006 Spezielle Computerverfahren
Refine
H-BRS Bibliography
- yes (56)
Departments, institutes and facilities
- Fachbereich Informatik (56) (remove)
Document Type
- Conference Object (24)
- Article (23)
- Preprint (4)
- Part of a Book (2)
- Doctoral Thesis (2)
- Research Data (1)
Year of publication
Language
- English (56) (remove)
Keywords
- Augmented Reality (3)
- Knowledge Graphs (3)
- Machine Learning (3)
- Virtual Reality (3)
- haptics (3)
- virtual reality (3)
- 3D user interface (2)
- Bioinformatics (2)
- Natural Language Processing (2)
- Robotics (2)
Background: Virtual reality combined with spherical treadmills is used across species for studying neural circuits underlying navigation.
New Method: We developed an optical flow-based method for tracking treadmil ball motion in real-time using a single high-resolution camera.
Results: Tracking accuracy and timing were determined using calibration data. Ball tracking was performed at 500 Hz and integrated with an open source game engine for virtual reality projection. The projection was updated at 120 Hz with a latency with respect to ball motion of 30 ± 8 ms.
Comparison: with Existing Method(s) Optical flow based tracking of treadmill motion is typically achieved using optical mice. The camera-based optical flow tracking system developed here is based on off-the-shelf components and offers control over the image acquisition and processing parameters. This results in flexibility with respect to tracking conditions – such as ball surface texture, lighting conditions, or ball size – as well as camera alignment and calibration.
Conclusions: A fast system for rotational ball motion tracking suitable for virtual reality animal behavior across different scales was developed and characterized.
While humans can effortlessly pick a view from multiple streams, automatically choosing the best view is a challenge. Choosing the best view from multi-camera streams poses a problem regarding which objective metrics should be considered. Existing works on view selection lack consensus about which metrics should be considered to select the best view. The literature on view selection describes diverse possible metrics. And strategies such as information-theoretic, instructional design, or aesthetics-motivated fail to incorporate all approaches. In this work, we postulate a strategy incorporating information-theoretic and instructional design-based objective metrics to select the best view from a set of views. Traditionally, information-theoretic measures have been used to find the goodness of a view, such as in 3D rendering. We adapted a similar measure known as the viewpoint entropy for real-world 2D images. Additionally, we incorporated similarity penalization to get a more accurate measure of the entropy of a view, which is one of the metrics for the best view selection. Since the choice of the best view is domain-dependent, we chose demonstration-based training scenarios as our use case. The limitation of our chosen scenarios is that they do not include collaborative training and solely feature a single trainer. To incorporate instructional design considerations, we included the trainer’s body pose, face, face when instructing, and hands visibility as metrics. To incorporate domain knowledge we included predetermined regions’ visibility as another metric. All of those metrics are taken into account to produce a parameterized view recommendation approach for demonstration-based training. An online study using recorded multi-camera video streams from a simulation environment was used to validate those metrics. Furthermore, the responses from the online study were used to optimize the view recommendation performance with a normalized discounted cumulative gain (NDCG) value of 0.912, which shows good performance with respect to matching user choices.
Vection underwater
(2022)
Using Visual and Auditory Cues to Locate Out-of-View Objects in Head-Mounted Augmented Reality
(2021)
It is challenging to provide users with a haptic weight sensation of virtual objects in VR since current consumer VR controllers and software-based approaches such as pseudo-haptics cannot render appropriate haptic stimuli. To overcome these limitations, we developed a haptic VR controller named Triggermuscle that adjusts its trigger resistance according to the weight of a virtual object. Therefore, users need to adapt their index finger force to grab objects of different virtual weights. Dynamic and continuous adjustment is enabled by a spring mechanism inside the casing of an HTC Vive controller. In two user studies, we explored the effect on weight perception and found large differences between participants for sensing change in trigger resistance and thus for discriminating virtual weights. The variations were easily distinguished and associated with weight by some participants while others did not notice them at all. We discuss possible limitations, confounding factors, how to overcome them in future research and the pros and cons of this novel technology.
Self-motion perception is a multi-sensory process that involves visual, vestibular, and other cues. When perception of self-motion is induced using only visual motion, vestibular cues indicate that the body remains stationary, which may bias an observer’s perception. When lowering the precision of the vestibular cue by for example, lying down or by adapting to microgravity, these biases may decrease, accompanied by a decrease in precision. To test this hypothesis, we used a move-to-target task in virtual reality. Astronauts and Earth-based controls were shown a target at a range of simulated distances. After the target disappeared, forward self-motion was induced by optic flow. Participants indicated when they thought they had arrived at the target’s previously seen location. Astronauts completed the task on Earth (supine and sitting upright) prior to space travel, early and late in space, and early and late after landing. Controls completed the experiment on Earth using a similar regime with a supine posture used to simulate being in space. While variability was similar across all conditions, the supine posture led to significantly higher gains (target distance/perceived travel distance) than the sitting posture for the astronauts pre-flight and early post-flight but not late post-flight. No difference was detected between the astronauts’ performance on Earth and onboard the ISS, indicating that judgments of traveled distance were largely unaffected by long-term exposure to microgravity. Overall, this constitutes mixed evidence as to whether non-visual cues to travel distance are integrated with relevant visual cues when self-motion is simulated using optic flow alone.
The majority of biomedical knowledge is stored in structured databases or as unstructured text in scientific publications. This vast amount of information has led to numerous machine learning-based biological applications using either text through natural language processing (NLP) or structured data through knowledge graph embedding models (KGEMs). However, representations based on a single modality are inherently limited. To generate better representations of biological knowledge, we propose STonKGs, a Sophisticated Transformer trained on biomedical text and Knowledge Graphs. This multimodal Transformer uses combined input sequences of structured information from KGs and unstructured text data from biomedical literature to learn joint representations. First, we pre-trained STonKGs on a knowledge base assembled by the Integrated Network and Dynamical Reasoning Assembler (INDRA) consisting of millions of text-triple pairs extracted from biomedical literature by multiple NLP systems. Then, we benchmarked STonKGs against two baseline models trained on either one of the modalities (i.e., text or KG) across eight different classification tasks, each corresponding to a different biological application. Our results demonstrate that STonKGs outperforms both baselines, especially on the more challenging tasks with respect to the number of classes, improving upon the F1-score of the best baseline by up to 0.083. Additionally, our pre-trained model as well as the model architecture can be adapted to various other transfer learning applications. Finally, the source code and pre-trained STonKGs models are available at https://github.com/stonkgs/stonkgs and https://huggingface.co/stonkgs/stonkgs-150k.
MOTIVATION
The majority of biomedical knowledge is stored in structured databases or as unstructured text in scientific publications. This vast amount of information has led to numerous machine learning-based biological applications using either text through natural language processing (NLP) or structured data through knowledge graph embedding models (KGEMs). However, representations based on a single modality are inherently limited.
RESULTS
To generate better representations of biological knowledge, we propose STonKGs, a Sophisticated Transformer trained on biomedical text and Knowledge Graphs (KGs). This multimodal Transformer uses combined input sequences of structured information from KGs and unstructured text data from biomedical literature to learn joint representations in a shared embedding space. First, we pre-trained STonKGs on a knowledge base assembled by the Integrated Network and Dynamical Reasoning Assembler (INDRA) consisting of millions of text-triple pairs extracted from biomedical literature by multiple NLP systems. Then, we benchmarked STonKGs against three baseline models trained on either one of the modalities (i.e., text or KG) across eight different classification tasks, each corresponding to a different biological application. Our results demonstrate that STonKGs outperforms both baselines, especially on the more challenging tasks with respect to the number of classes, improving upon the F1-score of the best baseline by up to 0.084 (i.e., from 0.881 to 0.965). Finally, our pre-trained model as well as the model architecture can be adapted to various other transfer learning applications.
AVAILABILITY
We make the source code and the Python package of STonKGs available at GitHub (https://github.com/stonkgs/stonkgs) and PyPI (https://pypi.org/project/stonkgs/). The pre-trained STonKGs models and the task-specific classification models are respectively available at https://huggingface.co/stonkgs/stonkgs-150k and https://zenodo.org/communities/stonkgs.
SUPPLEMENTARY INFORMATION
Supplementary data are available at Bioinformatics online.
Selection Performance and Reliability of Eye and Head Gaze Tracking Under Varying Light Conditions
(2024)
Robust Identification and Segmentation of the Outer Skin Layers in Volumetric Fingerprint Data
(2022)
Despite the long history of fingerprint biometrics and its use to authenticate individuals, there are still some unsolved challenges with fingerprint acquisition and presentation attack detection (PAD). Currently available commercial fingerprint capture devices struggle with non-ideal skin conditions, including soft skin in infants. They are also susceptible to presentation attacks, which limits their applicability in unsupervised scenarios such as border control. Optical coherence tomography (OCT) could be a promising solution to these problems. In this work, we propose a digital signal processing chain for segmenting two complementary fingerprints from the same OCT fingertip scan: One fingerprint is captured as usual from the epidermis (“outer fingerprint”), whereas the other is taken from inside the skin, at the junction between the epidermis and the underlying dermis (“inner fingerprint”). The resulting 3D fingerprints are then converted to a conventional 2D grayscale representation from which minutiae points can be extracted using existing methods. Our approach is device-independent and has been proven to work with two different time domain OCT scanners. Using efficient GPGPU computing, it took less than a second to process an entire gigabyte of OCT data. To validate the results, we captured OCT fingerprints of 130 individual fingers and compared them with conventional 2D fingerprints of the same fingers. We found that both the outer and inner OCT fingerprints were backward compatible with conventional 2D fingerprints, with the inner fingerprint generally being less damaged and, therefore, more reliable.
In this paper, we introduce an optical sensor system, which is integrated into an industrial push-button. The sensor allows to classify the type of material that is in contact with the button when pressed into different material categories on the basis of the material's so called "spectral signature". An approach for a safety sensor system at circular table saws on the same base has been introduced previously on SIAS-2007. This contactless working sensor is able to distinguish reliably between skin, textiles, leather and various other kinds of materials. A typical application for this intelligent push-button is the use at possibly dangerous machines, whose operating instructions include either the prohibition or the obligation to wear gloves during the work at the machine. An exemple of machines at which no gloves are allowed are pillar drilling machines, because of the risk of getting caught in the drill chuck and being turned in by the machine. In many cases this causes very serious hand injuries. Depending on the application needs, the sensor system integrated into the push-button can be configured flexibly by software to prevent the operator from accidentally starting a machine with or without gloves, which can decrease the risk of severe accidents significantly. Especially two-hand controls are incentive to manipulation for easier handling. By equipping both push-buttons of a two-hand control with material classification properties, the user is forced to operate the controls with his bare fingers. That limitation disallows the manipulation of a two-hand control by a simple rodding device.
ProtSTonKGs: A Sophisticated Transformer Trained on Protein Sequences, Text, and Knowledge Graphs
(2022)
While most approaches individually exploit unstructured data from the biomedical literature or structured data from biomedical knowledge graphs, their union can better exploit the advantages of such approaches, ultimately improving representations of biology. Using multimodal transformers for such purposes can improve performance on context dependent classication tasks, as demonstrated by our previous model, the Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs (STonKGs). In this work, we introduce ProtSTonKGs, a transformer aimed at learning all-encompassing representations of protein-protein interactions. ProtSTonKGs presents an extension to our previous work by adding textual protein descriptions and amino acid sequences (i.e., structural information) to the text- and knowledge graph-based input sequence used in STonKGs. We benchmark ProtSTonKGs against STonKGs, resulting in improved F1 scores by up to 0.066 (i.e., from 0.204 to 0.270) in several tasks such as predicting protein interactions in several contexts. Our work demonstrates how multimodal transformers can be used to integrate heterogeneous sources of information, paving the foundation for future approaches that use multiple modalities for biomedical applications.
Computer graphics research strives to synthesize images of a high visual realism that are indistinguishable from real visual experiences. While modern image synthesis approaches enable to create digital images of astonishing complexity and beauty, processing resources remain a limiting factor. Here, rendering efficiency is a central challenge involving a trade-off between visual fidelity and interactivity. For that reason, there is still a fundamental difference between the perception of the physical world and computer-generated imagery. At the same time, advances in display technologies drive the development of novel display devices. The dynamic range, the pixel densities, and refresh rates are constantly increasing. Display systems enable a larger visual field to be addressed by covering a wider field-of-view, due to either their size or in the form of head-mounted devices. Currently, research prototypes are ranging from stereo and multi-view systems, head-mounted devices with adaptable lenses, up to retinal projection, and lightfield/holographic displays. Computer graphics has to keep step with, as driving these devices presents us with immense challenges, most of which are currently unsolved. Fortunately, the human visual system has certain limitations, which means that providing the highest possible visual quality is not always necessary. Visual input passes through the eye’s optics, is filtered, and is processed at higher level structures in the brain. Knowledge of these processes helps to design novel rendering approaches that allow the creation of images at a higher quality and within a reduced time-frame. This thesis presents the state-of-the-art research and models that exploit the limitations of perception in order to increase visual quality but also to reduce workload alike - a concept we call perception-driven rendering. This research results in several practical rendering approaches that allow some of the fundamental challenges of computer graphics to be tackled. By using different tracking hardware, display systems, and head-mounted devices, we show the potential of each of the presented systems. The capturing of specific processes of the human visual system can be improved by combining multiple measurements using machine learning techniques. Different sampling, filtering, and reconstruction techniques aid the visual quality of the synthesized images. An in-depth evaluation of the presented systems including benchmarks, comparative examination with image metrics as well as user studies and experiments demonstrated that the methods introduced are visually superior or on the same qualitative level as ground truth, whilst having a significantly reduced computational complexity.
Advances in computer graphics enable us to create digital images of astonishing complexity and realism. However, processing resources are still a limiting factor. Hence, many costly but desirable aspects of realism are often not accounted for, including global illumination, accurate depth of field and motion blur, spectral effects, etc. especially in real‐time rendering. At the same time, there is a strong trend towards more pixels per display due to larger displays, higher pixel densities or larger fields of view. Further observable trends in current display technology include more bits per pixel (high dynamic range, wider color gamut/fidelity), increasing refresh rates (better motion depiction), and an increasing number of displayed views per pixel (stereo, multi‐view, all the way to holographic or lightfield displays). These developments cause significant unsolved technical challenges due to aspects such as limited compute power and bandwidth. Fortunately, the human visual system has certain limitations, which mean that providing the highest possible visual quality is not always necessary. In this report, we present the key research and models that exploit the limitations of perception to tackle visual quality and workload alike. Moreover, we present the open problems and promising future research targeting the question of how we can minimize the effort to compute and display only the necessary pixels while still offering a user full visual experience.