 3D change detection based on the joint use of the height and spatial information. In fact, when dealing with urban areas, one possibility to cope with the automatic growth monitoring is the exploitation of the height information relative to the different man-made objects that exist in the scene. The subtraction of Digital Surface Models (DSMs), acquired at different epochs, should thus provide a valuable information about the 3D urban changes occurred in the studied area. However, when at least one of the DSMs presents some artifacts, a simple DSM subtraction could result also in the detection of virtual changes. To remove these virtual changes, we propose in this work to include, in addition to the height information, some shape features that could be of a great help in describing the geometry of the constructed or demolished man-made structures. After that, the Support Vector Machine (SVM) classifier is used to differentiate real from virtual changes. Evaluation of the proposed approach in terms of completeness, correctness, overall accuracy, etc has been performed proving its efficiency and relatively high accuracy.

/pdf/automatic-urban-area-monitoring-using-digital-surface-models-6eww7xbuky.pdf

Automatic urban area monitoring using digital surface models and shape features

Hyperspectral unmixing is a sub pixel classification method which aims at recovering fraction and type of materials mixed in a single pixel. This work addresses the unmixing problem from the compressive sensing point of view by using overcomplete dictionaries enabling automatization of the process. However, overcomplete dictionaries of spectra are highly coherent which might confuse the final unmixing result. To deal with this problem we propose the use of differentiated spectra for coherence reduction. In this paper we study the approximation error for the proposed method as well as the correctness of the material detection.

/pdf/on-the-use-of-overcomplete-dictionaries-for-spectral-14ujvg7y3t.pdf

On the use of overcomplete dictionaries for spectral unmixing

In the method for geo-referencing of optical remote sensing images of an area of the earth's surface, the geo-referencing is corrected based on an SAR image which is geo-referenced.

Peter Reinartz

Papers

A metaheuristic feature-level fusion strategy in classification of urban area using hyperspectral imagery and LiDAR data

Automatic Generation of High Quality DSM Based on IRS-P5 Cartosat-1 Stereo Data

Automatic urban area monitoring using digital surface models and shape features

On the use of overcomplete dictionaries for spectral unmixing

Method for geo-referencing of optical remote sensing images