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

Combinations of advanced driver assistance systems (ADAS) enabling semi-autonomous driving are now being brought to market. Recently developed ADAS are amongst others the adaptive break control, the lane keeping assist and the lane change support. The complexity in the development of these systems increases, as fully autonomous vehicles should become a reality within the next decade.
The use of airborne optical sensors can be an independent tool to validate ADAS operating at test sites or in real traffic. The German Aerospace Center (DLR) has developed an optical camera system which is installed on a helicopter for a variety of traffic monitoring applications. With this system, it is possible to track a single test vehicle and to monitor the vehicle with the surrounding traffic situation. The camera system can acquire high resolution images with 54Mpix and a frame rate below 12fps or 4k (Ultra-HD) videos with 25fps. In combination with a high-end GNSS/IMU system, the images and videos can be timely registered within milliseconds precision and georeferenced with an absolute accuracy better than one meter, i.e. the instantaneous position, timestamp and speed of the test and surrounding vehicles can be derived very accurate.
Additionally, the positions and speed of front and rear traffic can be determined automatically, which are necessary for the validation of ADAS. In combination with automatic image analysis tools, the road markings can be extracted, which allows the relative positioning of vehicles with respect to the road markings and the surrounding traffic within few centimetres. 
In this contribution, the potential of airborne optical imagery for the validation of ADAS is presented and demonstrated on example imagery and videos taken from motorways in Germany.

https://elib.dlr.de/96876/1/paper.final.pdf

Validation of advanced driver assistance systems by airborne optical imagery

This paper describes the contribution of the DLR team ranking 3rd in Track 1 of the 2020 IEEE GRSS Data Fusion Contest, with results ranking 2nd in Track 2 of the same contest being reported in a companion paper. The classifications are based on refinements of low-resolution MODIS labeling using available higher resolution Sentinel-1 and Sentinel-2 data. Results are initialized with a handcrafted decision tree integrating output from a random forest classifier, and subsequently boosted by detectors for specific classes.

/pdf/stepwise-refinement-of-low-resolution-labels-for-earth-2zabw6dpdc.pdf

Stepwise Refinement Of Low Resolution Labels For Earth Observation Data: Part 1

Multi-pedestrian tracking in aerial imagery has several applications such as large-scale event monitoring, disaster management, search-and-rescue missions, and as input into predictive crowd dynamic models Due to the challenges such as the large number and the tiny size of the pedestrians (eg, 4 x 4 pixels) with their similar appearances as well as different scales and atmospheric conditions of the images with their extremely low frame rates (eg, 2 fps), current state-of-the-art algorithms including the deep learning-based ones are unable to perform well In this paper, we propose AerialMPTNet, a novel approach for multi-pedestrian tracking in geo-referenced aerial imagery by fusing appearance features from a Siamese Neural Network, movement predictions from a Long Short-Term Memory, and pedestrian interconnections from a GraphCNN In addition, to address the lack of diverse aerial pedestrian tracking datasets, we introduce the Aerial Multi-Pedestrian Tracking (AerialMPT) dataset consisting of 307 frames and 44,740 pedestrians annotated We believe that AerialMPT is the largest and most diverse dataset to this date and will be released publicly We evaluate AerialMPTNet on AerialMPT and KIT AIS, and benchmark with several state-of-the-art tracking methods Results indicate that AerialMPTNet significantly outperforms other methods on accuracy and time-efficiency

AerialMPTNet: Multi-Pedestrian Tracking in Aerial Imagery Using Temporal and Graphical Features

Remote sensing applications like disaster or mass event monitoring need the acquired data and extracted information within a very short time span. Airborne sensors can acquire the data quickly and on-board processing combined with data downlink is the fastest possibility to achieve this requirement. For this purpose, a new low-cost airborne frame camera system has been developed at the German Aerospace Center (DLR) named 3K-camera. The pixel size and swath width range between 15 cm to 50 cm and 2.5 km to 8 km respectively. Within two minutes an area of approximately 10 km x 8 km can be monitored. Image data are processed onboard on five computers using data from a real time GPS/IMU system including direct georeferencing. Due to high frequency image acquisition (3 images/second) the monitoring of moving objects like vehicles and people is performed allowing wide area detailed traffic monitoring.

/pdf/real-time-airborne-monitoring-for-disaster-and-traffic-4ksbyfv66v.pdf

Real Time Airborne Monitoring for Disaster and Traffic Applications

Real-time monitoring of crowded regions has crucial importance to avoid overload of people in certain areas. Understanding dynamics of large people crowds can also help to estimate future status of public areas. In order to bring an automatic solution to the problem, herein we introduce four different approaches based on keypoint extraction from airborne images. Using four different keypoint extraction methods separately, we form four different probability density functions (pdf) which hold information about density of people. With our experimental results, we discuss the strengths and weaknesses of these methods in detail. Besides using four different keypoint extraction methods, we also introduce fusion approaches in order to increase the robustness of the algorithm. Our promising experimental results indicate possible usage of the algorithm on real-time on board applications.

Peter Reinartz

Papers

Validation of advanced driver assistance systems by airborne optical imagery

Stepwise Refinement Of Low Resolution Labels For Earth Observation Data: Part 1

AerialMPTNet: Multi-Pedestrian Tracking in Aerial Imagery Using Temporal and Graphical Features

Real Time Airborne Monitoring for Disaster and Traffic Applications

Performance assessment of automatic crowd detection techniques on airborne images