TY - INPR A1 - Wolf, Dominik Werner A1 - Braun, Alexander A1 - Ulrich, Markus T1 - Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration T2 - International Journal of Computer Vision (IJCV) N2 - 'A trustworthy representation of uncertainty is desirable and should be considered as a key feature of any machine learning method' (Huellermeier and Waegeman, 2021). This conclusion of Huellermeier et al. underpins the importance of calibrated uncertainties. Since AI-based algorithms are heavily impacted by dataset shifts, the automotive industry needs to safeguard its system against all possible contingencies. One important but often neglected dataset shift is caused by optical aberrations induced by the windshield. For the verification of the perception system performance, requirements on the AI performance need to be translated into optical metrics by a bijective mapping (Braun, 2023). Given this bijective mapping it is evident that the optical system characteristics add additional information about the magnitude of the dataset shift. As a consequence, we propose to incorporate a physical inductive bias into the neural network calibration architecture to enhance the robustness and the trustworthiness of the AI target application, which we demonstrate by using a semantic segmentation task as an example. By utilizing the Zernike coefficient vector of the optical system as a physical prior we can significantly reduce the mean expected calibration error in case of optical aberrations. As a result, we pave the way for a trustworthy uncertainty representation and for a holistic verification strategy of the perception chain. Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-50120 PB - arXiv ER - TY - INPR A1 - Wolf, Dominik Werner A1 - Balaji, Prasannavenkatesh A1 - Braun, Alexander A1 - Ulrich, Markus T1 - Decoupling of neural network calibration measures T2 - German Conference on Pattern Recognition (GCPR) 2024 N2 - A lot of effort is currently invested in safeguarding autonomous driving systems, which heavily rely on deep neural networks for computer vision. We investigate the coupling of different neural network calibration measures with a special focus on the Area Under the Sparsification Error curve (AUSE) metric. We elaborate on the well-known inconsistency in determining optimal calibration using the Expected Calibration Error (ECE) and we demonstrate similar issues for the AUSE, the Uncertainty Calibration Score (UCS), as well as the Uncertainty Calibration Error (UCE). We conclude that the current methodologies leave a degree of freedom, which prevents a unique model calibration for the homologation of safety-critical functionalities. Furthermore, we propose the AUSE as an indirect measure for the residual uncertainty, which is irreducible for a fixed network architecture and is driven by the stochasticity in the underlying data generation process (aleatoric contribution) as well as the limitation in the hypothesis space (epistemic contribution). Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-50104 PB - arXiv ER - TY - JOUR A1 - Jakab, Daniel A1 - Braun, Alexander A1 - Agnew, Cathaoir A1 - Mohandas, Reenu A1 - Deegan, Brian Michael A1 - Molloy, Dara A1 - Ward, Enda A1 - Scanlan, Anthony A1 - Eising, Ciarán T1 - SS-SFR: synthetic scenes spatial frequency response on Virtual KITTI and degraded automotive simulations for object detection JF - IET Conference Proceedings Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-50080 SN - 2732-4494 VL - 2024 IS - 10 SP - 110 EP - 117 PB - Institution of Engineering and Technology (IET) ER - TY - JOUR A1 - Wolf, Dominik Werner A1 - Thielbeer, Boris A1 - Ulrich, Markus A1 - Braun, Alexander T1 - Wavefront aberration measurements based on the Background Oriented Schlieren method JF - Measurement: Sensors N2 - Applications based on neural networks tend to be very sensitive to dataset shifts. Hence, the perception chain for autonomous driving is safeguarded against perturbations by imposing exaggerated optical quality requirements. Due to the non-linear coupling of optical elements, system requirements of camera-based Advanced Driver Assistance Systems (ADAS) can not be easily decomposed into individual part tolerances of the objective lens and the windscreen. This holds true for intensity-based part measurements, e.g. slanted edge measurements according to ISO12233, which can fundamentally not capture interference effects of the complex light field. Instead wavefront-based part measurements are required. Unfortunately, state-of-the-art wavefront measurement techniques are limited by the spanned sensitive area of the Shack-Hartmann lenslet array or the aperture stop of a corresponding interferometrical setup, respectively. Further, both measurements are limited by using collimated light only, whereas the target application has a large (angular) field of view, requiring many different measurements. We address those bottlenecks by proposing a novel wavefront aberration measurement procedure based on the Background Oriented Schlieren (BOS) method utilizing image auto-correlation. We analytically derive the governing equations for determining the Zernike coefficients of a wavefront aberration map in the knowledge of the local refractive power map obtained by a high-resolution BOS measurement. Furthermore, we experimentally demonstrate the feasibility of the measurement technique. Applying this novel method yields the promise of affordable wavefront aberration measurements only requiring a high-resolution camera and a sophisticated alignment strategy. KW - Wavefront aberration measurements KW - Deep optics KW - Dataset shifts KW - Data augmentation KW - Autonomous driving Y1 - 2024 U6 - https://doi.org/10.1016/j.measen.2024.101509 SN - 2665-9174 N1 - In Press, Corrected Proof PB - Elsevier ER - TY - JOUR A1 - Molloy, Dara A1 - Müller, Patrick A1 - Deegan, Brian A1 - Mullins, Darragh A1 - Horgan, Jonathan A1 - Ward, Enda A1 - Jones, Edward A1 - Braun, Alexander A1 - Glavin, Martin T1 - Analysis of the Impact of Lens Blur on Safety-Critical Automotive Object Detection JF - IEEE Access N2 - Camera-based object detection is widely used in safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous vehicle research. Road infrastructure has been designed for human vision, so computer vision, with RGB cameras, is a vital source of semantic information from the environment. Sensors, such as LIDAR and RADAR, are also often utilized for these applications; however, cameras provide a higher spatial resolution and color information. The spatial frequency response (SFR), or sharpness of a camera, utilized in object detection systems must be sufficient to allow a detection algorithm to localize objects in the environment over its lifetime reliably. This study explores the relationship between object detection performance and SFR. Six state-of-the-art object detection models are evaluated with varying levels of lens defocus. A novel raw image dataset is created and utilized, containing pedestrians and cars over a range of distances up to 100-m from the sensor. Object detection performance for each defocused dataset is analyzed over a range of distances to determine the minimum SFR necessary in each case. Results show that the relationship between object detection performance and lens blur is much more complex than previous studies have found due to lens field curvature, chromatic aberration, and astigmatisms. We have found that smaller objects are disproportionately impacted by lens blur, and different object detection models have differing levels of robustness to lens blur KW - DOAJ KW - Object detection KW - intelligent transportation system KW - autonomous vehicles KW - ADAS KW - lens blur Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-42999 SN - 2169-3536 VL - 12 SP - 3554 EP - 3569 PB - IEEE ER - TY - JOUR A1 - Geerkens, Simon A1 - Sieberichs, Christian A1 - Braun, Alexander A1 - Waschulzik, Thomas T1 - QI²: an interactive tool for data quality assurance JF - AI and Ethics N2 - The importance of high data quality is increasing with the growing impact and distribution of ML systems and big data. Also, the planned AI Act from the European commission defines challenging legal requirements for data quality especially for the market introduction of safety relevant ML systems. In this paper, we introduce a novel approach that supports the data quality assurance process of multiple data quality aspects. This approach enables the verification of quantitative data quality requirements. The concept and benefits are introduced and explained on small example data sets. How the method is applied is demonstrated on the well-known MNIST data set based an handwritten digits. KW - Performance metrics KW - HSD Publikationsfonds KW - DEAL KW - DFG Publikationskosten KW - Machine learning KW - Quality assurance KW - Data integrity KW - Data quality Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-42945 SN - 2730-5961 N1 - Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 532148125 and supported by the central publication fund of Hochschule Düsseldorf University of Applied Sciences VL - 4 SP - 141 EP - 149 PB - Springer Nature ER - TY - JOUR A1 - Sieberichs, Christian A1 - Geerkens, Simon A1 - Braun, Alexander A1 - Waschulzik, Thomas T1 - ECS: an interactive tool for data quality assurance JF - AI and Ethics N2 - With the increasing capabilities of machine learning systems and their potential use in safety-critical systems, ensuring high-quality data is becoming increasingly important. In this paper, we present a novel approach for the assurance of data quality. For this purpose, the mathematical basics are first discussed and the approach is presented using multiple examples. This results in the detection of data points with potentially harmful properties for the use in safety-critical systems. KW - DEAL KW - HSD Publikationsfonds KW - Data visulization KW - Distance based KW - Data quality assurance KW - Equivalence class sets KW - DFG Publikationskosten Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-42908 SN - 2730-5961 N1 - Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 532148125 and supported by the central publication fund of Hochschule Düsseldorf University of Applied Sciences VL - 4 SP - 131 EP - 139 PB - Springer Nature ER -