Stoppe, Jannis Ulrich
Lade...
5 Ergebnisse
Einstellungen
Gerade angezeigt 1 - 5 von 5
- Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Investigating the training of convolutional neural networks with limited sidescan sonar image datasetsFor the automatic analysis of sonar images, deep learning methods, like convolutional neural networks (CNN), outperform traditional approaches. However, the training of a CNN requires a sufficient dataset, which is difficult to obtain. Thus, ways to improve the training of CNNs with limited data are necessary to reach a reasonable performance of the networks under such circumstances. In our work we consider an extreme case of having less than 20 samples per class to train a CNN for classification. We train two custom CNNs with various depths from scratch, as well as the even deeper VGG-16 network, which is a commonly used architecture for sonar imagery. Furthermore, the benefits of several augmentation methods in the sonar imagery context are investigated. In addition, we study how the image complexity can be reduced so that a CNN can learn more efficiently with the limited training data. Besides, we evaluate if we can feed additional features to the CNN for a further improvement. Our best model is a VGG-16 which is trained using flipping, cropping and addition of Gaussian noise for data augmentation. The complexity of the input images is reduced using tight bounding boxes for snippet extraction, which remove the object size information. Adding this size information as an explicit feature to the CNN increases the performance and results in a balanced accuracy of 77.2%.Wissenschaftlicher Artikel89 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Verbesserung der Klassifikationsperformance von Deep Learning Modellen durch Reduktion der Komplexität von Seitensichtsonarbildern(Deutsche Gesellschaft für Akustik e.V., 2023); ; ; Wissenschaftlicher Artikel47 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, On the detection and classification of objects in scarce sidescan sonar image dataset with deep learning methodsApplying deep learning detection methods to sonar imagery is a challenging task due to the complexity of the image itself as well as the limited amount of available data. In this work, we analyze one-step and two-step setups for detection multiple different objects in sidescan sonar images. The one-step setup and the first step in the two-step setup uses standard deep learning models, like YOLOv8, to either directly locate and classify the objects or to serve as a snippet extractor. In the second step these extracted snippets are further classified by a convolutional neural network. Furthermore, we investigate a setup in which the detected objects from the one-step approach are filtered by another CNN to reduce false alarms. Finally, we compare the performance of multiple deep learning detectors to a classical two-step approach using template matching combined with a CNN. Our results show that both two-step setups generate less false alarms. Furthermore, all deep learning models outperform the template matching approach.Wissenschaftlicher Artikel83 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, SystemC Through the Looking Glass : Non-Intrusive Analysis of Electronic System Level Designs in SystemC(2017-02-07); ; ; Due to the ever increasing complexity of hardware and hardware/software co-designs, developers strive for higher levels of abstractions in the early stages of the design flow. To address these demands, design at the Electronic System Level (ESL) has been introduced. SystemC currently is the "de-facto standard" for ESL design. The extraction of data from system designs written in SystemC is thereby crucial e.g. for the proper understanding of a given system. However, no satisfactory support of reflection/introspection of SystemC has been provided yet. Previously proposed methods for this purpose %introduced to achieve the goal nonetheless either focus on static aspects only, restrict the language means of SystemC, or rely on modifications of the compiler and/or parser. In this thesis, approaches that overcome these limitations are introduced, allowing the extraction of information from a given SystemC design without changing the SystemC library or the compiler. The proposed approaches retrieve both, static and dynamic (i.e. run-time) information.Dissertation760 207 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, A study on modern deep learning detection algorithms for automatic target recognition in sidescan sonar images(American Instut. of Physics, 2021); ; ; ; State-of-the art deep learning models have shown remarkable performance on computer vision tasks like object classification or detection. These networks are typically trained on large-scale datasets of natural RGB images. However, sidescan sonar images are gray-scaled images representing acoustic intensities. The fundamental differences between camera and sonar as well as the images itself makes it necessary to investigate the transfer of results achieved on RGB images to the sonar imagery domain. Therefore, we compare the deep learning detection algorithm YOLOv2 with its updated version YOLOv3, both adopted for object detection in sidescan sonar images. In addition to this, a small convolutional neural network (CNN) is trained from scratch and used for detection. The experiments answer two questions: First, whether, as for general computer vision problems, transfer learning of large deep learning models is preferable over training of custom networks when dealing with limited sonar data. Secondly, whether improvements in the YOLO architecture, developed based on RGB images, lead to significant improvements on sonar data as well. Our results show that YOLOv3 indeed performs better than YOLOv2. Furthermore, YOLOv3 achieves a true positive rate of up to 98.2% and outperforms the small CNN.Wissenschaftlicher ArtikelHeft:4482