Refine
Language
- English (4)
Is part of the Bibliography
- yes (4)
Keywords
- Autonomous driving (1)
- Data augmentation (1)
- Dataset shifts (1)
- Deep optics (1)
- Wavefront aberration measurements (1)
Department/institution
Refractive power measurements serve as the primary quality standard in the automotive glazing industry. In the light of autonomous driving new optical metrics are becoming more and more popular for specifying optical quality requirements for the windshield. Nevertheless, the link between those quantities and the refractive power needs to be established in order to ensure a holistic requirement profile for the windshield. As a consequence, traceable high-resolution refractive power measurements are still required for the glass quality assessment. Standard measurement systems using Moiré patterns for refractive power monitoring in the automotive industry are highly resolution limited, wherefore they are insufficient for evaluating the camera window area. Consequently, there is a need for more sophisticated refractive power measurement systems that provide a higher spatial resolution. In addition, a calibration procedure has to be developed in order to guarantee for comparability of the measurement results. For increasing the resolution, a measurement setup based on an auto-correlation algorithm is tested in this paper. Furthermore, a calibration procedure is established by using a single reference lens with a nominal refractive power of 100 km-1. For the calibration of the entire measurement range of the system, the lens is tilted by an inclination angle orthogonal to the optical axis. The effective refractive power is then given by the Kerkhof model. By adopting the measurement and calibration procedure presented in this paper, glass suppliers in the automotive industry will be able to detect relevant manufacturing defects within the camera window area more accurately paving the way for a holistic quality assurance of the windshield for future advanced driver-assistance system (ADAS) functionalities. Concurrently, the traceability of the measurement results is ensured by establishing a calibration chain based on a single reference lens, which is traced back to international standards.
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.
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).
'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.