Filtern
Erscheinungsjahr
Dokumenttyp
- Masterarbeit (16)
- Bachelorarbeit (12)
- Dissertation (9)
- Ausgabe (Heft) zu einer Zeitschrift (7)
- Diplomarbeit (5)
- Studienarbeit (2)
Sprache
- Englisch (51) (entfernen)
Gehört zur Bibliographie
- nein (51) (entfernen)
Schlagworte
- virtual reality (3)
- Bildverarbeitung (2)
- Computer Graphics (2)
- Computergraphik (2)
- Graphik (2)
- Line Space (2)
- OpenGL (2)
- Volumen-Rendering (2)
- tracking (2)
- Acceleration Structures (1)
Institut
- Institut für Computervisualistik (51) (entfernen)
This paper describes the robots TIAGo and Lisa used by
team homer@UniKoblenz of the University of Koblenz-Landau, Germany,
for the participation at the RoboCup@Home 2019 in Sydney,
Australia. We ended up first at RoboCup@Home 2019 in the Open Platform
League and won the competition in our league now three times
in a row (four times in total) which makes our team the most successful
in RoboCup@Home. We demonstrated approaches for learning from
demonstration, touch enforcing manipulation and autonomous semantic
exploration in the finals. A special focus is put on novel system components
and the open source contributions of our team. We have released
packages for object recognition, a robot face including speech synthesis,
mapping and navigation, speech recognition interface, gesture recognition
and imitation learning. The packages are available (and new packages
will be released) on http://homer.uni-koblenz.de.
This paper describes the robots TIAGo and Lisa used by team homer@UniKoblenz of the University of Koblenz-Landau, Germany, for the participation at the RoboCup@Home 2018 in Montreal, Canada. Further this paper serves as qualification material for the RoboCup-@Home participation in 2018. A special focus is put on novel system components and the open source contributions of our team. This year the team from Koblenz won the biggest annual scientianc robot competition in Montreal in the RoboCup@Home Open Platform track for the third time and also won the RoboCup@Home German Open for the second time. As a research highlight a novel symbolic imitation learning approach was demonstrated during the annals. The TIAGo robotic research platform was used for the first time by the team. We have released packages for object recognition, a robot face including speech synthesis, mapping and navigation, speech recognition interface via android and a GUI. The packages are available (and new packages will be released) on http://wiki.ros.org/agas-ros-pkg. Further information can be found on our project page http://homer.uni-koblenz.de.
Human action recognition from a video has received growing attention in computer vision and has made significant progress in recent years. Action recognition is described as a requirement to decide which human actions appear in videos. The difficulties involved in distinguishing human actions are due to the high complexity of human behaviors as well as appearance variation, motion pattern variation, occlusions, etc. Many applications use human action recognition on captured video from cameras, resulting in video surveillance systems, health monitoring, human-computer interaction, and robotics. Action recognition based on RGB-D data has increasingly drawn more attention to it in recent years. RGB-D data contain color (Red, Green, and Blue (RGB)) and depth data that represent the distance from the sensor to every pixel in the object (object point). The main problem that this thesis deals with is how to automate the classification of specific human activities/actions through RGB-D data. The classification process of these activities utilizes a spatial and temporal structure of actions. Therefore, the goal of this work is to develop algorithms that can distinguish these activities by recognizing low-level and high-level activities of interest from one another. These algorithms are developed by introducing new features and methods using RGB-D data to enhance the detection and recognition of human activities. In this thesis, the most popular state-of-the-art techniques are reviewed, presented, and evaluated. From the literature review, these techniques are categorized into hand-crafted features and deep learning-based approaches. The proposed new action recognition framework is based on these two categories that are approved in this work by embedding novel methods for human action recognition. These methods are based on features extracted from RGB-D data that are
evaluated using machine learning techniques. The presented work of this thesis improves human action recognition in two distinct parts. The first part focuses on improving current successful hand-crafted approaches. It contributes into two significant areas of state-of-the-art: Execute the existing feature detectors, and classify the human action in the 3D spatio-temporal domains by testing a new combination of different feature representations. The contributions of this part are tested based on machine learning techniques that include unsupervised and supervised learning to evaluate this suitability for the task of human action recognition. A k-means clustering represents the unsupervised learning technique, while the supervised learning technique is represented by: Support Vector Machine, Random Forest, K-Nearest Neighbor, Naive Bayes, and Artificial Neural Networks classifiers. The second part focuses on studying the current deep-learning-based approach and how to use it with RGB-D data for the human action recognition task. As the first step of each contribution, an input video is analyzed as a sequence of frames. Then, pre-processing steps are applied to the video frames, like filtering and smoothing methods to remove the noisy data from each frame. Afterward, different motion detection and feature representation methods are used to extract features presented in each frame. The extracted features
are represented by local features, global features, and feature combination besides deep learning methods, e.g., Convolutional Neural Networks. The feature combination achieves an excellent accuracy performance that outperforms other methods on the same RGB-D datasets. All the results from the proposed methods in this thesis are evaluated based on publicly available datasets, which illustrate that using spatiotemporal features can improve the recognition accuracy. The competitive experimental results are achieved overall. In particular, the proposed methods can be better applied to the test set compared to the state-of-the-art methods using the RGB-D datasets.
Efficient Cochlear Implant (CI) surgery requires prior knowledge of the cochlea’s size and its characteristics. This information helps to select suitable implants for different patients. Registered and fused images helps doctors by providing more informative image that takes advantages of different modalities. The cochlea’s small size and complex structure, in addition to the different resolutions and head positions during imaging, reveals a big challenge for the automated registration of the different image modalities. To obtain an automatic measurement of the cochlea length and the volume size, a segmentation method of cochlea medical images is needed. The goal of this dissertation is to introduce new practical and automatic algorithms for the human cochlea multi-modal 3D image registration, fusion, segmentation and analysis. Two novel methods for automatic cochlea image registration (ACIR) and automatic cochlea analysis (ACA) are introduced. The proposed methods crop the input images to the cochlea part and then align the cropped images to obtain the optimal transformation. After that, this transformation is used to align the original images. ACIR and ACA use Mattes mutual information as similarity metric, the adaptive stochastic gradient descent (ASGD) or the stochastic limited memory Broyden–Fletcher–Goldfarb–Shanno (s-LBFGS) optimizer to estimate the parameters of 3D rigid transform. The second stage of nonrigid registration estimates B-spline coefficients that are used in an atlas-model-based segmentation to extract cochlea scalae and the relative measurements of the input image. The image which has segmentation is aligned to the input image to obtain the non-rigid transformation. After that the segmentation of the first image, in addition to point-models are transformed to the input image. The detailed transformed segmentation provides the scala volume size. Using the transformed point-models, the A-value, the central scala lengths, the lateral and the organ of corti scala tympani lengths are computed. The methods have been tested using clinical 3D images of total 67 patients: from Germany (41 patients) and Egypt (26 patients). The atients are of different ages and gender. The number of images used in the experiments is 217, which are multi-modal 3D clinical images from CT, CBCT, and MRI scanners. The proposed methods are compared to the state of the arts ptimizers related medical image registration methods e.g. fast adaptive stochastic gradient descent (FASGD) and efficient preconditioned tochastic gradient descent (EPSGD). The comparison used the root mean squared distance (RMSE) between the ground truth landmarks and the resulted landmarks. The landmarks are located manually by two experts to represent the round window and the top of the cochlea. After obtaining the transformation using ACIR, the landmarks of the moving image are transformed using the resulted transformation and RMSE of the transformed landmarks, and at the same time the fixed image landmarks are computed. I also used the active length of the cochlea implant electrodes to compute the error aroused by the image artifact, and I found out an error ranged from 0.5 mm to 1.12 mm. ACIR method’s RMSE average was 0.36 mm with a standard deviation (SD) of 0.17 mm. The total time average required for registration of an image pair using ACIR was 4.62 seconds with SD of 1.19 seconds. All experiments are repeated 3 times for justifications. Comparing the RMSE of ACIR2017 and ACIR2020 using paired T-test shows no significant difference (p-value = 0.17). The total RMSE average of ACA method was 0.61 mm with a SD of 0.22 mm. The total time average required for analysing an image was 5.21 seconds with SD of 0.93 seconds. The statistical tests show that there is no difference between the results from automatic A-value method and the manual A-value method (p-value = 0.42). There is no difference also between length’s measurements of the left and the right ear sides (p-value > 0.16). Comparing the results from German and Egypt dataset shows there is no difference when using manual or automatic A-value methods (p-value > 0.20). However, there is a significant difference when using ACA2000 method between the German and the Egyptian results (p-value < 0.001). The average time to obtain the segmentation and all measurements was 5.21 second per image. The cochlea scala tympani volume size ranged from 38.98 mm3 to 57.67 mm3 . The combined scala media and scala vestibuli volume size ranged from 34.98 mm 3 to 49.3 mm 3 . The overall volume size of the cochlea should range from 73.96 mm 3 to 106.97 mm 3 . The lateral wall length of scala tympani ranged from 42.93 mm to 47.19 mm. The organ-of-Corti length of scala tympani ranged from 31.11 mm to 34.08 mm. Using the A-value method, the lateral length of scala tympani ranged from 36.69 mm to 45.91 mm. The organ-of-Corti length of scala tympani ranged from 29.12 mm to 39.05 mm. The length from ACA2020 method can be visualised and has a well-defined endpoints. The ACA2020 method works on different modalities and different images despite the noise level or the resolution. In the other hand, the A-value method works neither on MRI nor noisy images. Hence, ACA2020 method may provide more reliable and accurate measurement than the A-value method. The source-code and the datasets are made publicly available to help reproduction and validation of my result.
In scientific data visualization huge amounts of data are generated, which implies the task of analyzing these in an efficient way. This includes the reliable detection of important parts and a low expenditure of time and effort. This is especially important for the big-sized seismic volume datasets, that are required for the exploration of oil and gas deposits. Since the generated data is complex and a manual analysis is very time-intensive, a semi-automatic approach could on one hand reduce the time required for the analysis and on the other hand offer more flexibility, than a fully automatic approach.
This master's thesis introduces an algorithm, which is capable of locating regions of interest in seismic volume data automatically by detecting anomalies in local histograms. Furthermore the results are visualized and a variety of tools for the exploration and interpretation of the detected regions are developed. The approach is evaluated by experiments with synthetic data and in interviews with domain experts on the basis of real-world data. Conclusively further improvements to integrate the algorithm into the seismic interpretation workflow are suggested.
Mit dem Aufkommen von Head-Mounted Displays (HMDs) der aktuellen Generation erlangt Virtual Reality (VR) wieder großes Interesse im Feld von medizinischer Bildgebung und Diagnose. Exploration von CT oder MRT Daten in raumfüllender Virtual Reality stellt eine intuitive Anwendung dar. Allerdings gilt in Virtual Reality, dass das Aufrechterhalten einer hohen Bildwiederholungsrate noch wichtiger ist als bei konventioneller Benutzerinteraktion, die sitzend vor einem Bildschirm erfolgt. Es existieren starke wissenschaftliche Hinweise, die nahelegen, dass geringe Bildwiederholungsraten und hohe Latenzzeit einen starken Einfluss auf das Auftreten von Cybersickness besitzen. Diese Abschlussarbeit untersucht zwei praktische Ansätze, um den hohen Rechenaufwand von Volumenrendering zu überkommen. Einer liegt in der Ausnutzung von Kohärenzeigenschaften des besonders aufwändigen stereoskopischen Rendering Set-ups. Der Hauptbeitrag ist die Entwicklung und Auswertung einer neuartigen Beschleunigungstechnik für stereoskopisches GPU Raycasting. Zudem wird ein asynchroner Renderingansatz verfolgt, um das Ausmaß von Latenz im System zu minimieren. Eine Auswahl von Image-Warping Techniken wurden implementiert und systematisch evaluiert, um die Tauglichkeit für VR Volumenrendering zu bewerten.
Part-of-Speech tagging is the process of assigning words with similar grammatical properties to a part of speech (PoS). In the English language, PoS-tagging algorithms generally reach very high accuracy. This thesis undertakes the task to test against these accuracies in PoS-tagging as a qualitative measure in classification capabilities for a recently developed neural network model, called graph convolutional network (GCN). The novelty proposed in this thesis is to translate a corpus into a graph as a direct input for the GCN. The experiments in this thesis serve as a proof of concept with room for improvements.
Die Koloskopie ist der Goldstandard zur Aufspürung von gefährlichen Darmpolypen, die sich zu Krebs entwickeln können. In einer solchen Untersuchung sucht der Arzt in den vom Endoskop gelieferten Bildern nach Polypen und kann diese gegebenenfalls entfernen. Um den Arzt bei der Suche zu unterstützen, erforscht die Universität Koblenz-Landau zur Zeit Methoden, die zur automatischen Detektion von Polypen auf endoskopischen Bildern verwendet werden können. Wie auch bei anderen Systemen zur Mustererkennung werden hierzu zunächst Merkmale aus den Bildern extrahiert und mit diesen ein Klassifikator trainiert. Dieser kann dann für die Klassifikation von ihm unbekannten Bildern eingesetzt werden. In dieser Arbeit wurde das vorhandene System zur Polypendetektion um Merkmalsdetektoren erweitert und mit den bereits vorhandenen verglichen. Implementiert wurden Merkmale basierend auf der Diskreten Wavelet-Transformation, auf Grauwertübergangsmatrizen und auf Local Binary Patterns. Verschiedene Modifikationen dieser Merkmale wurden getestet und evaluiert.
Die Mitralklappe ist eine der vier Herzklappen des Menschen. Sie befindet sich in der linken Herzkammer und agiert als ein unidirektionales Ventil, welches den Blutfluss vom linken Atrium zum linken Ventrikel steuert. Eine funktionierende Mitralklappe verhindert den Rückfluss von Blut in den Lungenkreislauf, wodurch sie einen unverzichtbaren Anteil zu einem gesunden Herzkreislauf beiträgt. Pathologien der Mitralklappe können eine Reihe von Symptomen hervorrufen, welche in ihrer Schwere von Brustschmerzen und Ermüdung bis zum Lungenödem (dem Eindringen von Flüssigkeit in die Lunge) reichen können. Im schlimmsten Fall kann dieses zum Atemversagen führen.
Dysfunktionale Mitralklappen können mithilfe komplexer chirurgischer Eingriffe wiederhergestellt werden, welche in hohem Maße von intensiver Planung und präoperativer Analyse profitieren. Visualisierungstechniken eröffnen die Möglichkeit, solche Vorbereitungsprozesse zu unterstützen und können zudem einer postoperativen Evaluation dienlich sein. Die vorliegende Arbeit erweitert die Forschung in diesem Bereich. Sie stützt sich auf patientenspezifische Segmentierungen der Mitralklappe, wie sie am Deutschen Krebsforschungszentrum entwickelt werden. Solche Segmentierungen resultieren in 3D-Modellen der Mitralklappe. Der Kern dieser Arbeit wird sich mit der Konstruktion einer 2D-Ansicht dieser Modelle befassen. Die 2D-Visualisierung wird durch Methoden der globalen Parametrisierung erzeugt, welche es erlauben, bijektive Abbildungen zwischen einem planaren Parameterraum und Oberflächen in höheren Dimensionen zu erstellen.
Eine ebene Repräsentation der Mitralklappe ermöglicht Ärzten einen unmittelbaren Blick auf deren gesamte Oberfläche, analog zu einer Karte. Dies erlaubt die Begutachtung der Fläche und Form ohne die Notwendigkeit unterschiedlicher Blickwinkel. Teile der Klappe, die in der 3D-Ansicht von Geometrie verdeckt sind, werden in der 2D-Darstellung sichtbar.
Ein weiterer Beitrag dieser Arbeit ist die Untersuchung verschiedener Visualisierungen der 3D- und 2D-Mitralklappenrepräsentationen. Merkmale der Klappe können durch Assoziation mit spezifizierten Farbschemata hervorgehoben werden. So können zum Beispiel Pathologie-Indikatoren direkt vermittelt werden.
Qualität und Wirkungsgrad der vorgestellten Methoden wurden in einer Studie am Universitätsklinikum Heidelberg evaluiert.
Diese Bachelorarbeit erforscht eine Methode zur 3D-Objekterkennung und Posenschätzung, basierend auf dem Punkte-Paare-Eigenschaften-Verfahren (PPE) von Drost et. al. [Dro+10]. Die Methoden der Posenschätzung haben sich in den letzten Jahre zwar deutlich verbessert, stellen jedoch weiterhin ein zentrales Problem im Bereich der Computervisualistik dar. Im Rahmen dieser Arbeit wurde ein Programm implementiert, welches Punktewolkenszenen als Ausgangspunkt erhält und daraus eine Objekterkennung und Posenschätzung durchführt. Das Programm deckt alle Schritte eines Objekterkennungsprogramm ab, indem es 3D-Modelle von Objekten verarbeitet, um deren PPE zu extrahieren. Diese Eigenschaften werden gruppiert und in einer Tabelle gespeichert. Anhand des Auswahlverfahrens, bei dem die Übereinstimmung der Eigenschaften überprüft wird, können potenzielle Posen des Objekts ermittelt werden. Die Posen mit der größten Übereinstimmung werden miteinander verglichen, um ähnliche Posen zu gruppieren. Die Gruppen mit der höchsten Übereinstimmung werden erneut überprüft, sodass am Ende nur eine Pose ausgewählt wird. Das Programm wurde anhand von Real– und Simulationsdaten Daten getestet. Die erhaltenen Ergebnisse wurden anschließend analysiert und evaluiert.