Steiniger, Yannik
Lade...
9 Ergebnisse
Gerade angezeigt 1 - 9 von 9
- Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Erzeugung von synthetischen Seitensichtsonar-Bildern mittels Generative Adversarial NetworksFür die Anwendung von Deep-Learning-Methoden zur automatischen Auswertung von Daten bildgebender Sonare stellt die nicht vorhandene Verfügbarkeit größerer Trainingsdatenmengen nach wie vor ein Problem dar. In den letzten Jahren wurden jedoch sogenannte Generative Adversarial Networks (GAN) als ein Werkzeug aus dem Bereich Deep Learning für die Erzeugung synthetischer Daten entwickelt. In dieser Arbeit wird untersucht, inwieweit sich GANs zur Erzeugung künstlicher Sonarbilder eignen. Um das GAN auch mit wenigen Beispielen trainieren zu können, wird eine Art des Transfer-Lernens mit Hilfe von einfachen simulierten Bildern entwickelt. Es zeigt sich, dass die Performance eines Klassifikators durch Hinzunahme der künstlichen Bilder gesteigert werden kann.Wissenschaftlicher ArtikelHeft:11969 - 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, Survey on deep learning based computer vision for sonar imageryResearch on the automatic analysis of sonar images has focused on classical, i.e. non deep learning based, approaches for a long time. Over the past 15 years, however, the application of deep learning in this research field has constantly grown. This paper gives a broad overview of past and current research involving deep learning for feature extraction, classification, detection and segmentation of sidescan and synthetic aperture sonar imagery. Most research in this field has been directed towards the investigation of convolutional neural networks (CNN) for feature extraction and classification tasks, with the result that even small CNNs with up to four layers outperform conventional methods. The purpose of this work is twofold. On one hand, due to the quick development of deep learning it serves as an introduction for researchers, either just starting their work in this specific field or working on classical methods for the past years, and helps them to learn about the recent achievements. On the other hand, our main goal is to guide further research in this field by identifying main research gaps to bridge. We propose to leverage the research in this field by combining available data into an open source dataset as well as carrying out comparative studies on developed deep learning methods.Wissenschaftlicher ArtikelBand:114276 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, 31 - 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, Tackling data scarcity in sonar image classification with hybrid scattering neural networksData scarcity remains the main challenge when developing deep learning models for sonar image analysis. Although dataset augmentation with synthetically generated images has been proposed, these methods are far from optimal as they are unable to capture the range of physical factors affecting sonar images, given the small data regimes used for their training. This work focuses on an alternative solution and investigates the learning of suitable representations for classifying small-sized sonar datasets. To achieve this, we propose a new approach that entails the combination of convolutional and scattering neural networks, a wavelet-based neural network that produces feature map representations robust to image variations. Our experiments show that these representations are easier to classify, leading to a performance increase of 4.5 percentage points in F1-score for the combined network compared to a plain convolutional neural network. Furthermore, we interpret the representation obtained by the scattering transformation as robust feature descriptors, where the geometric shapes of underwater objects are rendered prominent and stable to minor sonar distortions.Wissenschaftlicher Artikel71 - 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, Generating Synthetic Sidescan Sonar Snippets Using Transfer-Learning in Generative Adversarial NetworksThe training of a deep learning model requires a large amount of data. In case of sidescan sonar images, the number of snippets from objects of interest is limited. Generative adversarial networks (GAN) have shown to be able to generate photo-realistic images. Hence, we use a GAN to augment a baseline sidescan image dataset with synthetic snippets. Although the training of a GAN with few data samples is likely to cause mode collapse, a combination of pre-training using simple simulated images and fine-tuning with real data reduces this problem. However, for sonar data, we show that this approach of transfer-learning a GAN is sensitive to the pre-training step, meaning that the vanishing of the gradients of the GAN’s discriminator becomes a critical problem. Here, we demonstrate how to overcome this problem, and thus how to apply transfer-learning to GANs for generating synthetic sidescan snippets in a more robust way. Additionally, in order to further investigate the GAN’s ability to augment a sidescan image dataset, the generated images are analyzed in the image and the frequency domain. The work helps other researchers in the field of sonar image processing to augment their dataset with additional synthetic samples.Wissenschaftlicher ArtikelBand:9Heft:371 - 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