Search

Higher level functionality in autonomous driving depends strongly on a precise motion estimate of the vehicle. Powerful algorithms have been developed. However, their great majority focuses on either binocular imagery or pure LIDAR measurements. The promising combination of camera and LIDAR for visual localization has mostly been unattended. In this work we fill this gap, by proposing a depth extraction algorithm from LIDAR measurements for camera feature tracks and estimating motion by robustified keyframe based Bundle Adjustment. Semantic labeling is used for outlier rejection and weighting of vegetation landmarks. The capability of this sensor combination is demonstrated on the competitive KITTI dataset, achieving a placement among the top 15. The code is released to the community., Accepted at IROS 2018

While motion planning techniques for automated vehicles in a reactive and anticipatory manner have already been widely presented, cooperative motion planning has only been addressed recently. For the latter, interaction between traffic participants is crucial. Consequently, simulations where other traffic participants follow simple behavioral rules can no longer beused for development and evaluation. To close this gap, we present a multi vehicle simulation framework. Conventional simulation agents, using a simple, rule-based behavior, are replaced by multiple instances of sophisticated behavior generation algorithms. Thus, development, test and simulative evaluation of cooperative planning approaches is facilitated. The framework is implemented using the Robot Operating System (ROS) and its code will be released open source.

Accurate traffic participant prediction is the prerequisite for collision avoidance of autonomous vehicles. In this work, we propose to predict pedestrians using goal-directed planning. For this, we infer a mixture density function for possible destinations. We use these destinations as the goal states of a planning stage that performs motion prediction based on common behavior patterns. The patterns are learned by a fully convolutional network operating on maps of the environment. We show that this entire system can be modeled as one monolithic neural network and trained via inverse reinforcement learning. Experimental validation on real world data shows the system's ability to predict both, destinations and trajectories accurately.

Trajectory and intention prediction of traffic participants is an important task in automated driving and crucial for safe interaction with the environment. In this paper, we present a new approach to vehicle trajectory prediction based on automatically generated maps containing statistical information about the behavior of traffic participants in a given area. These maps are generated based on trajectory observations using image processing and map matching techniques and contain all typical vehicle movements and probabilities in the considered area. Our prediction approach matches an observed trajectory to a behavior contained in the map and uses this information to generate a prediction. We evaluated our approach on a dataset containing over 14000 trajectories and found that it produces significantly more precise mid-term predictions compared to motion model-based prediction approaches., 6 Pages, 9 figures, submitted to IV 2018

Spontaneous low frequency oscillations (LFO) in functional imaging data have gained increased interest in the study of cognitive decline. Persons diagnosed with mild cognitive impairment (MCI) and Alzheimer’s disease (AD) display alterations in their amount of LFO in various brain regions. This is commonly interpreted as disruptions in the autoregulation of the cerebral microvascular system. In the present study LFO (0,07–0,11 Hz) were measured with 52-channel near-infrared spectroscopy (NIRS) in 61 healthy elderly persons (70–76 years), 54 MCI subjects (70–76 years) and 25 healthy young controls (21–48 years) during rest over the frontal and the parietal cortex. Both MCI and healthy elderly controls showed less LFO in the frontal cortex as compared to young subjects. For the parietal cortex a decrease in LFO could be observed for the MCI group in comparison to healthy elderly subjects. Correlations of more LFO with worse performance in neuropsychological tests point to compensatory processes. LFO measured with NIRS might be especially suited for longitudinal studies aiming at predicting cognitive decline.

While motion planning approaches for automated driving often focus on safety and mathematical optimality with respect to technical parameters, they barely consider convenience, perceived safety for the passenger and comprehensibility for other traffic participants. For automated driving in mixed traffic, however, this is key to reach public acceptance. In this paper, we revise the problem statement of motion planning in mixed traffic: Instead of largely simplifying the motion planning problem to a convex optimization problem, we keep a more complex probabilistic multi agent model and strive for a near optimal solution. We assume cooperation of other traffic participants, yet being aware of violations of this assumption. This approach yields solutions that are provably safe in all situations, and convenient and comprehensible in situations that are also unambiguous for humans. Thus, it outperforms existing approaches in mixed traffic scenarios, as we show in simulation.

Zusammenfassung Im Jahre 1888 trat Bertha Benz die erste Überlandfahrt in der Geschichte des Automobils an. 125 Jahre später wiederholte die Mercedes Benz S-Klasse S 500 Intelligent Drive diese historische Fahrt von Mannheim nach Pforzheim – selbständig, ohne Fahrereingriff und im realen Verkehr. Die Bertha-Benz-Route ist 103 km lang und zeichnet sich durch eine breite Vielfalt von zu bewältigenden Fahrsituationen aus, die repräsentativ für den heutigen Alltagsverkehr sind. Die Strecke beinhaltet die Innenstädte von Mannheim und Heidelberg sowie die Durchfahrung von 23 Ortschaften und kleineren Städten. Zu den Situationen, die ein autonomes Fahrzeug auf der Bertha-Benz-Route beherrschen muss, gehören z. B. Kreisverkehre, Kreuzungen mit und ohne Ampelanlagen, Zebrastreifen, Überholen von Radfahrern oder enge Ortsdurchfahrten mit entgegenkommendem Verkehr. Eine Besonderheit des vorgestellten Projektes war die ausschließliche Verwendung seriennaher Sensorik. Kameras und Radarsensoren in Verbindung mit einer präzisen digitalen Karte ermöglichten die Erfassung des Fahrzeugumfelds auch in komplexen Situationen. Dieser Artikel liefert eine Systemübersicht des Fahrzeugs. Er beschreibt die kamerabasierte Umgebungswahrnehmung, die verwendeten digitalen Karten und die kartenrelative Selbstlokalisierung sowie die Manöverplanung in komplexen Verkehrsszenarien.

The reliable prediction of traffic participants' trajectories is an important challenge for automated driving. Prediction methods that try to deal with this challenge need similarity measures for trajectories in order to evaluate the quality of their prediction. Currently there exists no commonly accepted similarity measure suitable for this task. In this paper we review common trajectory similarity measures and analyze them with regard to prediction evaluation. Further we introduce a new approach for synthesizing a hybrid measure that combines a set of similarity measures and provide a heuristic to determine the parameters for this approach.

Vision systems become more and more popular to be applied in monitoring tasks such as controlling traffic flows or for security issues. The analysis of target behavior is always based on its observed trajectory, which can be acquired by tracking approaches. Although the fashion of tracking-by-detection is favored by the research community, it still faces challenges like unexpected occlusion caused by background objects or other tracked targets, which can interfere the matching operation and result in tracking errors. In this paper, we propose a novel approach by aggregating prediction events within target groups and integrating a graph-modeling based stitching procedure to handle the above mentioned problems. The evaluation results on the UA-DETRAC benchmark demonstrated the state-of-the-art performance of our tracking approach.

Knowledge about the location of a vehicle is indispensable for autonomous driving. In order to apply global localisation methods, a pose prior must be known which can be obtained from visual odometry. The quality and robustness of that prior determine the success of localisation. Momo is a monocular frame-to-frame motion estimation methodology providing a high quality visual odometry for that purpose. By taking into account the motion model of the vehicle, reliability and accuracy of the pose prior are significantly improved. We show that especially in low-structure environments Momo outperforms the state of the art. Moreover, the method is designed so that multiple cameras with or without overlap can be integrated. The evaluation on the KITTI-dataset and on a proper multi-camera dataset shows that even with only 100--300 feature matches the prior is estimated with high accuracy and in real-time.

In this paper a semi-empirical method is presented to predict the NOX emission of a pilot stabilized, technically premixed gas turbine combustor for arbitrary combustor inlet conditions. The method is based on measurement data for a reference operation cycle and ISO ambient condition. A model based correction function is used to account for the change of NOX emission, which results from combustor inlet condition and/or operation cycle deviating from reference data. The proposed method assumes that a pilot stabilized, technically premixed flame can be simplistically modeled as two separate combustion regimes: An assumed perfectly premixed regime, and an assumed diffusion flame regime. The emission of the combustor is then modeled as a superposition of the emissions from both individual combustion regimes. The emissions from the diffusion flame regime are the dominant contribution, although only a comparably small share of fuel is burnt in this regime. The emission of the perfectly premixed combustion regime can be modeled as a sole function of flame temperature. On the other hand, the emissions from the diffusion regime are strongly affected by combustor inlet pressure and temperature, which are in turn a function of the gas turbine operation cycle and inlet conditions. To simplify matters, only the change in NOX emission from the diffusion regime, which results from deviation of combustor inlet pressure and/or temperature from values expected for a reference operation cycle and ISO ambient condition, is modeled. NOX emission data for this reference operation cycle is necessary experimental input for the method. The proposed method can — with minimum experimental input — predict the NOX emission of a pilot stabilized, technically premixed combustor with good accuracy for arbitrary engine operation cycles and inlet conditions. It is aimed at providing reliable NOX emission estimates without the need for time intensive CFD or expensive experimental investigations. Typical applications are the assessment of a gas turbine’s NOX potential for feasibility studies of new operation or engine concepts with a proven combustor design, and for NOX estimates for out-of-experience ambient or site conditions for existing engines.

The visual based tracking has been an active area among the research community in recent years. Its application can be broadly found in intelligent transportation systems like advanced driver assistance systems (ADAS) or autonomous vehicles. One objective is to monitor the trajectory and behavior of the vulnerable road users (VRUs), e.g., pedestrians and cyclists, to prevent the probable collisions. However, the tracking of VRUs is still challenging, especially in cases, where severe occlusion occurs and the tracker fails due to the abrupt change of object appearance. To tackle this problem we propose a new tracking approach leveraging the part based trackers, which are built based on correlation filters. In this method both the number and the size of part filters are adapted to the current appearance of the object, to eliminate the influence by occluded parts. Experimental results show that our tracker performs robust with respect to occlusions, especially in cases, where long term and severe occlusions appear. Due to a sophisticated design, a real time processing performance can also be achieved by our approach.

Stereo cameras are among the most promising sensors for automated driving. For their deployment, however, calibration should be automated and possible in-situ. We propose a restructuring of bundle adjustment into an incremental online calibration system. It allows us to estimate all observable camera parameters on the fly. Both simulations and experiments with real world cameras show its capability to calibrate stereo rigs in real time while driving. With this method, cameras can be employed with almost no calibration overhead. Only the non-observable parameter of scale has to be defined in advance.

Intelligent vehicles heavily rely on robust and accurate self-localization. Global navigation satellite systems (GNSS) are not reliable in urban environments due to multipath and shadowing effects. Vision-based localization offers a promising alternative. We present a high-precision six degrees of freedom self-localization method using multiple cameras covering the surrounding environment. First, a point feature map is created using images from a previous pass of the area to map. Thereafter, the map is used for high-precision localization in real-time. While localization, a rough prior estimate of the current pose is used to shrink the search space for feature matching by projecting mapped landmarks into current images. Then, stored observations of the projected landmarks are matched to actual observations and the egopose is estimated by back-projection error minimization. Thereby, our map structure provides mapped landmarks efficiently towards localization with multiple cameras. In real-world experiments we show that our approach provides reliable localization results while passing the mapped area in arbitrary orientation.

Rail wear measurement is a necessary task in railway infrastructure inspection. To acquire the wear amounts accurately with more continuous scanning data, a rail wear measurement method based on structured light scanning is proposed in this paper. The CAD model of the rail is converted into a point set, and the data registration is implemented by aligning the scanning data to the point cloud generated by the CAD model. On a cross section plane of the rail, the vertical and lateral wear amounts are calculated by the nearby points projected onto the plane. To verify the accuracy of wear measurement based on structured light scanning, the wear amounts calculated by laser scanning data are compared. For the comparison, an experiment is designed to ensure that the same plane is sliced in two different kinds of measurement. On the cross section plane, the wear amounts are calculated by the distances from these points to the 2D profile of the rail CAD model, and then the results are compared with those from laser scanning data for the accuracy evaluation. It indicates that the accuracy of the structured light scanning is sufficient for railway track wear measurement.

Apolipoprotein-E4 (APOE-E4) is a major genetic risk factor for developing Alzheimer’s disease (AD). The verbal fluency task (VFT), especially the subtask category fluency, has shown to provide a good discrimination between cognitively normal controls and subjects with AD. Interestingly, APOE-E4 seems to have no effect on the behavioral performance during a VFT in healthy elderly. Thus, the purpose of the present study was to reveal possible compensation mechanisms by investigating the effect of APOE-E4 on the hemodynamic response in non-demented elderly during a VFT by using functional near-infrared spectroscopy (fNIRS). We compared performance and hemodynamic response of high risk APOE-E4/E4, -E3/E4 carriers with neutral APOE-E3/E3 non-demented subjects (N = 288; 70–77 years). No difference in performance was found. APOE-E4/E4, -E3/E4 carriers had a decreased hemodynamic response in the right inferior frontal junction (IFJ) with a corresponding higher response in the left middle frontal gyrus (MFG) during category fluency. Performance was correlated with the hemodynamic response in the MFG. We assume a compensation of decreased IFJ brain activation by utilizing the MFG during category fluency and thus resulting in no behavioral differences between APOE-groups during the performance of a VFT.

Functional near-infrared spectroscopy (fNIRS) and vagus somatosensory evoked potentials (VSEP) show deviant patterns in subjects with Alzheimer’s disease (AD) compared to healthy controls. We now aimed at testing the predictive value of these methods in the early diagnosis of AD. The Vogel study is a prospective, observational, long-term follow-up study with three time points of investigation within 6 years. Residents of the city of Wurzburg born between 1936 and 1941 were recruited. Every participant underwent physical, psychiatric, and laboratory examinations, and performed an intense neuropsychological testing as well as VSEP and NIRS according to the published procedures. 604 subjects were included. Mean age of the participants was 73.9 ± 1.55 years. The most frequent pathological physical and laboratory examination results were observed for blood pressure (62%), body weight (54%), HbA1c (16%), cholesterol (42%), and homocysteine (69%). Comprehensive analysis of cognitive testing showed mild cognitive impairment (MCI) in 12.3% of the patients. Concurrent major depression was found in 6.6% of the patients. We observed a high rate of MCI and somatic comorbidity in our cohort. The high rate of vascular risk factors and depressive symptoms, all of which are known risk factors of AD, is consistent with the notion that there are multiple options to prevent or postpone the onset of AD in a geriatric population like the one of the Vogel studies.

Die E-Klasse steht seit jeher – neben vielen anderen Werten – auch fur Langstreckentauglichkeit. Die Ingenieure von Mercedes-Benz haben sich einiges einfallen lassen, damit es den Passagieren, im wahrsten Sinne des Wortes, rundherum gut geht. Ergonomie, Ablage-, Sitz- und Materialkonzept wurden nochmals verbessert.

Objective:To assess the utility of serum neurofilament for diagnosis and monitoring of primary progressive aphasia (PPA) variants.Methods:We investigated neurofilament light chain (NF-L) levels in blood of 99 patients with PPA (40 with nonfluent variant PPA [nfvPPA], 38 with semantic variant PPA [svPPA], 21 with logopenic variant PPA [lvPPA]) and compared diagnostic performance with that reached by CSF NF-L, phosphorylated neurofilament heavy chain (pNF-H), β-amyloid (Aβ1-42), tau, and phosphorylated tau. The longitudinal change of blood NF-L levels was measured and analyzed for correlation with functional decline and brain atrophy.Results:Serum NF-L is increased in PPA compared to controls and discriminates between nfvPPA/svPPA and lvPPA with 81% sensitivity and 67% specificity (cutoff 31 pg/mL). CSF NF-L, pNF-H, tau, phosphorylated tau, and Aβ1-42 achieved similar performance, and pNF-H was the only marker for discrimination of nfvPPA from svPPA/lvPPA. In most patients with nfvPPA and svPPA, but not lvPPA, serum NF-L increased within follow-up. The increase correlated with functional decline and progression of atrophy of the left frontal lobe of all patients with PPAs and the right middle frontal gyrus of patients with nfvPPA and svPPA.Conclusions:Blood level of NF-L can aid the differential diagnosis of PPA variants, especially in combination with CSF pNF-H. Because serum NF-L correlates with functional decline and atrophy in the disease course, it qualifies as an objective disease status marker. Extended follow-up studies with cases of known neuropathology are imperative.Classification of evidence:This study provides Class I evidence that in patients with PPA, blood levels of NF-L can distinguish the logopenic variant from the nonfluent/agrammatic and semantic variants.

We present an improved model for MRF-based depth upsampling, guided by image- as well as 3D surface normal features. By exploiting the underlying camera model we define a novel regularization term that implicitly evaluates the planarity of arbitrary oriented surfaces. Our method improves upsampling quality in scenes composed of predominantly planar surfaces, such as urban areas. We use a synthetic dataset to demonstrate that our approach outperforms recent methods that implement distance-based regularization terms. Finally, we validate our approach for mapping applications on our experimental vehicle., Comment: 6 pages, 6 figures

The rapid advances of transportation infrastructure have led to a dramatic increase in the demand for smart systems capable of monitoring traffic and street safety. Fundamental to these applications are a community-based evaluation platform and benchmark for object detection and multi-object tracking. To this end, we organize the AVSS2017 Challenge on Advanced Traffic Monitoring, in conjunction with the International Workshop on Traffic and Street Surveillance for Safety and Security (IWT4S), to evaluate the state-of-the-art object detection and multi-object tracking algorithms in the relevance of traffic surveillance. Submitted algorithms are evaluated using the large-scale UA-DETRAC benchmark and evaluation protocol. The benchmark, the evaluation toolkit and the algorithm performance are publicly available from the website http://detrac-db.rit.albany.edu.

Human detection is an important task for many autonomous robots as well as automated driving systems. The Regionlets detector was one of the best-performing approaches for pedestrian detection on the KITTI dataset during 2015. We analysed the Regionlets detector and its performance. This paper discusses the improvements in accuracy that were achieved by the different ideas of the Regionlets detector. It also analyses what the boosting algorithm learns and how this relates to the expectations. We found that the random generation of regionlet configurations can be replaced by a regular grid of regionlets. Doing so reduces the dimensionality of the feature space drastically but does not decrease detection performance. This translates into a decrease in memory consumption and computing time during training.

This paper describes an algorithm that enables a railway vehicle to determine its position in a track network. The system is based solely on onboard sensors such as a velocity sensor and a Global Navigation Satellite System (GNSS) sensor and does not require trackside infrastructure such as axle counters or balises. The paper derives a probabilistic modeling of the localization task and develops a sensor fusion approach to fuse the inputs of the GNSS sensor and the velocity sensor with the digital track map. We describe how we can treat ambiguities and stochastic uncertainty adequately. Moreover, we introduce the concept of virtual balises that can be used to replace balises on the track and evaluate the approach experimentally. This paper focuses on an accurate modeling of sensor and estimation uncertainties, which is relevant for safety critical applications.

In modern automated systems the usage of sensors with orthogonal measurement principles is indispensable for assuring a redundant system. The combination of laser scanners and cameras is particularly prevalent. To profit from the potential of fusing information from these sensors, the basic step is sensor registration. State of the art cross-calibration methods for laser scanners and cameras establish geometric correspondences for example by detecting checker-boards in size and form. However these approaches suffer from ambivalent features and are only usable if the laser scanner has a high scanning density. Therefore, we present a reconstruction-free and vision-based extrinsic calibration algorithm with distinct features, which was developed with special focus on low-density laser scanners and high measurement noise. Moreover, we contribute an evaluation methodology demonstrating the capability of our approach. Along with this paper, we publish the associated code.

Apolipoprotein-E4 (APOE-E4) is a major genetic risk factor for developing Alzheimer’s disease (AD). The verbal fluency task (VFT), especially the subtask category fluency, has shown to provide a good discrimination between cognitively normal controls and subjects with AD. Interestingly, APOE-E4 seems to have no effect on the behavioral performance during a VFT in healthy elderly. Thus, the purpose of the present study was to reveal possible compensation mechanisms by investigating the effect of APOE-E4 on the hemodynamic response in non-demented elderly during a VFT by using functional near-infrared spectroscopy (fNIRS). We compared performance and hemodynamic response of high risk APOE-E4/E4, -E3/E4 carriers with neutral APOE-E3/E3 non-demented subjects (N = 288; 70–77 years). No difference in performance was found. APOE-E4/E4, -E3/E4 carriers had a decreased hemodynamic response in the right inferior frontal junction (IFJ) with a corresponding higher response in the left middle frontal gyrus (MFG) during category fluency. Performance was correlated with the hemodynamic response in the MFG. We assume a compensation of decreased IFJ brain activation by utilizing the MFG during category fluency and thus resulting in no behavioral differences between APOE-groups during the performance of a VFT.

Nowadays railway vehicle speed sensors suffer from insufficient measurement accuracy. E. g. the Doppler radar is prone to adverse weather conditions while wheel speed sensors are not sufficiently robust against wheel slip and wheel wear. However, since velocity sensors are safety relevant components, it becomes clear that conventional sensors are not able to cover all the requirements for an everyday use.

The ever-increasing requirements on gas turbine efficiency, which are at least partially met by increasing firing temperatures, and the simultaneous demand for reduced emissions, necessitate much more accurate calculations of the combustion process and combustor wall temperatures. Thermocouples give locally very accurate measurements of these temperatures, but there is a practical limit to the amount of measurement points. Thermal paints are another established measurement technique, but are toxic and at the same time require dedicated, short-duration tests. Thermal History Paints (THPs) provide an innovative alternative to the aforementioned techniques, but so far only a limited number of tests has been conducted under real engine conditions. THPs are similar in their chemical and physical make-up to conventional thermographic phosphors which have been successfully used in gas turbine applications for on-line temperature detection before. A typical THP comprises of oxide ceramic pigments and a water based binder. The ceramic is synthesized to be amorphous and when heated it crystallizes, permanently changing the microstructure. The ceramic is doped with lanthanide ions to make it phosphorescent. The lanthanide ions act as atomic level sensors and as the structure of the material changes, so do the phosphorescent properties of the material. By measuring the phosphorescence the maximum temperature of exposure can be determined through calibration, enabling post operation measurements at ambient conditions. This paper describes a test in which THP was applied to an impingement-cooled front panel from a combustor of an industrial gas turbine. Since this component sees a wide range of temperatures, it is ideally suited for the testing of the measurement techniques under real engine conditions. The panel was instrumented with a thermocouple and thermal paint was applied to the cold side of the impingement plate. THP was applied to the hot-gas side of this plate for validation against the other measurement techniques and to evaluate its resilience against the reacting hot gas environment. The durability and temperature results of the three different measurement techniques are discussed. The results demonstrate the benefits of THPs as a new temperature profiling technique. It is shown that the THP exhibited greater durability compared to the conventional thermal paint. Furthermore, the new technology provided detailed measurements down to millimeters indicating local temperature variations and global variations over the complete component.

In this paper, we present the concepts and methods developed for the autonomous vehicle known as AnnieWAY, which is our winning entry to the 2011 Grand Cooperative Driving Challenge. We describe algorithms for sensor fusion, vehicle-to-vehicle communication, and cooperative control. Furthermore, we analyze the performance of the proposed methods and compare them with those of competing teams. We close with our results from the competition and lessons learned.

We present a wearable assistance system for visually impaired persons that perceives the environment with a stereo camera and communicates obstacles and other objects to the user. We develop our idea of combining perception on an increased level of scene understanding with acoustic feedback to obtain an intuitive mobility aid. We describe our core techniques of scene modelling, object tracking, and acoustic feedback and show in an experimental study how our system can help improving the mobility and safety of visually impaired users.

This paper presents a novel technique of stereo vision based on the combination of an omnidirectional camera and a perspective camera. The technique combines the 360° field of view of the omnidirectional camera with the long field of view of a perspective camera. We describe the setup of such a camera system and how it can be used to achieve 3D-position estimates. Furthermore, we develop a maximum likelihood approach and a Bayesian approach that are able to fuse monocular and binocular observations of the same object to estimate its position and movement and show how this technique can be applied successfully in the RoboCup MiddleSizeLeague.

Computational concepts of cognition, their implementation in complex autonomous systems, and their empirical evaluation are key techniques to understand and validate concepts of cognition and intelligence. In this paper we want to describe computational concepts of cognition that were successfully implemented in the domain of soccer playing robots and show the interactions between cognitive concepts, software engineering and real-time application development. Beside a description of the general concepts we will focus on aspects of perception, behavior architecture, and reinforcement learning.

The second preparation workshop for the Grand Cooperative Driving Challenge (GCDC) was held in Helmond, The Netherlands, in December 2009. Like the first workshop in May, it was organized excellently by TNO, the Dutch research organization which, together with HTAS, has initiated the GCDC. The main objective of the workshop was to discuss the rules and regulations with potential participants starting from a draft document provided by TNO. The workshop was attended by 80 researchers from different universities, knowledge institutes, and manufacturers from eighteen countries spread over four continents.

Seit zehn Jahren gibt es jahrlich die Weltmeisterschaft Robocup fur autonome, fusballspielende Roboter. Inzwischen sind der mechanische Aufbau der Roboter, die Sensorauswertung und Verhaltenssteuerung per Bordrechner so weit entwickelt, dass ein echtes Fusballspiel entstehen kann. Allerdings erfordert die Ubertragung der Techniken von radbasierten Robotern auf zweibeinige, humanoide Roboter noch intensive Forschung. Das gilt auch fur eine technische Ausstattung, die die Entwicklung eines umfassenden taktischen Spiels ermoglicht. Trotz des ermutigenden Fortschritts ist der Weg noch weit, bis ein Fusballroboter mit menschlichen Spielern mithalten kann.

We present a wearable assistance system for visually impaired persons that perceives the environment with a stereo camera system and communicates obstacles and other objects to the user in form of intuitive acoustic feedback. The system is designed to complement traditional assistance aids. We describe the core techniques of scene understanding, head tracking, and sonification and show in an experimental study that it enables users to walk in unknown urban terrain and to avoid obstacles safely.

In this paper, we present a novel probabilistic generative model for multi-object traffic scene understanding from movable platforms which reasons jointly about the 3D scene layout as well as the location and orientation of objects in the scene. In particular, the scene topology, geometry, and traffic activities are inferred from short video sequences. Inspired by the impressive driving capabilities of humans, our model does not rely on GPS, lidar, or map knowledge. Instead, it takes advantage of a diverse set of visual cues in the form of vehicle tracklets, vanishing points, semantic scene labels, scene flow, and occupancy grids. For each of these cues, we propose likelihood functions that are integrated into a probabilistic generative model. We learn all model parameters from training data using contrastive divergence. Experiments conducted on videos of 113 representative intersections show that our approach successfully infers the correct layout in a variety of very challenging scenarios. To evaluate the importance of each feature cue, experiments using different feature combinations are conducted. Furthermore, we show how by employing context derived from the proposed method we are able to improve over the state-of-the-art in terms of object detection and object orientation estimation in challenging and cluttered urban environments.

Environment perception is an important task in computer vision for many applications in robotics. Especially for robots navigating through different levels of a building, stair detection constitutes an important perception task. In this paper, we propose a stair detection algorithm using range data. Firstly, we introduce a parameter, which describes local surface orientations w.r.t. a global reference. Secondly, a matched filter is used to detect relevant edges in the orientation data. Afterwards, line segments are determined using these edge data which are further used to estimate stairs. The proposed method is invariant against rotations of the sensor. We show that the system can handle typical outdoor stair types and outperforms the accuracy of state-of-the-art stair detection methods. Moreover, the method is used in real time to assist visually impaired people who wear the camera system on a helmet.

In this paper we present a vision-based detection system for cyclists. We build cascaded detectors with different classifiers and shared features to detect cyclists from multiple viewpoints. To improve the performance, we reveal the dependence between the size and the position of an object in the image by a regression method. We also explore the applications of this geometric constraint with different camera setups. Based on experiments we demonstrate that our detector is suitable for real time applications.

While monocular visual odometry has been widely investigated, one of its key issues restrains its broad appliance: the scale drift. To tackle it, we leverage scene inherent information about the ground plane to estimate the scale for usage on Advanced Driver Assistance Systems. The algorithm is conceived so that it is independent of the unscaled ego-motion estimation, augmenting its adaptability to other frameworks. A ground plane estimation using Structure From Motion techniques is complemented by a vanishing point estimation to render our algorithm robust in urban scenarios. The method is evaluated on the KITTI dataset, outperforming state of the art algorithms in areas where urban scenery is dominant.

Estimating the ground plane is often one of the first steps in geometric reasoning processes as it offers easily accessible context knowledge. Especially unconstrained platforms that capture video from egocentric viewpoints can benefit from such knowledge in various ways. A key requirement here is keeping orientation, which can be greatly achieved by keeping track of the ground. We present an approach to keep track of the ground plane in cluttered inner-urban environments using stereo vision in real-time. We fuse a planar model fit in low-resolution disparity data with the direction of the vertical vanishing point. Our experiments show how this effectively decreases the error of plane attitude estimation compared to classic least-squares fitting and allows to track the plane with camera configurations in which the ground is not visible. We evaluate the approach using ground-truth from an inertial measurement unit and demonstrate long-term stability on a dataset of challenging inner city scenes.

Das “Brainstormers” Projekt wurde 1998 gestartet mit dem Ziel, lernfahige autonome Agenten in komplexen Umgebungen am Beispiel Roboterfusball zu erforschen. Dabei hat die Bearbeitung der vielfaltigen Fragestellungen, die sich in dieser sehr dynamischen und verrauschten Umgebung ergeben, zu einer Vielzahl neuartiger Methoden und theoretischer Ergebnisse gefuhrt.

Excrescences are unique dendritic postsynaptic structures of the hippocampal formation. Only CA3 pyramidal neurones and hilar mossy cells possess these complex dendritic structures. Dendritic excrescences have so far only been investigated in rabbit, rat and rhesus monkey. Applying a Golgi impregnation method optimized for human brain tissue, we describe the detailed morphology of excrescences of CA3 pyramidal neurons of man. Human thorny excrescences possess a thin and single spine neck and multiple spine heads (4 on average, sometimes more than 10). Human cluster excrescences sit upon the dendrite with a broad stem, and exhibit a “papilloma-like” surface. Some human CA3 pyramidal neurons seem to possess markedly longer spine necks and larger spine heads compared to human neocortical pyramid cells; they were named long-neck spines. Thorny excrescences, cluster excrescences and the newly described long-neck spines can also be found on the dendritic main stem of human CA3 pyramidal neurons. CA2 pyramidal neurons neither possess these long neck spines nor thorny or cluster excrescences. Thus, the unique excrescences of CA3 pyramidal neurones seem to be another criterion for a demarcation between the CA3- and CA2 region of the human hippocampus.

The phenomenon of adult neurogenesis (AN), that is, the generation of functional neurons from neural stem cells in the dentate gyrus of the hippocampus, has attracted remarkable attention, especially as it was shown that this process is also active in the human brain. Based on animal studies, it has been suggested that reduced AN is implicated in the etiopathology of psychiatric disorders, and that stimulation of AN contributes to the mechanism of action of antidepressant therapies. As data from human post-mortem brain are still lacking, we investigated whether the first step of AN, that is, the level of neural stem cell proliferation (NSP; as quantified by Ki-67 immunohistochemistry), is altered in tissue from the Stanley Foundation Neuropathology Consortium comprising brain specimens from patients with bipolar affective disorder, major depression, schizophrenia as well as control subjects (n=15 in each group). The hypothesis was that stem cell proliferation is reduced in affective disorders, and that antidepressant treatment increases NSP. Neither age, brain weight or pH, brain hemisphere investigated nor duration of storage had an effect on NSP. Only in bipolar disorder, post-mortem interval was a significant intervening variable. In disease, onset of the disorder and its duration likewise did not affect NSP. Also, cumulative lifetime dose of fluphenazine was not correlated with NSP, and presence of antidepressant treatment did not result in an increase of NSP. Concerning the different diagnostic entities, reduced amounts of newly formed cells were found in schizophrenia, but not in major depression. Our findings suggest that reduced NSP may contribute to the pathogenesis of schizophrenia, whereas the rate of NSP does not seem to be critical to the etiopathology of affective disorders, nor is it modified by antidepressant drug treatment.