004 Informatik
Refine
Document Type
- Bachelor Thesis (2)
- Master's Thesis (1)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3)
Keywords
- API (1)
- Automatisierung (1)
- Autonomie (1)
- CSAF (1)
- Computersicherheit (1)
- Datenqualität (1)
- Deep learning (1)
- Fußgängererkennung (1)
- Go <Programmiersprache> (1)
- Golang (1)
Institute
Open Access
- Diamond (3) (remove)
Garbage in, Garbage out: How does ambiguity in data affect state-of-the-art pedestrian detection?
(2024)
This thesis investigates the critical role of data quality in computer vision, particularly in the realm of pedestrian detection. The proliferation of deep learning methods has emphasised the importance of large datasets for model training, while the quality of these datasets is equally crucial. Ambiguity in annotations, arising from factors like mislabelling, inaccurate bounding box geometry and annotator disagreements, poses significant challenges to the reliability and robustness of the pedestrian detection models and their evaluation. This work aims to explore the effects of ambiguous data on model performance with a focus on identifying and separating ambiguous instances, employing an ambiguity measure utilizing annotator estimations of object visibility and identity. Through accurate experimentation and analysis, trade-offs between data cleanliness and representativeness, noise removal and retention of valuable data emerged, elucidating their impact on performance metrics like the log average miss-rate, recall and precision. Furthermore, a strong correlation between ambiguity and occlusion was discovered with higher ambiguity corresponding to greater occlusion prevalence. The EuroCity Persons dataset served as the primary dataset, revealing a significant proportion of ambiguous instances with approximately 8.6% ambiguity in the training dataset and 7.3% in the validation set. Results demonstrated that removing ambiguous data improves the log average miss-rate, particularly by reducing the false positive detections. Augmentation of the training data with samples from neighbouring classes enhanced the recall but diminished precision. Error correction of wrong false positives and false negatives significantly impacts model evaluation results, as evidenced by shifts in the ECP leaderboard rankings. By systematically addressing ambiguity, this thesis lays the foundation for enhancing the reliability of computer vision systems in real-world applications, motivating the prioritisation of developing robust strategies to identify, quantify and address ambiguity.
Die vorliegende Arbeit beschäftigt sich mit der Nutzung von Reinforcement Learning in der Informationsbeschaffungs-Phase eines Penetration Tests. Es werden Kernprobleme in den bisherigen Ansätzen anderer das Thema betreffender wissenschaftlicher Arbeiten analysiert und praktische Lösungsansätze für diese bisherigen Hindernisse vorgestellt und implementiert. Die Arbeit zeigt damit eine beispielhafte Implementierung eines Reinforcement Learning Agenten zur Automatisierung der Informationsbeschaffungs-Phase eines Penetration Tests und stellt Lösungen für existierende Probleme in diesem Bereich dar.
Eingebettet wird diese wissenschaftliche Arbeit in die Anforderungen der Herrenknecht AG hinsichtlich der Absicherung des Tunnelbohrmaschinen-Netzwerks. Dabei werden praktische Ergebnisse des eigen entwickelten Reinforcement Learning Modells im Tunnelbohrmaschinen-Test-Netzwerk der Herrenknecht AG vorgestellt.
This work addresses the conceptualization, design, and implementation of an Application Programming Interface (API) for the Common Security Advisory Framework (CSAF) 2.0, introducing another method for distributing CSAF documents in addition to two already existing methods. These don't allow the use of flexible queries as well as filtering, which makes it difficult for operators of software and hardware to use CSAF. An API is intended to simplify this process and thus advance the automation goal of CSAF.
First, it is evaluated whether the current standard allows the implementation of an API. Any conflicts are highlighted and suggestions for standard adaptations are made. Based on these results, the API is designed to meet the previously defined requirements. Subsequently, a proof of concept is successfully developed according to the design and extensively tested with specially prepared test data. Finally, the results and the necessary standard adjustments are summarized and justified.
The conceptual design and the implementation were successfully completed. However, during the implementation of the proof of concept, some routes could not be fully implemented.