1 - 10 of 4105
-
-
PublicationQ-switched Ho3+:YAG Porro resonators with improved alignment stability( 2023-03-08)We present a crossed-Porro prism resonator with a Ho3+:YAG crystal and investigate it with a focus on the alignment stability. Furthermore, we show a single-Porro-ended resonator optimized for Q-switched operation. Both resonators are compared to corresponding mirror resonators. In the crossed-Porro prism resonator, a maximum output power of 30.7 W is reached with a high slope efficiency of 67.4 %. By tilting each of the prism axes one by one and measuring the entailed drop in output power, the alignment sensitivity is determined. In comparison to a corresponding mirror resonator, it is improved by a factor of up to 200. With this design, 170 ns Q-switched pulses with an energy of 0.51 mJ are generated at a repetition rate of 50 kHz. In the single-Porroended resonator significantly shorter pulses with a duration of 55 ns and a maximum pulse energy of 0.8 mJ were achieved.
-
PublicationMethodische Evaluation von Verfahren zur Korrektur atmosphärischer Turbulenz in Bildsequenzen(KIT, 2023-03-01)Bei langen horizontalen Ausbreitungswegen in Bodennähe ist die Atmosphäre und nicht die Qualität moderner bildgebender Systeme ausschlaggebend für die Qualität aufgenommener Bilddaten. Besonders wird die Bildqualität durch atmosphärische Turbulenz beeinträchtigt, die je nach Schweregrad zeitlich und räumlich variierende Unschärfe, (scheinbare) Bildbewegungen und geometrische Deformationen, sowie Intensitätsfluktuationen (Szintillation), verringerten (Farb-)Kontrast und Rauschen verursacht. Korrekturverfahren haben entsprechend die Aufgabe, einen, mehrere oder ggfs. alle dieser Turbulenzeffekte in Bilddaten zu reduzieren und diese bestmöglich zu rekonstruieren. Im Idealfall wäre eine solche Rekonstruktion identisch mit einer Aufnahme am Diffraktionslimit ohne Turbulenz.
-
PublicationEffects of Architectures on Continual Semantic Segmentation( 2023-02-21T15:12:01Z)Research in the field of Continual Semantic Segmentation is mainly investigating novel learning algorithms to overcome catastrophic forgetting of neural networks. Most recent publications have focused on improving learning algorithms without distinguishing effects caused by the choice of neural architecture.Therefore, we study how the choice of neural network architecture affects catastrophic forgetting in class- and domain-incremental semantic segmentation. Specifically, we compare the well-researched CNNs to recently proposed Transformers and Hybrid architectures, as well as the impact of the choice of novel normalization layers and different decoder heads. We find that traditional CNNs like ResNet have high plasticity but low stability, while transformer architectures are much more stable. When the inductive biases of CNN architectures are combined with transformers in hybrid architectures, it leads to higher plasticity and stability. The stability of these models can be explained by their ability to learn general features that are robust against distribution shifts. Experiments with different normalization layers show that Continual Normalization achieves the best trade-off in terms of adaptability and stability of the model. In the class-incremental setting, the choice of the normalization layer has much less impact. Our experiments suggest that the right choice of architecture can significantly reduce forgetting even with naive fine-tuning and confirm that for real-world applications, the architecture is an important factor in designing a continual learning model.
-
PublicationSynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning( 2023-01-11)In this paper, we develop a novel benchmark suite including both a 2D synthetic image dataset and a 3D synthetic point cloud dataset. Our work is a sub-task in the framework of a remanufacturing project, in which small electric motors are used as fundamental objects. Apart from the given detection, classification, and segmentation annotations, the key objects also have multiple learnable attributes with ground truth provided. This benchmark can be used for computer vision tasks including 2D/3D detection, classification, segmentation, and multi-attribute learning. It is worth mentioning that most attributes of the motors are quantified as continuously variable rather than binary, which makes our benchmark well-suited for the less explored regression tasks. In addition, appropriate evaluation metrics are adopted or developed for each task and promising baseline results are provided. We hope this benchmark can stimulate more research efforts on the sub-domain of object attribute learning and multi-task learning in the future.
-
PublicationGenerative-Contrastive Learning for Self-Supervised Latent Representations of 3D Shapes from Multi-Modal Euclidean Input( 2023-01-11T18:14:24Z)We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes. The architecture uses two encoder branches for voxel grids and multi-view images from the same underlying shape. The main idea is to combine a contrastive loss between the resulting latent representations with an additional reconstruction loss. That helps to avoid collapsing the latent representations as a trivial solution for minimizing the contrastive loss. A novel switching scheme is used to cross-train two encoders with a shared decoder. The switching scheme also enables the stop gradient operation on a random branch. Further classification experiments show that the latent representations learned with our self-supervised method integrate more useful information from the additional input data implicitly, thus leading to better reconstruction and classification performance.
-
PublicationObject Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding( 2023-01-11)We present an improved approach for 3D object detection in point cloud data based on the Frustum PointNet (F-PointNet). Compared to the original F-PointNet, our newly proposed method considers the point neighborhood when computing point features. The newly introduced local neighborhood embedding operation mimics the convolutional operations in 2D neural networks. Thus features of each point are not only computed with the features of its own or of the whole point cloud but also computed especially with respect to the features of its neighbors. Experiments show that our proposed method achieves better performance than the F-Pointnet baseline on 3D object detection tasks.
-
PublicationPilot Study on Interaction with Wide Area Motion Imagery Comparing Gaze Input and Mouse Input( 2023)
-
PublicationDatenökosysteme und Datenräume schaffen Mehrwert( 2023)In Deutschland waren 2022 knapp 7,5 Millionen Menschen in Betrieben des verarbeitenden Gewerbes mit 50 und mehr Beschäftigten tätig. Direkt und indirekt hängen rund 15 Millionen der knapp 45 Millionen Arbeitsplätze von der produzierenden Wirtschaft ab. Der Wohlstand Deutschlands als rohstoffarmes Land hängt also auch künftig massiv von innovativer und effizienter Wertschöpfung ab. Neue Produkt-Service-Systeme der Fabrikausrüster unterstützen die produzierende Industrie dabei und machen sie resilienter.
-
PublicationCounterfactual Root Cause Analysis via Anomaly Detection and Causal Graphs( 2023)Anomalies in production processes can cause expensive standstills, damages to the production equipment, waste of materials and flaws in the final product. In production, finding anomalies is usually accomplished by machine learning methods. But to avert anomalies and to automatically recover, actually the detection of the root causes is required. We developed an approach that detects anomalies and then deduces root causes by combining an anomaly detector with a novel Root Cause Analysis (RCA) method based on a causal graph. This specific combination of methods allows causally justified, explainable and counterfactual RCA. The developed algorithm was applied to a simulated gripping process using robotic arms. It found the two root causes of the detected anomalies in the simulated scenarios.
