TY - THES A1 - Fröhling, Felix Korbinian T1 - Evaluation of CNN-based object detection algorithms of thermal and color image sensors under adverse environment conditions N2 - Functional safety is becoming increasingly important in current ADAS systems, especially with technology facing an evolution as responsibility is gradually transferred from the driver to the car. The systems must perceive their environment correctly in any situation but sensors have their limitations. Thus, different sensor types must be combined to compensate the weakness of each sensor. The aim of this work is to find out whether thermal cameras have an added value for object detection in adverse environmental conditions such as rain, fog and different light conditions compared to conventional color cameras. To answer this question, three state-of-the-art algorithms for object detection on images based on neural networks are analyzed and compared. Current state-of-the-art algorithms are based on neural networks and need a large amount of labeled data. This data is generated using IPG CarMaker, a simulation tool, to simulate labeled color and thermal images. Besides synthetic data, also real sensor data is recorded in the CARISSMA test facility, where real adverse environmental conditions can be reproduced. This dataset is used for evaluation, i.e. by comparing the ground-truth data with the neural network predictions from the color and thermal images. With the evaluationdata statements can be done in which situations the algorithm is able to detect the object based on the color and thermal images and thereby what performance the algorithm achieves. Y1 - 2021 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-11609 CY - Ingolstadt ER - TY - JOUR A1 - Denk, Florian A1 - Fröhling, Felix A1 - Brunner, Pascal A1 - Huber, Werner A1 - Margreiter, Martin A1 - Bogenberger, Klaus A1 - Kates, Ronald T1 - Influence of gaze strategies and cognitive load on safeguarding performance of motorists in right-turning scenarios involving potential conflicts with vulnerable road users JF - Transportation Research Part F: Traffic Psychology and Behaviour N2 - In urban traffic, while the fraction of collisions involving Vulnerable Road Users (VRU) is low, their importance is high due to the higher injury risk for VRU. Their infrequent occurrence on average (compared with far more common individual perceptual and behavioral errors by both drivers and VRUs) reflects an underlying fault tolerance in traffic processes. However, the degree of fault tolerance varies among traffic situations. The underlying perceptual and cognitive processes involved are complex and can require a high level of attention and concentration, particularly in situations with intersecting trajectories. These processes can occasionally fail, leading to collision risk. The situation of right-turning motorists (in right-hand-drive countries) encountering cyclists moving straight on a bike lane (with right of way) has a particularly low error tolerance, since motorists must actively scan for cyclists approaching from behind. In order to develop, test and assess solutions that mitigate collision risk in this situation, the behavior-related causation mechanisms need investigation. This is the focus of this article. We conducted a trial on our closed test track with n = 35 subjects. The experiment was designed as a within-subject design with three independent factors: maneuver, target velocity, and cognitive load in an n-back task. The trial included observations of participants' gaze control. A primary research focus was the quality and efficiency of the safeguarding gaze behavior of participants in order to draw conclusions on the causation mechanisms of collisions in this situation. For this purpose we define metrics in order to quantify the quality and efficiency of a specific gaze behavior. Furthermore, we studied the effect of factors cognitive load and target velocity on safety and secondary (n-back) task performance. Remarkably, only four out of 35 participants reached a collision risk of 0% relating to the defined quality metric. Furthermore, we identified four distinct gaze strategy groups through hierarchical clustering, where one group performed particularly few glances overall. This group showed significant differences with respect to the defined quality metric whereas the other groups showed only slight differences to each other. The results have implications on subsequent crash causation model development. UR - https://doi.org/10.1016/j.trf.2024.11.012 Y1 - 2024 UR - https://doi.org/10.1016/j.trf.2024.11.012 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-63967 SN - 1873-5517 VL - 2025 IS - 109 SP - 32 EP - 49 PB - Elsevier CY - Amsterdam ER - TY - CHAP A1 - Denk, Florian A1 - Fröhling, Felix A1 - Brunner, Pascal A1 - Huber, Werner A1 - Margreiter, Martin A1 - Bogenberger, Klaus A1 - Kates, Ronald T1 - Design of an Experiment to Pinpoint Cognitive Failure Processes in the Interaction of Motorists and Vulnerable Road Users T2 - IEEE IV 2023: Symposium Proceedings UR - https://doi.org/10.1109/IV55152.2023.10186550 KW - Traffic analysis KW - human factors KW - cognitive models KW - experimental design Y1 - 2023 UR - https://doi.org/10.1109/IV55152.2023.10186550 SN - 979-8-3503-4691-6 PB - IEEE CY - Piscataway ER -