05 Fakultät Informatik, Elektrotechnik und Informationstechnik
Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/6
Browse
11 results
Search Results
Item Open Access Improving automotive radar spectra object classification using deep learning and multi-class uncertainty calibration(2022) Patel, Kanil; Yang, Bin (Prof. Dr.-Ing.)Being a prerequisite for successful automated driving, ameliorating the perception capabilities of vehicles is of paramount importance for reliable and robust scene understanding. Required for decision-making in autonomous vehicles, scene understanding becomes particularly challenging in adverse weather and lighting conditions; situations also often posing challenges for human drivers. Automotive radars can greatly assist sensors currently deployed on vehicles for robust measurements, especially in challenging conditions where other sensors often fail to operate reliably. However, classification using radar sensors is often limited to a few classes (e.g. cars, humans, and stop signs), controlled laboratory settings, and/or simulations. Already offering reliable distance, azimuth and velocity estimates of the objects in the scene, improving radar-based classification greatly expands the usage of radar sensors for tackling multiple driving-related tasks which are often performed by other less robust sensors. This thesis investigates how automated driving perception can be improved using multi-class radar classification by using deep learning algorithms for exploiting object class characteristics captured in the radar spectra. Despite the highly-accurate predictions of deep learning models, such classifiers exhibit severe over-confidence which can lead decision-making systems to false conclusions, with possibly catastrophic consequences - often a matter of life and death for automated driving. Consequently, high-quality, robust, and interpretable uncertainty estimates are indispensable characteristics of any unassailable automated driving system. With the goal of uncertainty estimates for real-time predictive systems, this thesis also aims at tackling the prominent over-confidence of deep learning classification models, which persists for all data modalities. Being an important measure for the quality of uncertainty estimates, this work focuses on the accurate estimation of the calibration of trained classifiers, as well as present novel techniques for improving their calibration. The presented solutions offer high-quality real-time confidence estimates for classification models of all data modalities (e.g. non-radar applications), as well as classifiers which are already trained and used in practise and new training strategies for learning new classifiers. Furthermore, the presented uncertainty calibration algorithms could also be extended to tasks other than classification, for example, regression and segmentation. On a challenging new realistic automated driving radar dataset, the solutions proposed in this thesis show that radar classifiers are able to generalize to novel driving environments, driving patterns, and object instances in realistic static driving scenes. To further replicate realistic encounters of autonomous vehicles, we study the behaviour of the classifiers to spectra corruptions and outlier detection of unknown objects, showing significant performance improvements in safely handling these prevalent encounters through accurate uncertainty estimates. With the proposed generalization and requisite accurate uncertainty estimation techniques, the radar classifiers in this study greatly improve radar-based perception for scene understanding and lay a solid foundation for current sensor fusion techniques to leverage radar measurements for object classification.Item Open Access Rehearsal-based continual learning with deep neural networks for image classification(2024) Wiewel, Felix; Yang, Bin (Prof. Dr.-Ing.)Item Open Access Least-squares based layerwise pruning of Deep Neural Networks(2024) Mauch, Lukas; Yang, Bin (Prof. Dr.-Ing.)Tiefe Neuronale Netze (DNNs) sind derzeit die leistungsstärksten Modelle im Bereich des maschinellen Lernens und lösen erfolgreich viele Aufgaben, wie zum Beispiel Bild- und Spracherkennung, semantische Segmentierung oder Datengenerierung. Aufgrund der inhärent hohen Rechenkomplexität von DNNs wurden schon früh Pruningverfahren angewandt um die Rechenkomplexität von DNNs zu reduzieren und um die Inferenz zu beschleunigen. Pruningverfahren entfernen (prunen) Parameter aus einem trainierten DNN, ohne ihre Leistung dadurch signifikant zu beeinträchtigen. Die dadurch erhaltenen Modelle können auch auf schwachen Rechenplattformen mit hoher Geschwindigkeit ausgewertet werden. In den letzten Jahren wurden Pruningverfahren nicht nur nach dem Training, sondern auch als Bestandteil von modernen Trainingsalgorithmen für DNNs eingesetzt. So wenden zum Beispiel viele speichereffiziente Trainingsalgorithmen oder Architektursuchverfahren pruning schon während des Trainings an, um unwichtige Parameter aus dem DNN zu entfernen. Problematisch ist, dass viele moderne Pruningverfahren auf regularisierten, überwachten Trainingverfahren beruhen und daher selbst sehr rechenaufwändig sind. Solche Pruningverfahren können nicht ohne Weiteres in andere Trainingsalgorithmen eingebettet werden. Es besteht daher ein wachsendes Interesse an Pruningmethoden, die sowohl schnell als auch genau sind. In dieser Arbeit untersuchen wir das layerbasierte Least-Squares (LS) Pruning – ein Framework für das strukturierte Pruning von DNNs. Wir zeigen, dass LS-Pruning eine schnelleund dennoch genaue Methode für die DNN-reduktion ist, die für Zero-Shot oder für die unüberwachte Netzwerkreduktion verwendet werden kann. In experimenten vergleichen wir LS-Pruning mit anderen schnellen Reduktionsmethoden, wie zum Beispiel dem magnitudenbasierten Pruning und der LS-Faktorisierung. Darüber hinaus vergleichen wir LS-Pruning mit überwachten Pruningverfahren.Item Open Access Behavior-aware pedestrian trajectory prediction in ego-centric camera views with spatio-temporal ego-motion estimation(2023) Czech, Phillip; Braun, Markus; Kreßel, Ulrich; Yang, BinWith the ongoing development of automated driving systems, the crucial task of predicting pedestrian behavior is attracting growing attention. The prediction of future pedestrian trajectories from the ego-vehicle camera perspective is particularly challenging due to the dynamically changing scene. Therefore, we present Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), a novel approach to pedestrian trajectory prediction for ego-centric camera views. It incorporates behavioral features extracted from real-world traffic scene observations such as the body and head orientation of pedestrians, as well as their pose, in addition to positional information from body and head bounding boxes. For each input modality, we employed independent encoding streams that are combined through a modality attention mechanism. To account for the ego-motion of the camera in an ego-centric view, we introduced Spatio-Temporal Ego-Motion Module (STEMM), a novel approach to ego-motion prediction. Compared to the related works, it utilizes spatial goal points of the ego-vehicle that are sampled from its intended route. We experimentally validated the effectiveness of our approach using two datasets for pedestrian behavior prediction in urban traffic scenes. Based on ablation studies, we show the advantages of incorporating different behavioral features for pedestrian trajectory prediction in the image plane. Moreover, we demonstrate the benefit of integrating STEMM into our pedestrian trajectory prediction method, BA-PTP. BA-PTP achieves state-of-the-art performance on the PIE dataset, outperforming prior work by 7% in MSE-1.5 s and CMSE as well as 9% in CFMSE.Item Open Access Image preprocessing for outdoor luminescence inspection of large photovoltaic parks(2021) Kölblin, Pascal; Bartler, Alexander; Füller, MarvinElectroluminescence (EL) measurements allow one to detect damages and/or defective parts in photovoltaic systems. In principle, it seems possible to predict the complete current/voltage curve from such pictures even automatically. However, such a precise analysis requires image corrections and calibrations, because vignetting and lens distortion cause signal and spatial distortions. Earlier works on crystalline silicon modules used the cell gap joints (CGJ) as calibration pattern. Unfortunately, this procedure fails if the detection of the gaps is not accurate or if the contrast in the images is low. Here, we enhance the automated camera calibration algorithm with a reliable pattern detection and analyze quantitatively the quality of the process. Our method uses an iterative Hough transform to detect line structures and uses three key figures (KF) to separate detected busbars from cell gaps. This method allows a reliable identification of all cell gaps, even in noisy images or if disconnected edges in PV cells exist or potential induced degradation leads to a low contrast between active cell area and background. In our dataset, a subset of 30 EL images (72 cell each) forming grid (5×11) lead to consistent calibration results. We apply the calibration process to 997 single module EL images of PV modules and evaluate our results with a random subset of 40 images. After lens distortion correction and perspective correction, we analyze the residual deviation between ideal target grid points and the previously detected CGJ after applied distortion and perspective correction. For all of the 2200 control points in the 40 evaluation images, we achieve a deviation of less than or equal to 3 pixels. For 50% of the control points, a deviation of of less than or equal to 1 pixel is reached.Item Open Access Avoiding shortcut-learning by mutual information minimization in deep learning-based image processing(2023) Fay, Louisa; Cobos, Erick; Yang, Bin; Gatidis, Sergios; Küstner, ThomasItem Open Access Machine learning for end-use electrical energy monitoring(2021) Barsim, Karim Said; Yang, Bin (Prof. Dr.-Ing.)Promoting end-users awareness of their usage and consumption of energy is one of the main measures towards achieving energy efficiency in buildings, which is one of the main targets in climate-aware energy transition programs. End-use energy disaggregation and monitoring is a practical and efficient approach towards achieving the targeted awareness of energy users by providing them with real-time fine-grained feedback about their own usage of energy. In this work, we address the case of electrical energy and the problem of end-use load monitoring and disaggregation in a variety of machine learning paradigms. This work starts from unsupervised energy disaggregation based on simple constraints and assumptions without the need for labeled training data. We then study and propose semi-supervised disaggregation approaches that learn from labeled observations, but are also capable of compensating for the scarcity of labeled data by leveraging unlabeled measurements. Finally, we propose a generic neural architecture for data-driven disaggregation upon availability of an abundance of training data. Results from this work not only assert the feasibility of end-use energy disaggregation, but also propose efficient models that adapt to the availability of labeled data, and are capable of monitoring different categories of end-use loads.Item Open Access Algorithms for event-based non-intrusive load monitoring(2024) Liebgott, Florian; Yang, Bin (Prof. Dr.-Ing.)Item Open Access Automated imaging-based abdominal organ segmentation and quality control in 20,000 participants of the UK Biobank and German National Cohort Studies(2022) Kart, Turkay; Fischer, Marc; Winzeck, Stefan; Glocker, Ben; Bai, Wenjia; Bülow, Robin; Emmel, Carina; Friedrich, Lena; Kauczor, Hans-Ulrich; Keil, Thomas; Kröncke, Thomas; Mayer, Philipp; Niendorf, Thoralf; Peters, Annette; Pischon, Tobias; Schaarschmidt, Benedikt M.; Schmidt, Börge; Schulze, Matthias B.; Umutle, Lale; Völzke, Henry; Küstner, Thomas; Bamberg, Fabian; Schölkopf, Bernhard; Rückert, Daniel; Gatidis, SergiosLarge epidemiological studies such as the UK Biobank (UKBB) or German National Cohort (NAKO) provide unprecedented health-related data of the general population aiming to better understand determinants of health and disease. As part of these studies, Magnetic Resonance Imaging (MRI) is performed in a subset of participants allowing for phenotypical and functional characterization of different organ systems. Due to the large amount of imaging data, automated image analysis is required, which can be performed using deep learning methods, e. g. for automated organ segmentation. In this paper we describe a computational pipeline for automated segmentation of abdominal organs on MRI data from 20,000 participants of UKBB and NAKO and provide results of the quality control process. We found that approx. 90% of data sets showed no relevant segmentation errors while relevant errors occurred in a varying proportion of data sets depending on the organ of interest. Image-derived features based on automated organ segmentations showed relevant deviations of varying degree in the presence of segmentation errors. These results show that large-scale, deep learning-based abdominal organ segmentation on MRI data is feasible with overall high accuracy, but visual quality control remains an important step ensuring the validity of down-stream analyses in large epidemiological imaging studies.Item Open Access Not all features are equal: feature selection based on deep learning(2025) Liao, Yiwen; Yang, Bin (Prof. Dr.-Ing)