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

Digital elevation models (DEM) of high resolution and high quality are required for many applications like urban modeling, readiness for
catastrophes or disaster assessment. A good source for the derivation of such DEMs from any place in the world are very high resolution
(VHR) satellite stereo images as provided e.g. by Ikonos, QuickBird or WorldView. In this paper a method for the generation and
refinement of urban high resolution DEMs from VHR imagery is presented and evaluated. Urban DEMs generated from very high
resolution satellite imagery of ground sampling distances of about one meter are normally of resolutions of about three to ten meters. For
the above mentioned applications of urban DEMs such results are often too coarse. In this paper an advanced method for the generation
of dense digital elevation models is presented and discussed. The method is mainly based on dense stereo algorithms developed for
computer vision applications. It is adapted and optimized to earth observation requirements. In the paper the DEM generation together
with the additional refinement steps is presented and evaluated using very high resolution stereo imagery from Munich and Athens. The
generated DEMs are compared to ground truth data where available and the quality and efficiency of the algorithms are analyzed and
discussed.

/pdf/refinement-of-urban-digital-elevation-models-from-very-high-45wyyr2h6u.pdf

Refinement of urban digital elevation models from very high resolution stereo satellite images

Through the improvements of satellite sensor and matching technology, the derivation of 3D models from space borne stereo data obtained a lot of interest for various applications such as mobile navigation, urban planning, telecommunication, and tourism. The automatic reconstruction of 3D building models from space borne point cloud data is still an active research topic. The challenging problem in this field is the relatively low quality of the Digital Surface Model (DSM) generated by stereo matching of satellite data comparing to airborne LiDAR data. In order to establish an efficient method to achieve high quality models and complete automation from the mentioned DSM, in this paper a new method based on a model-driven strategy is proposed. For improving the results, refined orthorectified panchromatic images are introduced into the process as additional data. The idea of this method is based on ridge line extraction and analysing height values in direction of and perpendicular to the ridgeline direction. After applying pre-processing to the orthorectified data, some feature descriptors are extracted from the DSM, to improve the automatic ridge line detection. Applying RANSAC a line is fitted to each group of ridge points. Finally these ridge lines are refined by matching them or closing gaps. In order to select the type of roof model the heights of point in extension of the ridge line and height differences perpendicular to the ridge line are analysed. After roof model selection, building edge information is extracted from canny edge detection and parameters derived from the roof parts. Then the best model is fitted to extracted facade roofs based on detected type of model. Each roof is modelled independently and final 3D buildings are reconstructed by merging the roof models with the corresponding walls.

/pdf/automatic-model-selection-for-3d-reconstruction-of-buildings-4pp43k2jiv.pdf

Automatic Model Selection for 3D Reconstruction of Buildings from Satellite Imagary

Automatic Line-Based Registration of DSM and Hyperspectral Images

3D Building change detection has become a popular research topic along with the improvement of image quality and computer science. When only building changes are of interest, both the multi-temporal images and Digital Surface Models provide valuable but not comprehensive information in the change detection procedure. Therefore, in this paper, belief functions have been adopted for fusing information from these two sources.

/pdf/building-change-detection-in-satellite-stereo-imagery-based-1k2at3iem8.pdf

Building Change Detection in Satellite Stereo Imagery Based on Belief Functions

High resolution stereo satellite imagery is now well suited for the creation of digital surface models (DSM) in urban areas due to recent developments in data resolution, quality and collection capabilities. A system for highly automated and operational DSM and orthoimage generation based on WorldView-2 imagery is presented using dense matching methodology, with emphasis on the usage of tri-stereo data for the generation of optimized DSMs. Due to constraints given by the three images, which allow six different pair-wise matchings (including left and right matching of each pair), robust results containing only very few outliers can be generated. The proposed system processes level-1 stereo scenes using the rational polynomial coefficients (RPC) universal sensor model. The RPC are derived from orbit and attitude information and exhibit a lower absolute accuracy than the ground resolution of approximately 0.5 m. In order to use the images for orthorectification or DSM generation, a bias or affine RPC correction is required, which can be achieved through a bundle adjusment using further scenes of the covered area from different dates. Furthermore these DSMs can be used to generate higher level products like digital terrain models (DTM), extracted single 3D objects like buildings and for automatic 3D change detection analysis. DLR-IMF and GAF AG developed and implemented within a close co-operation an operational workflow which now provides operational services based on multi source tri-stereo satellite data. The DSM processing is shortly described, some results of generated DSMs are shown and also examples for higher level products are given in the paper.

/pdf/operational-generation-of-high-resolution-digital-surface-2dsvz5mqp0.pdf

Peter Reinartz

Papers

Refinement of urban digital elevation models from very high resolution stereo satellite images

Automatic Model Selection for 3D Reconstruction of Buildings from Satellite Imagary

Automatic Line-Based Registration of DSM and Hyperspectral Images

Building Change Detection in Satellite Stereo Imagery Based on Belief Functions

Operational Generation of High-Resolution Digital Surface Models from Commercial Tri-Stereo Satellite Data