Refine
Year of publication
Document Type
- Conference Proceeding (34) (remove)
Has Fulltext
- yes (34) (remove)
Keywords
- 3D Extended Object Tracking (1)
- 3D shape tracking (1)
- Abtragsprinzip (1)
- Accelerometer (1)
- Automotive (1)
- Ballistocardiography (1)
- Bernstein polynomial (1)
- Biomedical Signal Capturing (1)
- Checkerboard ordering (2)
- Complex interval (1)
Institute
- Fakultät Bauingenieurwesen (4)
- Fakultät Elektrotechnik und Informationstechnik (1)
- Fakultät Informatik (2)
- Fakultät Maschinenbau (2)
- Institut für Angewandte Forschung - IAF (3)
- Institut für Optische Systeme - IOS (5)
- Institut für Strategische Innovation und Technologiemanagement - IST (2)
- Institut für Systemdynamik - ISD (3)
- Institut für Werkstoffsystemtechnik Konstanz - WIK (1)
- Institut für Werkstoffsystemtechnik Thurgau - WITg (1)
Using multi-camera matching techniques for 3d reconstruction there is usually the trade-off between the quality of the computed depth map and the speed of the computations. Whereas high quality matching methods take several seconds to several minutes to compute a depth map for one set of images, real-time methods achieve only low quality results. In this paper we present a multi-camera matching method that runs in real-time and yields high resolution depth maps. Our method is based on a novel multi-level combination of normalized cross correlation, deformed matching windows based on the multi-level depth map information, and sub-pixel precise disparity maps. The whole process is implemented completely on the GPU. With this approach we can process four 0.7 megapixel images in 129 milliseconds to a full resolution 3d depth map. Our technique is tailored for the recognition of non-technical shapes, because our target application is face recognition.
Techniken zur Energiewende - studentische Fachkonferenz im Masterstudiengang Elektrische Systeme
(2013)
Die studentische Fachkonferenz im Rahmen des Seminars im Masterstudiengang Elektrische Systeme in der Fakultät für Elektrotechnik und Informationstechnik wird zum sechsten Mal veranstaltet.
Alle Studierenden erarbeiten unter dem vorgegebenen Rahmenthema eigene Beiträge, recherchieren, ergänzen, stellen die aktuellen Erkenntnisse zu wissenschaftlichen Publikationen zusammen.
Die Energiewende ist seit einigen Jahren ein heiß diskutiertes Thema. Die dezentrale Energieversorgung
unter Anwendung erneuerbarer Quellen, insbesondere Wind- und Solarkraft, ist langfristig gesehen die
einzige Antwort auf die Ausbeutung der Erde und Zerstörung der Umwelt durch Gewinnung nichtregenerativer
Energien, insbesondere Öl, Erdgas und Uran. Allerdings gibt es noch viele Bereiche, die intensive wissenschaftliche und entwicklungstechnische Arbeiten benötigen. Wie aus dem Titel durch Verwendung des Wortes „zur“ anstatt „der“ schon erkennbar, werden in dieser Fachtagung weniger die Techniken betrachtet, die schon zum Einsatz kommen, sondern zukünftige Techniken, die gedanklich auf Papier gebracht wurden, oder inzwischen das Stadium der Machbarkeitsstudie erreicht haben.
Das Thema Energiewende beinhaltet ein sehr breites Feld von Techniken. Daher haben sich die Teilnehmer
auf nur wenige, wichtige Gebiete konzentriert: Regenerative Energiegewinnung, Elektromobilität,
Speichertechnologien und Smart Grid. Durch das intensive Befassen mit diesen Themen haben sich die
Studierenden zum ersten Mal richtig mit den Problemen der Energiewende vertraut gemacht. Sie haben
dabei erkannt, dass für die Ingenieure der Fachrichtungen Elektrotechnik und Informationstechnik überaus
vielfältige, spannende und auch aus gesellschaftspolitischer Sicht notwendige und lohnende Aufgaben auf
sie warten.
SInCom 2015
(2015)
Increasing robustness of handwriting recognition using character N-Gram decoding on large lexica
(2016)
Offline handwriting recognition systems often include a decoding step, that is retrieving the most likely character sequence from the underlying machine learning algorithm. Decoding is sensitive to ranges of weakly predicted characters, caused e.g. by obstructions in the scanned document. We present a new algorithm for robust decoding of handwriting recognizer outputs using character n-grams. Multidimensional hierarchical subsampling artificial neural networks with Long-Short-Term-Memory cells have been successfully applied to offline handwriting recognition. Output activations from such networks, trained with Connectionist Temporal Classification, can be decoded with several different algorithms in order to retrieve the most likely literal string that it represents. We present a new algorithm for decoding the network output while restricting the possible strings to a large lexicon. The index used for this work is an n-gram index with tri-grams used for experimental comparisons. N-grams are extracted from the network output using a backtracking algorithm and each n-gram assigned a mean probability. The decoding result is obtained by intersecting the n-gram hit lists while calculating the total probability for each matched lexicon entry. We conclude with an experimental comparison of different decoding algorithms on a large lexicon.
Im Rahmen der Lehrveranstaltung "Nachhaltigkeit im industriellen Umfeld" im Masterstudiengang Umwelt- und Verfahrenstechnik der Hochschulen Konstanz und Ravensburg-Weingarten wurde 2015 eine studentische Fachkonferenz durchgeführt.
Die Studierenden entwickelten in Einzelarbeit oder als Zweierteam Konferenzbeiträge zu folgenden Themen:
- Innovationen und Spannendes aus dem Bereich der Energieerzeugung und -wandlung
- Aspekte der Schließung von Stoffkreisläufen und Vermeidung von Schadstoffeinträgen in die Umwelt
- Chancen und Herausforderungen Nachwachsender Rohstoffe bei verschiedenen Einsatzmöglichkeiten sowie Themen der Nachhaltigkeit in der Landwirtschaft
- verschiedene Blickwinkel auf das Thema Wasser (von der Abwasserreinigung bis zum Wasserkonsum der Konsumenten)
- die Betrachtung spezifischer Industrien und Unternehmen sowie deren Werkzeuge zur Umsetzung von Nachhaltigkeit
Die Ergebnisse der studentischen Fachkonferenz zur „Nachhaltigkeit im industriellen Umfeld“ werden in der vorliegenden Publikation präsentiert.
In the reverse engineering process one has to classify parts of point clouds with the correct type of geometric primitive. Features based on different geometric properties like point relations, normals, and curvature information can be used, to train classifiers like Support Vector Machines (SVM). These geometric features are estimated in the local neighborhood of a point of the point cloud. The multitude of different features makes an in-depth comparison necessary. In this work we evaluate 23 features for the classification of geometric primitives in point clouds. Their performance is evaluated on SVMs when used to classify geometric primitives in simulated and real laser scanned point clouds. We also introduce a normalization of point cloud density to improve classification generalization.
Im Rahmen der Lehrveranstaltung "Nachhaltigkeit im industriellen Umfeld" im Masterstudiengang Umwelt- und Verfahrenstechnik der Hochschulen Konstanz und Ravensburg-Weingarten fand im Dezember 2016 eine studentische Fachkonferenz statt. Die Studierenden entwickelten in Einzelarbeit oder als Zweierteam
Konferenzbeiträge zu folgenden Themen:
- Spannendes aus dem Bereich der Energieerzeugung und der Grauen Energie
- Aspekte der Kreislaufwirtschaft
- Ökosysteme - ihre Belastung und Erhalt
- Spezifische Wirtschaftszweige und Nachhaltigkeit
Die Ergebnisse der studentischen Fachkonferenz zur „Nachhaltigkeit im
industriellen Umfeld“ werden in der vorliegenden Publikation präsentiert.
InBetween
(2017)
In tourism, energy demands are particularly high.Tourism facilities such as hotels require large amounts ofelectric and heating resp. cooling energy. Their supply howeveris usually still based on fossil energies. This research approachanalyses the potential of promoting renewable energies in BlackForest tourism. It focuses on a combined and hence highlyefficient production of both electric and thermal energy bybiogas plants on the one hand and its provision to local tourismfacilities via short distance networks on the other. Basing onsurveys and qualitative empiricism and considering regionalresource availability as well as socio-economic aspects, it thusexamines strengths, weaknesses, opportunities and threats thatcan arise from such a cooperation.
We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each 1≤k≤kmax, a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this “learning to cluster” and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end.
Smart-Future-Living-Bodensee
(2018)
In tourism, energy demands are particularly high. Tourism facilities such as hotels require large amounts of electric and heating / cooling energy while their supply is usually still based on fossil energies.
This research approach analyses the potential of promoting renewable energies in tourism. It focuses on a combined and hence highly efficient production of both electric and thermal energy by biogas plants on the one hand and its provision to local tourism facilities via short distance networks on the other. Considering regional resource availability as well as socio-economic aspects, it thus examines strengths, weaknesses, opportunities and threats that can arise from such a micro-cooperation. The research aim is to provide an actor-based, spatially transferable feasibility analysis.
Offline handwriting recognition systems often use LSTM networks, trained with line- or word-images. Multi-line text makes it necessary to use segmentation to explicitly obtain these images. Skewed, curved, overlapping, incorrectly written text, or noise can lead to errors during segmentation of multi-line text and reduces the overall recognition capacity of the system. Last year has seen the introduction of deep learning methods capable of segmentation-free recognition of whole paragraphs. Our method uses Conditional Random Fields to represent text and align it with the network output to calculate a loss function for training. Experiments are promising and show that the technique is capable of training a LSTM multi-line text recognition system.
Algorithms for calculating the string edit distance are used in e.g. information retrieval and document analysis systems or for evaluation of text recognizers. Text recognition based on CTC-trained LSTM networks includes a decoding step to produce a string, possibly using a language model, and evaluation using the string edit distance. The decoded string can further be used as a query for database search, e.g. in document retrieval. We propose to closely integrate dictionary search with text recognition to train both combined in a continuous fashion. This work shows that LSTM networks are capable of calculating the string edit distance while allowing for an exchangeable dictionary to separate learned algorithm from data. This could be a step towards integrating text recognition and dictionary search in one deep network.
Deep neural networks have become a veritable alternative to classic speaker recognition and clustering methods in recent years. However, while the speech signal clearly is a time series, and despite the body of literature on the benefits of prosodic (suprasegmental) features, identifying voices has usually not been approached with sequence learning methods. Only recently has a recurrent neural network (RNN) been successfully applied to this task, while the use of convolutional neural networks (CNNs) (that are not able to capture arbitrary time dependencies, unlike RNNs) still prevails. In this paper, we show the effectiveness of RNNs for speaker recognition by improving state of the art speaker clustering performance and robustness on the classic TIMIT benchmark. We provide arguments why RNNs are superior by experimentally showing a “sweet spot” of the segment length for successfully capturing prosodic information that has been theoretically predicted in previous work.
Today’s markets are characterized by fast and radical changes, posing an essential challenge to established companies. Startups, yet, seem to be more capable in developing radical innovations to succeed in those volatile markets. Thus, established companies started to experiment with various approaches to implement startup-like structures in their organization. Internal corporate accelerators (ICAs) are a novel form of corporate venturing, aiming to foster bottom-up innovations through intrapreneurship. However, ICAs still lack empirical investigations. This work contributes to a deeper understanding of the interface between the ICA and the core organization and the respective support activities (resource access and support services) that create an innovation-supportive work environment for the intrapreneurial team. The results of this qualitative study, comprising 12 interviews with ICA teams out of two German high-tech companies, show that the resources provided by ICAs differ from the support activities of external accelerators. Further, the study shows that some resources show both supportive as well as obstructive potential for the intrapreneurial teams within the ICA.