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

When monitoring urban areas from space, change detection based on satellite images is one of the most heavily investigated topics. In the case of monitoring change in 2D, one major shortcoming consists in the lack of height change detection. Thereby only changes related to reflectance values or local textures changes can be detected. However, changes in the vertical direction are completely ignored. In this paper we present a new 3D change detection approach. We focus our work on the detection of changes using Digital Surface Models (DSMs) which are generated from stereo imagery acquired at two different epochs. The so called “difference image” method is adopted in this framework where the final DSM is subtracted from the initial one to get the height difference. Our approach is a two-step approach. While in the first step, reduction of the noise effects (coming from registration noise, matching artifacts caused by the DEM generation procedures, etc), the second one exploits the rectangular property of the building shape in order to provide an accurate urban area monitoring change map. The method is tested, evaluated and compared with manually extraction results over the city centre of Munich in Germany

/pdf/automatic-3d-change-detection-based-on-optical-satellite-3ue1imuh7x.pdf

Automatic 3d change detection based on optical satellite stereo imagery

Because of the all-weather and all-time data acquisition capability, high resolution space borne synthetic aperture radar (SAR) plays an important role in remote sensing applications like earth mapping. However, the visual interpretation of SAR images is usually difficult, especially for urban areas. This paper shows a method for visual interpreting SAR images by means of optical and SAR images simulated from digital elevation models (DEM), which are derived from LiDAR data. The simulated images are automatically geocoded and enable a direct comparison with the real SAR image. An application for the simulation concept is presented for the city center of Munich where the comparison to the TerraSAR-X data shows good similarity. The simulated optical image can be used for direct and quick identification of objects in the corresponding SAR image. Additionally, simulated SAR image can separate multiple reflections mixed in the real SAR image, thus enabling easier interpretation of an urban scene.

/pdf/interpretation-of-sar-images-in-urban-areas-using-simulated-1b1v1aozxv.pdf

Interpretation of SAR images in urban areas using simulated optical and radar images

This paper proposes a novel algorithm for automatic Digital Terrain Model (DTM) generation from high resolution CARTOSAT-1 satellite images generating accurate and reliable results. It consists of two major steps: Generation of Digital Surface Models (DSM) from CARTOSAT-1 stereo scenes and hierarchical image filtering for DTM generation.
High resolution stereo satellite imagery is well suited for the creation of DSM. A system for automated and operational DSM and orthoimage generation based on CARTOSAT-1 imagery is presented, with emphasis on fully automated georeferencing. It processes level-1 stereo scenes using the rational polynomial coefficients (RPC) universal sensor model. A novel, automatic georeferencing method is used to derive a high quality RPC correction from lower resolution reference dataset, such as Landsat ETM+ Geocover and SRTM C Band DSM. Digital surface models (DSM) are derived from dense stereo matching and forward intersection and subsequent interpolation into a regular grid.
In the second step which is dedicated to DSM filtering, the DSM pixels are classified into ground and non-ground using the algorithm motivated from the gray-scale image reconstruction to suppress unwanted elevated pixels. In this method, non-ground regions, i.e., 3D objects as well as outliers (very low or very high elevated regions) are hierarchically separated from the ground regions.
The generated DTM is qualitatively and quantitatively evaluated. Profiles in the image as well as a comparison of the derived DTM to the original data and ground truth data are presented. The ground truth data consist of a high quality DTM produced from aerial images which is generated by the Institut Cartografic de Catalunya (ICC) in Barcelona, Spain. The evaluation result indicates that almost all non-ground objects regardless of their size are eliminated and the iterative approach gives good results in hilly as well as smooth residential areas.

/pdf/automatic-generation-of-digital-terrain-models-from-cartosat-3wlrzgyki1.pdf

Automatic generation of digital terrain models from Cartosat-1 stereo images

Multisensor data fusion is one of the most common and popular remote sensing data classification topics by considering a robust and complete description about the objects of interest. Furthermore, deep feature extraction has recently attracted significant interest and has become a hot research topic in the geoscience and remote sensing research community. A deep learning decision fusion approach is presented to perform multisensor urban remote sensing data classification. After deep features are extracted by utilizing joint spectral–spatial information, a soft-decision made classifier is applied to train high-level feature representations and to fine-tune the deep learning framework. Next, a decision-level fusion classifies objects of interest by the joint use of sensors. Finally, a context-aware object-based postprocessing is used to enhance the classification results. A series of comparative experiments are conducted on the widely used dataset of 2014 IEEE GRSS data fusion contest. The obtained results illustrate the considerable advantages of the proposed deep learning decision fusion over the traditional classifiers.

/pdf/deep-learning-decision-fusion-for-the-classification-of-jq5di9uxx4.pdf

Deep learning decision fusion for the classification of urban remote sensing data

Automatic crowd detection in aerial images is certainly a useful source of information to prevent crowd disasters in large complex scenarios of mass events. A number of publications employ regression-based methods for crowd counting and crowd density estimation. However, these methods work only when a correct manual count is available to serve as a reference. Therefore, it is the objective of this paper to detect high-density crowds in aerial images, where counting– or regression–based approaches would fail. We compare two texture–classification methodologies on a dataset of aerial image patches which are grouped into ranges of different crowd density. These methodologies are: (1) a Bag–of–words (BoW) model with two alternative local features encoded as Improved Fisher Vectors and (2) features based on a Gabor filter bank. Our results show that a classifier using either BoW or Gabor features can detect crowded image regions with 97% classification accuracy. In our tests of four classes of different crowd-density ranges, BoW–based features have a 5%–12% better accuracy than Gabor.

https://www.mdpi.com/2072-4292/8/6/470/pdf

Peter Reinartz

Papers

Automatic 3d change detection based on optical satellite stereo imagery

Interpretation of SAR images in urban areas using simulated optical and radar images

Automatic generation of digital terrain models from Cartosat-1 stereo images

Deep learning decision fusion for the classification of urban remote sensing data

Detection of High-Density Crowds in Aerial Images Using Texture Classification