Kaiserslautern - Fachbereich Informatik
Refine
Year of publication
Document Type
- Preprint (290)
- Doctoral Thesis (217)
- Report (111)
- Article (107)
- Conference Proceeding (8)
- Master's Thesis (7)
- Study Thesis (5)
- Bachelor Thesis (4)
- Habilitation (2)
- Part of a Book (1)
Language
- English (752) (remove)
Has Fulltext
- yes (752)
Keywords
- AG-RESY (47)
- PARO (25)
- Visualisierung (16)
- SKALP (15)
- Case-Based Reasoning (11)
- RODEO (11)
- HANDFLEX (9)
- Visualization (8)
- Deep Learning (7)
- Robotics (7)
Faculty / Organisational entity
Machine learning algorithms are widely applied to create powerful prediction models. With increasingly complex models, humans' ability to understand the decision function (that maps from a high-dimensional input space) is quickly exceeded. To explain a model's decisions, black-box methods have been proposed that provide either non-linear maps of the global topology of the decision boundary, or samples that allow approximating it locally. The former loses information about distances in input space, while the latter only provides statements about given samples, but lacks a focus on the underlying model for precise ‘What-If'-reasoning. In this paper, we integrate both approaches and propose an interactive exploration method using local linear maps of the decision space. We create the maps on high-dimensional hyperplanes—2D-slices of the high-dimensional parameter space—based on statistical and personal feature mutability and guided by feature importance. We complement the proposed workflow with established model inspection techniques to provide orientation and guidance. We demonstrate our approach on real-world datasets and illustrate that it allows identification of instance-based decision boundary structures and can answer multi-dimensional ‘What-If'-questions, thereby identifying counterfactual scenarios visually.
Edit distances between merge trees of scalar fields have many applications in scientific visualization, such as ensemble analysis, feature tracking or symmetry detection. In this paper, we propose branch mappings, a novel approach to the construction of edit mappings for merge trees. Classic edit mappings match nodes or edges of two trees onto each other, and therefore have to either rely on branch decompositions of both trees or have to use auxiliary node properties to determine a matching. In contrast, branch mappings employ branch properties instead of node similarity information, and are independent of predetermined branch decompositions. Especially for topological features, which are typically based on branch properties, this allows a more intuitive distance measure which is also less susceptible to instabilities from small-scale perturbations. For trees with 𝒪(n) nodes, we describe an 𝒪(n4) algorithm for computing optimal branch mappings, which is faster than the only other branch decomposition-independent method in the literature by more than a linear factor. Furthermore, we compare the results of our method on synthetic and real-world examples to demonstrate its practicality and utility.
The development of algorithmic differentiation (AD) tools focuses mostly on handling floating point types in the target language. Taping optimizations in these tools mostly focus on specific operations like matrix vector products. Aggregated types like std::complex are usually handled by specifying the AD type as a template argument. This approach provides exact results, but prevents the use of expression templates. If AD tools are extended and specialized such that aggregated types can be added to the expression framework, then this will result in reduced memory utilization and improve the timing for applications where aggregated types such as complex number or matrix vector operations are used. Such an integration requires a reformulation of the stored data per expression and a rework of the tape evaluation process. We will demonstrate the overheads on a synthetic benchmark and show the improvement when aggregated types are handled properly by the expression framework of the AD tool.
To increase situational awareness of the crane operator, the aim of this thesis is to develop a vision-based deep learning object detection from crane load-view using an adaptive perception in the construction area. Conventional worker detection methods are based on simple shape or color features from the worker's appearances. Nonetheless, these methods can fail to recognize the workers who do not wear the protective gears. To find out an image representation of the object from the top view manually or handcrafted feature is crucial. We, therefore, employed deep learning methods to automatically learn those features.
To yield optimal results, deep learning methods require mass amount of data.
Due to the data deficit especially in the construction domain, we developed the photorealistic world to create the data in addition to our samples collected from the real construction area. The simulated platform does not benefit only from diverse data types, but also concurrent research development which speeds up the pipeline at a low cost.
Our research findings indicate that the combination of synthetic and real training samples improved the state-of-the-art detector. In line with previous studies to bridge the gap between synthetic and real data, the results of preprocessed synthetic images are substantially better than using the raw data by approximately 10%.
Finding the right deep learning model for load-view detection is challenging.
By investigating our training data, it becomes evident that the majority of bounding box sizes are very small with a complex background.
In addition, we gave the priority to speed over accuracy based on the construction safety criteria. Finally, RetinaNet is chosen out of the three primary object detection models.
Nevertheless, the data-driven detection algorithm can fail to handle scale invariance, especially for detectors whose input size is changed in an extremely wide range.
The adaptive zoom feature can enhance the quality of the worker detection.
To avoid further data gathering and extensive retraining, the proposed automatic zoom method of the load-view crane camera supports the deep learning algorithm, specifically in the high scale variant problem. The finite state machine is employed for control strategies to adapt the zoom level to cope not only with inconsistent detection but also abrupt camera movement during lifting operation. Consequently, the detector is able to detect a small size object by smooth continuous zoom control without additional training.
The adaptive zoom control not only enhances the performance of the top-view object detection but also reduces the interaction of the crane operator with camera system, reducing the risk of fatality during load lifting operation.
Turbulence models, which are a means to fix the closure problem arising from Reynolds averaging of Navier-Stokes equations, are economical stop-gaps but suffer from accuracy issues. Modifying turbulence models by incorporating corrections in their functional form is one approach to improve their accuracy. We estimate correction functionals for the Spalart - Allmaras turbulence model, based on an inverse problem with PDE constraints emphasizing the issue of regularization.
Algorithmic decision-making (ADM) systems have come to support, pre-empt or substitute for human decisions in manifold areas, with potentially significant impacts on individuals' lives. Achieving transparency and accountability has been formulated as a general goal regarding the use of these systems. However, concrete applications differ widely in the degree of risk and the accountability problems they entail for data subjects. The present paper addresses this variation and presents a framework that differentiates regulatory requirements for a range of ADM system uses. It draws on agency theory to conceptualize accountability challenges from the point of view of data subjects with the purpose to systematize instruments for safeguarding algorithmic accountability. The paper furthermore shows how such instruments can be matched to applications of ADM based on a risk matrix. The resulting comprehensive framework can guide the evaluation of ADM systems and the choice of suitable regulatory provisions.
We describe a novel technique for the simultaneous visualization of multiple scalar fields, e.g. representing the members of an ensemble, based on their contour trees. Using tree alignments, a graph-theoretic concept similar to edit distance mappings, we identify commonalities across multiple contour trees and leverage these to obtain a layout that can represent all trees simultaneously in an easy-to-interpret, minimally-cluttered manner. We describe a heuristic algorithm to compute tree alignments for a given similarity metric, and give an algorithm to compute a joint layout of the resulting aligned contour trees. We apply our approach to the visualization of scalar field ensembles, discuss basic visualization and interaction possibilities, and demonstrate results on several analytic and real-world examples.
In recent years, there has been a growing need for accurate 3D scene reconstruction. Recent developments in the automotive industry have led to the increased use of ADAS where 3D reconstruction techniques are used, for example, as part of a collision detection system. For such applications, scene geometry reconstruction is usually performed in the form of depth estimation, where distances to scene objects are obtained.
In general, depth estimation systems can be divided into active and passive. Both systems have their advantages and disadvantages, but passive systems are usually cheaper to produce and easier to assemble and integrate than active systems. Passive systems can be stereo- or multiple-view based. Up to a certain limit, increasing the number of views in multi-view systems usually results in improved depth estimation accuracy.
One potential problem for ensuring the reliability of multi-view systems is the need to accurately estimate the orientation of their optical sensors. One way to ensure sensor placement for multi-view systems is to rigidly fix the sensors at the manufacturing stage. Unlike arbitrary sensor placement, using of a simplified and known sensor placement geometry further simplifies the depth estimation.
We meet with the concept of light field, which parameterizes all visible light passing through all viewpoints by their intersection with angular and spatial planes. When applied to computer vision, this gives us a 2D set of 2D images, where the physical distances between each image are fixed and proportional to each other.
Existing light field depth estimation methods provide good accuracy, which is suitable for industrial applications. However, the main problems of these methods are related to their running time and resource requirements. Most of the algorithms presented in the literature are typically sharpened for accuracy, can only be run on high-performance machines and often require a significant amount of time to process and obtain results.
Real-world applications often have running time requirements. Also, often there is a power-consumption limitation. In this dissertation, we investigate the problem of building a depth estimation system with an light field camera that satisfies the operating time and power consumption constraints without significant loss of estimation accuracy.
First, an algorithm for calibrating light field cameras is proposed, together with an algorithm for automatic calibration refinement, that works on arbitrary captured scenes. An algorithm for classical geometric depth estimation using light field cameras is proposed. Ways to optimize the algorithm for real-time use without significant loss of accuracy are presented. Finally, the ways how the presented depth estimation methods can be extended using modern deep learning paradigms under the two previously mentioned constraints are shown.
Knowledge workers face an ever increasing flood of information in their daily work. They live in a “multi-tasking craziness”, involving activities like creating, finding, processing, assessing or organizing information while constantly switching from one context to another, each being associated with different tasks, documents, mails, etc. Hence, their personal information sphere consisting of file, mail and bookmark folders as well as their content, calendar entries, etc. is cluttered with information that has become irrelevant. Finding important information thus gets harder and much of previously gained knowledge is practically lost.
This thesis explores new ways of solving this problem by investigating the potential of self-(re)organizing and especially forgetting-enabled personal knowledge assistants in the given scenario. It utilizes so-called Managed Forgetting, which is an escalating set of measures to overcome the binary keep-or-delete paradigm, ranging from temporal hiding, to condensation, to adaptive reorganization, synchronization, archiving and deletion. Managed Forgetting is combined with two other major ideas: First, it uses the Semantic Desktop as an ecosystem, which brings Semantic Web and thus knowledge graph technologies to a user’s desktop, making it possible to capture and represent major parts of a user’s personal mental model in a machine-understandable way and exploit it in many different applications. Second, the system uses explicated context information – so-called Context Spaces: context is seen as an explicit interaction element users can work with (i.e. a “tangible” object similar to a folder) and in (immersion). The thesis is structured according to the basic interaction cycle with such a system, ranging from evidence collection to information extraction and context elicitation, followed by information value assessment and the actual support measures consisting of self-(re)organization decisions (back-end) and user interface updates (front-end). The system’s data foundation are personal or group knowledge graphs as well as native data. This work makes contributions to all of these aspects, whereas several of them have been investigated and developed in interdisciplinary research with cognitive scientists. On a more general level, searching and trust in such highly autonomous assistants have also been investigated.
In summary, a self-(re)organizing and especially forgetting-enabled support system for information management and knowledge work has been realized. Its different features vary in maturity: the most mature ones are already in practical use (also in industry), while the latest are just well elaborated (position papers) or rough ideas. Different evaluation strategies have been applied ranging from mere data-driven experiments to various user studies. Some of them were rather short-term with controlled laboratory conditions, others less controlled but spanning several months. Different benefits of working with such a system could be quantified, e.g. cognitive offloading effects and reduced task switching/resumption time. Other benefits were gathered qualitatively, e.g. tidiness of the information sphere and its better alignment with the user’s mental model. The presented approach has been shown to hold a lot of potential. In some aspects, however, only first steps have been taken towards tapping it, e.g. several support measures can be further refined and automation further increased.
Editorial
(2020)