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

Change analysis for remote sensing data taken at different times over urban areas provides meaningful information like the expansion of cities. This paper presents a method for the generation of a coregistered geocoded simulated SAR image using a LiDAR digital surface model (DSM) and the comparison to a real SAR image for the purpose of change detection. The DSM and metadata of the SAR image are used for the geocoding of the simulated image, while a line extraction and matching algorithm is used to compensate small shifts between the two images. Afterwards the shadow area in the simulated image is extracted and the corresponding mask is used to analyze the real SAR image in order to detect the changes. An application of the proposed concept is presented for the city centre of Munich where the comparison with the TerraSAR-X GEC product shows a good result. The detected positive changes (new buildings) are compared to a 3D change reference map and show a good correspondence.

/pdf/simulation-based-change-detection-between-dsm-and-high-3wwng0bfn0.pdf

Simulation Based Change Detection between DSM and High Resolution SAR Image

The interest in the joint use of remote sensing data from multiple sensors has been remarkably increased for classification applications. This is because a combined use is supposed to improve the results of classification tasks compared to single-data use. This paper addressed using of combination of hyperspectral and Light Detection And Ranging (LIDAR) data in classification field. This paper presents a new method based on the definition of a Multiple Classifier System on Hyperspectral and LIDAR data. In the first step, the proposed method applied some feature extraction strategies on LIDAR data to produce more information in this data set. After that in second step, Support Vector Machine (SVM) applied as a supervised classification strategy on LIDAR data and hyperspectal data separately. In third and final step of proposed method, a classifier fusion method used to fuse the classification results on hypersepctral and LIDAR data. For comparative purposes, results of classifier fusion compared to the results of single SVM classifiers on Hyperspectral and LIDAR data. Finally, the results obtained by the proposed classifier fusion system approach leads to higher classification accuracies compared to the single classifiers on hyperspectral and LIDAR data.

/pdf/classifier-fusion-of-hyperspectral-and-lidar-remote-sensing-3lydz2hta6.pdf

Classifier fusion of hyperspectral and lidar remote sensing data for improvement of land cover classifcation

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. In the first step, two change indicators are proposed by focusing on building changes. Both indicators have been projected to a sigmoid curve, in which both the concordance and discordance indexes are considered. In order to fuse the concordance and discordance indexes and further fuse the two change indicators, two belief functions are considered. One is the original Dempster-Shafer Theory (DST), and the most recent one is Dezert-Smarandache Theory (DSmT). This paper shows how these belief-based frameworks can help in building change detection problem. Besides using different belief functions in obtaining the global BBAs, four decision-making criteria are tested to extract final building change masks. The results have been validated by compared to the manually extracted change reference mask.

/pdf/building-change-detection-in-satellite-stereo-imagery-based-1na94jahdh.pdf

Building change detection in satellite stereo imagery based on belief functions

3D city models have a wide range of applications such as mobile navigation, urban planning, telecommunication, and tourism. The generation of high resolution Digital Surface Models (DSMs), in particular from airborne LIDAR data have found a major attraction of researchers in this field due to their high accuracy and high density of points. In this paper, a new approach is proposed for the generation of 3D models of buildings that are extracted from a high resolution DSM. Particularly the complex buildings containing several smaller building parts are discussed. The building parts are individually modeled by a projection-based method and merged to form the final 3D model. The following building parts are considered to be modeled in the proposed approach: (1) flat roof, (2) gable roof, (3) hipped roof, and (4) mansard-shaped roof buildings. The complex buildings are decomposed into several parts according to the number of existing ridge lines. The ridge line extraction begins with image reconstruction by geodesic morphology (Arefi and Hahn, 2005) extracting the pixels of the highest part of the building segment, i.e., local maxima. Next, a Random SAmple Consensus (RANSAC) (Hartley and Zisserman, 2004) based technique is used to fit straight lines to the ridge points. The pixels of the building part regarding to each ridge line are projected onto a plane which is defined based on ridge direction. According to the type of the roof, a 2D model is fitted to the projected points. The 2D model is converted back to 3D by extruding it orthogonally to the projection plane. After reconstructing 3D models for all building parts, they are merged to form the overall 3D model of the building.

/pdf/ridge-based-decomposition-of-complex-buildings-for-3d-model-2vbh5ts0nm.pdf

Ridge based decomposition of complex buildings for 3d model generation from high resolution digital surface models

This article describes several methods for traffic monitoring from airborne optical remote sensing data. These methods classify the traffic into free flowing traffic, traffic congestion and traffic jam. Furthermore a method is explained, which provides information about the average speed of dense traffic on a defined part of the road. All methods gather the information directly from image features, without the use of single vehicle detection.
The classification of the traffic is done by stacking at least three overlapping images on top of each other and calculating the standard deviation of the gray values of each overlying pixel. In addition to that a texture analysis is implemented to differentiate the traffic. The average speed of dense traffic is calculated employing disparities of two following images of the same scene.
All methods, which were presented in this article were tested on various data sets and compared with interactive measured reference data.
These methods will be applicable in combination with methods using single car detection in the ARGOS-Project (AiRborne wide area hiGh altitude mOnitoring System).

/pdf/traffic-monitoring-without-single-car-detection-from-optical-2slvhy9wry.pdf

Peter Reinartz

Papers

Simulation Based Change Detection between DSM and High Resolution SAR Image

Classifier fusion of hyperspectral and lidar remote sensing data for improvement of land cover classifcation

Building change detection in satellite stereo imagery based on belief functions

Ridge based decomposition of complex buildings for 3d model generation from high resolution digital surface models

Traffic Monitoring without single Car Detection from optical airborne Images