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

Traffic monitoring plays an important role in transportation management In addition, airborne acquisition enables a flexible and realtime mapping for special traffic situations eg mass events and disasters Also the automatic extraction of vehicles from aerial imagery is a common application However, many approaches focus on the target object only As an extension to previously developed car detection techniques, a validation scheme is presented The focus is on exploiting the background of the vehicle candidates as well as their color properties in the HSV color space Therefore, texture of the vehicle background is described by color co-occurrence histograms From all resulting histograms a likelihood function is calculated giving a quantity value to indicate whether the vehicle candidate is correctly classified Only a few robust parameters have to be determined Finally, the strategy is tested with a dataset of dense urban areas from the inner city of Munich, Germany First results show that certain regions which are often responsible for false positive detections, such as vegetation or road markings, can be excluded successfully

/pdf/validation-of-vehicle-candidate-areas-in-aerial-images-using-4b2kz8vf8t.pdf

Validation of Vehicle Candidate Areas in Aerial Images Using Color Co-Occurrence Histograms

MOMS-02 is the first representative of a new sensor generation, designed for the combined photogrammetric and thematic mapping of earth´s surface. MOMS-02 stereo data sets are observations of earth surfaces from three distinct view directions at the same illumination conditions. The time lack of only 40 seconds from forward the backward looking data take is neglectabel. Under this conditions it is possible to evaluate the reflectance differences between forward and backward looking stereo band, getting information on the anisotropy of the surface for each pixel. For the first time it is possible to investigate the surface property of anisotropic backscattering from space. The presented paper deals with aspects concerning the complementarity and synergy of multispectral and anisotropy classification approaches, comparing evaluations of multispectral and stereo bands of mode D data from the MOMS-02 Priroda mission. Mode D combines stereo data registration in the 21,4° off nadir looking bands 6 and 7 (panchromatic, 520-760 nm) with multispectral data registration in bands 1 (blue, 450 - 520 nm) and 4 (NIR, 770 - 810 nm).

The evaluation of spectral and angular signatures from MOMS-2/P mode D data sets an application case study for land use purposes

Tree species information is crucial in sectors such as forest management and nature conservation. It is often required over a large area. In this study, tree species classification was performed using hyperspectral data and the Digital Surface Model generated from DLR-3K aerial borne stereo camera System. In the classification step, pixel-based approach and the patch-based approach with Bag-of-Word (BoW) model were proposed and tested. The two approaches have been performed in the Kranzberg Forest near Munich, Germany. The comparison was taken in a statistical way. By using proper features combination, the pixel-based classification can achieve very high accuracy (Kappa $=0.95)$, while the patch-based method only has accuracy around 60%.

Tree Species Classification by Fusing of Very Highresoltuion Hyperspectral Images and 3K-DSM

The crowd density in public places increases in social
events. If an emergency occurs during such events, authorities should take urgent measures to prevent causalities. Therefore, crowd detection and analysis is a critical research area. Even though there are several studies on person detection from street or indoor cameras, these may not be directly used to detect or analyze the crowd formed from people. In this study, we approach
the problem using aerial images. We propose two novel methods to detect the crowd using spatial statistics. The first novel method is based on the first-order statistics. It uses the nearest neighbor relations for each person in the image. The second novel method is based on the second-order statistics. Here, the spatial position of persons are checked whether they are clustered or randomly
distributed. We test these two methods on a sample test image and provide performance measures.

/pdf/crowd-detection-in-airborne-images-using-spatial-point-18eeoq4r2f.pdf

Peter Reinartz

Papers

Validation of Vehicle Candidate Areas in Aerial Images Using Color Co-Occurrence Histograms

The evaluation of spectral and angular signatures from MOMS-2/P mode D data sets an application case study for land use purposes

Tree Species Classification by Fusing of Very Highresoltuion Hyperspectral Images and 3K-DSM

Crowd detection in airborne images using spatial point statistics

GMES Fast Track Land Service 2006-2008 - Production of European orthoimage coverage