1,720,956 research outputs found
Mind the Gap: On the Domain Shift Between Synthetic and Real-World 3D Data for Indoor Object Detection
No full text3D-Objekterkennung ist in verschiedenen Bereichen, darunter Robotik und autonome Fahrzeuge, von entscheidender Bedeutung. Während synthetische Daten, die mit Spiele-Engines erzeugt wurden, bereits zur Überwindung von Datenbeschränkungen getestet wurden, wurde der Domänenunterschied zwischen synthetischen und realen LiDAR-Daten in Innenräumen bisher nicht untersucht. Deshalb analysiert diese Arbeit den Einfluss synthetischer Daten auf die Leistung von 3D-Objekterkennungs-algorithmen in Innenraumumgebungen.Zu diesem Zweck wurde synthetische LiDAR-Daten mithilfe der Unreal Engine in verschiedenen vorgefertigten Apartment- und Hausumgebungen generiert. Anschließend wurden mehrere 3D-Objekterkennungsmodelle unter verschiedenen Bedingungen trainiert: ausschließlich mit realen Daten, ausschließlich mit synthetischen Daten und mit einer Kombination aus beiden.Zwei Modelle zur 3D-Objekterkennung, VoteNet und KPConv, wurden jeweils mit realen Daten, synthetischen Daten und einer Kombination aus beiden trainiert. VoteNet hatte dabei erhebliche Schwierigkeiten, die Daten zu lernen, und konnte in dieser Arbeit nicht zur Abschätzung des Domänenunterschieds verwendet werden. KPConv hingegen konnte erfolgreich trainiert werden. Die experimentellen Ergebnisse mit KPConv zeigen, dass das Training ausschließlich mit synthetischen Daten und die anschließende Evaluierung mit realen Daten („sim-to-real“) zu einer leichten Leistungssteigerung im Vergleich zum reinen Training und Testen mit realen Daten führte. Auch das Training mit einem kombinierten Datensatz aus realen und synthetischen Daten zeigte eine leichte Leistungssteigerung gegenüber dem ausschließlichen Einsatz realer Daten.Diese Ergebnisse verdeutlichen sowohl das Potenzial als auch die Einschränkungen synthetischer LiDAR-Daten für die 3D-Objekterkennung in Innenräumen. Die Generierung synthetischer LiDAR-Daten könnte eine vielversprechende Methode sein, um Datensätze gezielt zu erweitern und die Modellleistung für verschiedene Anwendungen zu verbessern. Allerdings sind weitere Untersuchungen erforderlich, um den Realismus der synthetischen Daten weiter zu verbessern.3D object detection is critical in various domains, including robotics and autonomous vehicles. While synthetic data generated using game engines has been tested to overcome data limitations, the domain shift between synthetic and real-world indoor environment data has not been investigated yet. Therefore, this thesis investigates the impact of synthetic data on the performance of 3D object detection algorithms in indoor environments.Synthetic LiDAR data was generated using the Unreal Engine in several readily available apartment and house environments. Different 3D object detection models were then trained under different conditions: using only real-world data, only synthetic data, and a combination of both.Two 3D object detection models, VoteNet and KPConv, were trained using only real data, synthetic data, and a combination of both. VoteNet faced significant challenges in learning the data and could not be used to estimate the domain shift in this study. However, KPConv was trained successfully. Experimental results with KPConv indicate that training exclusively on synthetic data and evaluating on real-world data ("sim-to-real") resulted in a slight performance increase when evaluated on real-world data compared to training and evaluating solely on real data. Furthermore, training with a combined real and synthetic dataset also led to a slight performance increase when evaluated on real data compared to using only real data.These findings highlight both the promise and limitations of synthetic data for 3D object detection in indoor environments. Generating synthetic LiDAR data could be a viable way to enhance datasets with more nuanced data, improving model performance for various applications. However, further research is needed to improve the realism of the synthetic data.Bachelorarbeit FH JOANNEUM 202
Mind the gap : on the domain shift between synthetic and real-world 3D data for indoor object detection
No full text3D-Objekterkennung ist in verschiedenen Bereichen, darunter Robotik und autonome Fahrzeuge, von entscheidender Bedeutung. Während synthetische Daten, die mit Spiele-Engines erzeugt wurden, bereits zur Überwindung von Datenbeschränkungen getestet wurden, wurde der Domänenunterschied zwischen synthetischen und realen LiDAR-Daten in Innenräumen bisher nicht untersucht. Deshalb analysiert diese Arbeit den Einfluss synthetischer Daten auf die Leistung von 3D-Objekterkennungs-algorithmen in Innenraumumgebungen. Zu diesem Zweck wurde synthetische LiDAR-Daten mithilfe der Unreal Engine in verschiedenen vorgefertigten Apartment- und Hausumgebungen generiert. Anschließend wurden mehrere 3D-Objekterkennungsmodelle unter verschiedenen Bedingungen trainiert: ausschließlich mit realen Daten, ausschließlich mit synthetischen Daten und mit einer Kombination aus beiden. Zwei Modelle zur 3D-Objekterkennung, VoteNet und KPConv, wurden jeweils mit realen Daten, synthetischen Daten und einer Kombination aus beiden trainiert. VoteNet hatte dabei erhebliche Schwierigkeiten, die Daten zu lernen, und konnte in dieser Arbeit nicht zur Abschätzung des Domänenunterschieds verwendet werden. KPConv hingegen konnte erfolgreich trainiert werden. Die experimentellen Ergebnisse mit KPConv zeigen, dass das Training ausschließlich mit synthetischen Daten und die anschließende Evaluierung mit realen Daten („sim-to-real“) zu einer leichten Leistungssteigerung im Vergleich zum reinen Training und Testen mit realen Daten führte. Auch das Training mit einem kombinierten Datensatz aus realen und synthetischen Daten zeigte eine leichte Leistungssteigerung gegenüber dem ausschließlichen Einsatz realer Daten. Diese Ergebnisse verdeutlichen sowohl das Potenzial als auch die Einschränkungen synthetischer LiDAR-Daten für die 3D-Objekterkennung in Innenräumen. Die Generierung synthetischer LiDAR-Daten könnte eine vielversprechende Methode sein, um Datensätze gezielt zu erweitern und die Modellleistung für verschiedene Anwendungen zu verbessern. Allerdings sind weitere Untersuchungen erforderlich, um den Realismus der synthetischen Daten weiter zu verbessern.3D object detection is critical in various domains, including robotics and autonomous vehicles. While synthetic data generated using game engines has been tested to overcome data limitations, the domain shift between synthetic and real-world indoor environment data has not been investigated yet. Therefore, this thesis investigates the impact of synthetic data on the performance of 3D object detection algorithms in indoor environments. Synthetic LiDAR data was generated using the Unreal Engine in several readily available apartment and house environments. Different 3D object detection models were then trained under different conditions: using only real-world data, only synthetic data, and a combination of both. Two 3D object detection models, VoteNet and KPConv, were trained using only real data, synthetic data, and a combination of both. VoteNet faced significant challenges in learning the data and could not be used to estimate the domain shift in this study. However, KPConv was trained successfully. Experimental results with KPConv indicate that training exclusively on synthetic data and evaluating on real-world data ("sim-to-real") resulted in a slight performance increase when evaluated on real-world data compared to training and evaluating solely on real data. Furthermore, training with a combined real and synthetic dataset also led to a slight performance increase when evaluated on real data compared to using only real data. These findings highlight both the promise and limitations of synthetic data for 3D object detection in indoor environments. Generating synthetic LiDAR data could be a viable way to enhance datasets with more nuanced data, improving model performance for various applications. However, further research is needed to improve the realism of the synthetic data.submitted by: Georg Arbesser-RastburgBachelorarbeit FH JOANNEUM 202
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
Author-wise bibliometric analysis based on entropy.
No full textAuthor-wise bibliometric analysis based on entropy.</p
- …
