@article{PandeyKuehnWeisetal.2025, author = {Pandey, Amit and K{\"u}hn, Stephan and Weis, Alexander and Wunderle, Bernhard and Elger, Gordon}, title = {Evaluating optical performance degradation of automotive cameras under accelerated aging}, volume = {2026}, pages = {109396}, journal = {Optics and Lasers in Engineering}, number = {196}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1873-0302}, doi = {https://doi.org/10.1016/j.optlaseng.2025.109396}, year = {2025}, abstract = {Automotive cameras are subject to environmental stress, which degrades performance by reducing image sharpness. To qualify for automotive use and to ensure that the cameras maintain sharpness according to the hard requirements of end-of-line testing, cameras have to undergo standardized accelerated aging tests. These tests are performed to demonstrate reliability and functional safety over lifetime. Few studies have been published that demonstrate how aging contributes to the degradation of optical performance. This study addresses this gap by combining accelerated thermal aging with sharpness tracking to investigate degradation over time. To quantify sharpness degradation, six series-production cameras were subjected to accelerated thermal aging between -40◦𝐶 and +85◦𝐶. Each camera underwent 2000 aging cycles, equivalent to 80\% of their lifetime based on the Coffin-Manson model of the LV124 standard. Sharpness was measured by calculating the Spatial Frequency Response (SFR) from images captured of a double-cross reticle projected by a virtual object generator with three illumination wavelengths (625nm, 520nm, and 470nm). The change in sharpness was evaluated with SFR50 and SFR at 60 line pairs per millimeter (SFR@60). During the first 250 cycles, a wear-in effect was observed, where sharpness increased before leveling off, as seen previously. The results also indicated a slow decline in sharpness showing long-term stability. Analysis indicated that before aging, the best focal plane was located closer to the focal position of the red wavelength, which lies furthest from the objective. By the end of the aging process, the best focal plane had shifted toward the focal position of the blue wavelength, which is located closer to the objective. This suggests a forward movement of the image sensor due to aging. Even after 2000 cycles, all cameras maintained an SFR@60 above 0.5. A Random Forest regression model was trained to predict the age based on the SFR curves, achieving a mean absolute error of 126 cycles and a 𝑅2 score of 0.96.}, language = {en} } @article{BhanderiAgrawalElger2025, author = {Bhanderi, Savankumar and Agrawal, Shiva and Elger, Gordon}, title = {Deep segmentation of 3+1D radar point cloud for real-time roadside traffic user detection}, volume = {15}, pages = {38489}, journal = {Scientific Reports}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-025-23019-6}, year = {2025}, abstract = {Smart cities rely on intelligent infrastructure to enhance road safety, optimize traffic flow, and enable vehicle-to-infrastructure (V2I) communication. A key component of such infrastructure is an efficient and real-time perception system that accurately detects diverse traffic participants. Among various sensing modalities, automotive radar is one of the best choices due to its robust performance in adverse weather and low-light conditions. However, due to low spatial resolution, traditional clustering-based approaches for radar object detection often struggle with vulnerable road user detection and nearby object separation. Hence, this paper proposes a deep learning-based D radar point cloud clustering methodology tailored for smart infrastructure-based perception applications. This approach first performs semantic segmentation of the radar point cloud, followed by instance segmentation to generate well-formed clusters with class labels using a deep neural network. It also detects single-point objects that conventional methods often miss. The described approach is developed and experimented using a smart infrastructure-based sensor setup and it performs segmentation of the point cloud in real-time. Experimental results demonstrate 95.35\% F1-macro score for semantic segmentation and 91.03\% mean average precision (mAP) at an intersection over union (IoU) threshold of 0.5 for instance segmentation. Further, the complete pipeline operates at 43.61 frames per second with a memory requirement of less than 0.7 MB on the edge device (Nvidia Jetson AGX Orin).}, language = {en} } @unpublished{KettelgerdesHillmannHirmeretal.2023, author = {Kettelgerdes, Marcel and Hillmann, Tjorven and Hirmer, Thomas and Erdogan, H{\"u}seyin and Wunderle, Bernhard and Elger, Gordon}, title = {Accelerated Real-Life (ARL) Testing and Characterization of Automotive LiDAR Sensors to facilitate the Development and Validation of Enhanced Sensor Models}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2312.04229}, year = {2023}, abstract = {In the realm of automated driving simulation and sensor modeling, the need for highly accurate sensor models is paramount for ensuring the reliability and safety of advanced driving assistance systems (ADAS). Hence, numerous works focus on the development of high-fidelity models of ADAS sensors, such as camera, Radar as well as modern LiDAR systems to simulate the sensor behavior in different driving scenarios, even under varying environmental conditions, considering for example adverse weather effects. However, aging effects of sensors, leading to suboptimal system performance, are mostly overlooked by current simulation techniques. This paper introduces a cutting-edge Hardware-in-the-Loop (HiL) test bench designed for the automated, accelerated aging and characterization of Automotive LiDAR sensors. The primary objective of this research is to address the aging effects of LiDAR sensors over the product life cycle, specifically focusing on aspects such as laser beam profile deterioration, output power reduction and intrinsic parameter drift, which are mostly neglected in current sensor models. By that, this proceeding research is intended to path the way, not only towards identifying and modeling respective degradation effects, but also to suggest quantitative model validation metrics.}, language = {en} } @article{AgrawalBhanderiElger2025, author = {Agrawal, Shiva and Bhanderi, Savankumar and Elger, Gordon}, title = {Infra-3DRC-FusionNet: Deep Fusion of Roadside Mounted RGB Mono Camera and Three-Dimensional Automotive Radar for Traffic User Detection}, volume = {25}, pages = {3422}, journal = {Sensors}, number = {11}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {https://doi.org/10.3390/s25113422}, year = {2025}, abstract = {Mono RGB cameras and automotive radar sensors provide a complementary information set that makes them excellent candidates for sensor data fusion to obtain robust traffic user detection. This has been widely used in the vehicle domain and recently introduced in roadside-mounted smart infrastructure-based road user detection. However, the performance of the most commonly used late fusion methods often degrades when the camera fails to detect road users in adverse environmental conditions. The solution is to fuse the data using deep neural networks at the early stage of the fusion pipeline to use the complete data provided by both sensors. Research has been carried out in this area, but is limited to vehicle-based sensor setups. Hence, this work proposes a novel deep neural network to jointly fuse RGB mono-camera images and 3D automotive radar point cloud data to obtain enhanced traffic user detection for the roadside-mounted smart infrastructure setup. Projected radar points are first used to generate anchors in image regions with a high likelihood of road users, including areas not visible to the camera. These anchors guide the prediction of 2D bounding boxes, object categories, and confidence scores. Valid detections are then used to segment radar points by instance, and the results are post-processed to produce final road user detections in the ground plane. The trained model is evaluated for different light and weather conditions using ground truth data from a lidar sensor. It provides a precision of 92\%, recall of 78\%, and F1-score of 85\%. The proposed deep fusion methodology has 33\%, 6\%, and 21\% absolute improvement in precision, recall, and F1-score, respectively, compared to object-level spatial fusion output.}, language = {en} } @unpublished{HanXuKefferpuetzetal.2024, author = {Han, Longfei and Xu, Qiuyu and Kefferp{\"u}tz, Klaus and Elger, Gordon and Beyerer, J{\"u}rgen}, title = {Applying Extended Object Tracking for Self-Localization of Roadside Radar Sensors}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2407.03084}, year = {2024}, abstract = {Intelligent Transportation Systems (ITS) can benefit from roadside 4D mmWave radar sensors for large-scale traffic monitoring due to their weatherproof functionality, long sensing range and low manufacturing cost. However, the localization method using external measurement devices has limitations in urban environments. Furthermore, if the sensor mount exhibits changes due to environmental influences, they cannot be corrected when the measurement is performed only during the installation. In this paper, we propose self-localization of roadside radar data using Extended Object Tracking (EOT). The method analyses both the tracked trajectories of the vehicles observed by the sensor and the aerial laser scan of city streets, assigns labels of driving behaviors such as "straight ahead", "left turn", "right turn" to trajectory sections and road segments, and performs Semantic Iterative Closest Points (SICP) algorithm to register the point cloud. The method exploits the result from a down stream task -- object tracking -- for localization. We demonstrate high accuracy in the sub-meter range along with very low orientation error. The method also shows good data efficiency. The evaluation is done in both simulation and real-world tests.}, language = {en} } @inproceedings{KettelgerdesPandeyUnruhetal.2024, author = {Kettelgerdes, Marcel and Pandey, Amit and Unruh, Denis and Erdogan, H{\"u}seyin and Wunderle, Bernhard and Elger, Gordon}, title = {Automotive LiDAR Based Precipitation State Estimation Using Physics Informed Spatio-Temporal 3D Convolutional Neural Networks (PIST-CNN)}, booktitle = {2023 29th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-2562-1}, doi = {https://doi.org/10.1109/M2VIP58386.2023.10413394}, year = {2024}, language = {en} } @inproceedings{OlcayMeessElger2024, author = {Olcay, Ertug and Meeß, Henri and Elger, Gordon}, title = {Dynamic Obstacle Avoidance for UAVs using MPC and GP-Based Motion Forecast}, booktitle = {2024 European Control Conference (ECC)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-3-9071-4410-7}, doi = {https://doi.org/10.23919/ECC64448.2024.10591083}, pages = {1024 -- 1031}, year = {2024}, language = {en} } @inproceedings{HanXuKefferpuetzetal.2024, author = {Han, Longfei and Xu, Qiuyu and Kefferp{\"u}tz, Klaus and Lu, Ying and Elger, Gordon and Beyerer, J{\"u}rgen}, title = {Scalable Radar-based Roadside Perception: Self-localization and Occupancy Heat Map for Traffic Analysis}, booktitle = {2024 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-4881-1}, doi = {https://doi.org/10.1109/iv55156.2024.10588397}, pages = {1651 -- 1657}, year = {2024}, language = {en} } @article{KettelgerdesSarmientoErdoganetal.2024, author = {Kettelgerdes, Marcel and Sarmiento, Nicolas and Erdogan, H{\"u}seyin and Wunderle, Bernhard and Elger, Gordon}, title = {Precise Adverse Weather Characterization by Deep-Learning-Based Noise Processing in Automotive LiDAR Sensors}, volume = {16}, pages = {2407}, journal = {Remote Sensing}, number = {13}, publisher = {MDPI}, address = {Basel}, issn = {2072-4292}, doi = {https://doi.org/10.3390/rs16132407}, year = {2024}, abstract = {With current advances in automated driving, optical sensors like cameras and LiDARs are playing an increasingly important role in modern driver assistance systems. However, these sensors face challenges from adverse weather effects like fog and precipitation, which significantly degrade the sensor performance due to scattering effects in its optical path. Consequently, major efforts are being made to understand, model, and mitigate these effects. In this work, the reverse research question is investigated, demonstrating that these measurement effects can be exploited to predict occurring weather conditions by using state-of-the-art deep learning mechanisms. In order to do so, a variety of models have been developed and trained on a recorded multiseason dataset and benchmarked with respect to performance, model size, and required computational resources, showing that especially modern vision transformers achieve remarkable results in distinguishing up to 15 precipitation classes with an accuracy of 84.41\% and predicting the corresponding precipitation rate with a mean absolute error of less than 0.47 mm/h, solely based on measurement noise. Therefore, this research may contribute to a cost-effective solution for characterizing precipitation with a commercial Flash LiDAR sensor, which can be implemented as a lightweight vehicle software feature to issue advanced driver warnings, adapt driving dynamics, or serve as a data quality measure for adaptive data preprocessing and fusion.}, language = {en} } @article{MeessGernerHeinetal.2024, author = {Meess, Henri and Gerner, Jeremias and Hein, Daniel and Schmidtner, Stefanie and Elger, Gordon and Bogenberger, Klaus}, title = {First steps towards real-world traffic signal control optimisation by reinforcement learning}, volume = {18}, journal = {Journal of Simulation}, number = {6}, publisher = {Taylor \& Francis}, address = {London}, issn = {1747-7778}, doi = {https://doi.org/10.1080/17477778.2024.2364715}, pages = {957 -- 972}, year = {2024}, abstract = {Enhancing traffic signal optimisation has the potential to improve urban traffic flow without the need for expensive infrastructure modifications. While reinforcement learning (RL) techniques have demonstrated their effectiveness in simulations, their real-world implementation is still a challenge. Real-world systems need to be developed that guarantee a deployable action definition for real traffic systems while prioritising safety constraints and robust policies. This paper introduces a method to overcome this challenge by introducing a novel action definition that optimises parameter-level control programmes designed by traffic engineers. The complete proposed framework consists of a traffic situation estimation, a feature extractor, and a system that enables training on estimates of real-world traffic situations. Further multimodal optimisation, scalability, and continuous training after deployment could be achieved. The first simulative tests using this action definition show an average improvement of more than 20\% in traffic flow compared to the baseline - the corresponding pre-optimised real-world control.}, language = {en} } @inproceedings{HanKefferpuetzElgeretal.2024, author = {Han, Longfei and Kefferp{\"u}tz, Klaus and Elger, Gordon and Beyerer, J{\"u}rgen}, title = {FlexSense: Flexible Infrastructure Sensors for Traffic Perception}, booktitle = {2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-9946-2}, doi = {https://doi.org/10.1109/ITSC57777.2023.10422616}, pages = {3810 -- 3816}, year = {2024}, language = {en} } @article{AgrawalBhanderiElger2024, author = {Agrawal, Shiva and Bhanderi, Savankumar and Elger, Gordon}, title = {Semi-Automatic Annotation of 3D Radar and Camera for Smart Infrastructure-Based Perception}, volume = {12}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2024.3373310}, pages = {34325 -- 34341}, year = {2024}, abstract = {Environment perception using camera, radar, and/or lidar sensors has significantly improved in the last few years because of deep learning-based methods. However, a large group of these methods fall into the category of supervised learning, which requires a considerable amount of annotated data. Due to uncertainties in multi-sensor data, automating the data labeling process is extremely challenging; hence, it is performed manually to a large extent. Even though full automation of such a process is difficult, semiautomation can be a significant step to ease this process. However, the available work in this regard is still very limited; hence, in this paper, a novel semi-automatic annotation methodology is developed for labeling RGB camera images and 3D automotive radar point cloud data using a smart infrastructure-based sensor setup. This paper also describes a new method for 3D radar background subtraction to remove clutter and a new object category, GROUP, for radar-based object detection for closely located vulnerable road users. To validate the work, a dataset named INFRA-3DRC is created using this methodology, where 75\% of the labels are automatically generated. In addition, a radar cluster classifier and an image classifier are developed, trained, and tested on this dataset, achieving accuracy of 98.26\% and 94.86\%, respectively. The dataset and Python scripts are available at https://fraunhoferivi.github.io/INFRA-3DRC-Dataset/.}, language = {en} } @inproceedings{AgrawalBhanderiAmanagietal.2023, author = {Agrawal, Shiva and Bhanderi, Savankumar and Amanagi, Sumit and Doycheva, Kristina and Elger, Gordon}, title = {Instance Segmentation and Detection of Children to Safeguard Vulnerable Traffic User by Infrastructure}, booktitle = {Proceedings of the 9th International Conference on Vehicle Technology and Intelligent Transport Systems}, editor = {Vinel, Alexey and Ploeg, Jeroen and Berns, Karsten and Gusikhin, Oleg}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-652-1}, issn = {2184-495X}, doi = {https://doi.org/10.5220/0011825400003479}, pages = {206 -- 214}, year = {2023}, abstract = {Cameras mounted on intelligent roadside infrastructure units and vehicles can detect humans on the road using state-of-the-art perception algorithms, but these algorithms are presently not trained to distinguish between human and adult. However, this is a crucial requirement from a safety perspective because a child may not follow all the traffic rules, particularly while crossing the road. Moreover, a child may stop or may start playing on the road. In such situations, the separation of a child from an adult is necessary. The work in this paper targets to solve this problem by applying a transfer-learning-based neural network approach to classify child and adult separately in camera images. The described work is comprised of image data collection, data annotation, transfer learning-based model development, and evaluation. For the work, Mask-RCNN (region-based convolutional neural network) with different backbone architectures and two different baselines are investigated and the perception precision of the architectures after transfer-learning is compared. The results reveal that the best performing trained model is able to detect and classify children and adults separately in different road scenarios with segmentation mask AP (average precision) of 85\% and bounding box AP of 92\%.}, language = {en} } @inproceedings{AgrawalSongDoychevaetal.2023, author = {Agrawal, Shiva and Song, Rui and Doycheva, Kristina and Knoll, Alois and Elger, Gordon}, title = {Intelligent Roadside Infrastructure for Connected Mobility}, booktitle = {Smart Cities, Green Technologies, and Intelligent Transport Systems: 11th International Conference, SMARTGREENS 2022 and 8th International Conference, VEHITS 2022: Revised Selected Papers}, editor = {Klein, Cornel and Jarke, Matthias and Ploeg, Jeroen and Helfert, Markus and Berns, Karsten and Gusikhin, Oleg}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-37470-8}, issn = {1865-0937}, doi = {https://doi.org/10.1007/978-3-031-37470-8_6}, pages = {134 -- 157}, year = {2023}, language = {en} } @inproceedings{SchmidMombergKettelgerdesetal.2023, author = {Schmid, Maximilian and Momberg, Marcel and Kettelgerdes, Marcel and Elger, Gordon}, title = {Transient thermal analysis for VCSEL Diodes}, booktitle = {2023 29th International Workshop on Thermal Investigations of ICs and Systems (THERMINIC)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-1862-3}, doi = {https://doi.org/10.1109/THERMINIC60375.2023.10325906}, year = {2023}, language = {en} } @article{SchmidZippeliusHanssetal.2023, author = {Schmid, Maximilian and Zippelius, Andreas and Hanß, Alexander and B{\"o}ckhorst, Stephan and Elger, Gordon}, title = {Investigations on High-Power LEDs and Solder Interconnects in Automotive Application: Part II - Reliability}, volume = {23}, journal = {IEEE Transactions on Device and Materials Reliability}, number = {3}, publisher = {IEEE}, address = {New York}, issn = {1558-2574}, doi = {https://doi.org/10.1109/TDMR.2023.3300355}, pages = {419 -- 429}, year = {2023}, language = {en} } @inproceedings{KettelgerdesMezmerHaeussleretal.2023, author = {Kettelgerdes, Marcel and Mezmer, Peter and Haeussler, Michael J. and B{\"o}ttger, Gunnar and Tavakolibasti, Majid and Pandey, Amit and Erdogan, H{\"u}seyin and Elger, Gordon and Schacht, Ralph and Wunderle, Bernhard}, title = {Realization, multi-field coupled simulation and characterization of a thermo-mechanically robust LiDAR front end on a copper coated glass substrate}, booktitle = {Proceedings: IEEE 73rd Electronic Components and Technology Conference, ECTC 2023}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-3498-2}, issn = {2377-5726}, doi = {https://doi.org/10.1109/ECTC51909.2023.00131}, pages = {753 -- 760}, year = {2023}, language = {en} } @article{AgrawalBhanderiDoychevaetal.2023, author = {Agrawal, Shiva and Bhanderi, Savankumar and Doycheva, Kristina and Elger, Gordon}, title = {Static multi-target-based auto-calibration of RGB cameras, 3D Radar, and 3D Lidar sensors}, volume = {23}, journal = {IEEE Sensors Journal}, number = {18}, publisher = {IEEE}, address = {Piscataway}, issn = {1530-437X}, doi = {https://doi.org/10.1109/JSEN.2023.3300957}, pages = {21493 -- 21505}, year = {2023}, language = {en} } @article{KettelgerdesElger2023, author = {Kettelgerdes, Marcel and Elger, Gordon}, title = {In-Field Measurement and Methodology for Modeling and Validation of Precipitation Effects on Solid-State LiDAR Sensors}, volume = {7}, journal = {IEEE Journal of Radio Frequency Identification}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, address = {New York}, issn = {2469-7281}, doi = {https://doi.org/10.1109/JRFID.2023.3234999}, pages = {192 -- 202}, year = {2023}, language = {en} } @inproceedings{KettelgerdesElger2022, author = {Kettelgerdes, Marcel and Elger, Gordon}, title = {Modeling Methodology and In-field Measurement Setup to Develop Empiric Weather Models for Solid-State LiDAR Sensors}, booktitle = {2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-9227-0}, doi = {https://doi.org/10.1109/DTPI55838.2022.9998918}, year = {2022}, language = {en} }