@unpublished{SongLiuChenetal.2022, author = {Song, Rui and Liu, Dai and Chen, Dave Zhenyu and Festag, Andreas and Trinitis, Carsten and Schulz, Martin and Knoll, Alois}, title = {Federated Learning via Decentralized Dataset Distillation in Resource Constrained Edge Environments}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2208.11311}, year = {2022}, abstract = {In federated learning, all networked clients contribute to the model training cooperatively. However, with model sizes increasing, even sharing the trained partial models often leads to severe communication bottlenecks in underlying networks, especially when communicated iteratively. In this paper, we introduce a federated learning framework FedD3 requiring only one-shot communication by integrating dataset distillation instances. Instead of sharing model updates in other federated learning approaches, FedD3 allows the connected clients to distill the local datasets independently, and then aggregates those decentralized distilled datasets (e.g. a few unrecognizable images) from networks for model training. Our experimental results show that FedD3 significantly outperforms other federated learning frameworks in terms of needed communication volumes, while it provides the additional benefit to be able to balance the trade-off between accuracy and communication cost, depending on usage scenario or target dataset. For instance, for training an AlexNet model on CIFAR-10 with 10 clients under non-independent and identically distributed (Non-IID) setting, FedD3 can either increase the accuracy by over 71\% with a similar communication volume, or save 98\% of communication volume, while reaching the same accuracy, compared to other one-shot federated learning approaches.}, language = {en} } @unpublished{SongLiangXiaetal.2025, author = {Song, Rui and Liang, Chenwei and Xia, Yan and Zimmer, Walter and Cao, Hu and Caesar, Holger and Festag, Andreas and Knoll, Alois}, title = {CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2503.06744}, year = {2025}, abstract = {Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic environments presents significant challenges in accurately rendering these scenes. In this paper, we introduce a novel 4D Gaussian Splatting (4DGS) approach, which incorporates context and temporal deformation awareness to improve dynamic scene rendering. Specifically, we employ a 2D semantic segmentation foundation model to self-supervise the 4D semantic features of Gaussians, ensuring meaningful contextual embedding. Simultaneously, we track the temporal deformation of each Gaussian across adjacent frames. By aggregating and encoding both semantic and temporal deformation features, each Gaussian is equipped with cues for potential deformation compensation within 3D space, facilitating a more precise representation of dynamic scenes. Experimental results show that our method improves 4DGS's ability to capture fine details in dynamic scene rendering for autonomous driving and outperforms other self-supervised methods in 4D reconstruction and novel view synthesis. Furthermore, CoDa-4DGS deforms semantic features with each Gaussian, enabling broader applications.}, 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} } @unpublished{HanKefferpuetzBeyerer2025, author = {Han, Longfei and Kefferp{\"u}tz, Klaus and Beyerer, J{\"u}rgen}, title = {3D Extended Object Tracking based on Extruded B-Spline Side View Profiles}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2503.10730}, year = {2025}, abstract = {Object tracking is an essential task for autonomous systems. With the advancement of 3D sensors, these systems can better perceive their surroundings using effective 3D Extended Object Tracking (EOT) methods. Based on the observation that common road users are symmetrical on the right and left sides in the traveling direction, we focus on the side view profile of the object. In order to leverage of the development in 2D EOT and balance the number of parameters of a shape model in the tracking algorithms, we propose a method for 3D extended object tracking (EOT) by describing the side view profile of the object with B-spline curves and forming an extrusion to obtain a 3D extent. The use of B-spline curves exploits their flexible representation power by allowing the control points to move freely. The algorithm is developed into an Extended Kalman Filter (EKF). For a through evaluation of this method, we use simulated traffic scenario of different vehicle models and realworld open dataset containing both radar and lidar data.}, language = {en} } @inproceedings{SongFestagJagtapetal.2024, author = {Song, Rui and Festag, Andreas and Jagtap, Abhishek Dinkar and Bialdyga, Maximilian and Yan, Zhiran and Otte, Maximilian and Sadashivaiah, Sanath Tiptur and Knoll, Alois}, title = {First Mile: An Open Innovation Lab for Infrastructure-Assisted Cooperative Intelligent Transportation Systems}, booktitle = {2024 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-4881-1}, doi = {https://doi.org/10.1109/IV55156.2024.10588500}, pages = {1635 -- 1642}, year = {2024}, language = {en} } @inproceedings{HegdeLoboFestag2022, author = {Hegde, Anupama and Lobo, Silas and Festag, Andreas}, title = {Cellular-V2X for Vulnerable Road User Protection in Cooperative ITS}, booktitle = {2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-6975-3}, doi = {https://doi.org/10.1109/WiMob55322.2022.9941707}, pages = {118 -- 123}, year = {2022}, language = {en} } @inproceedings{SongLiuChenetal.2023, author = {Song, Rui and Liu, Dai and Chen, Dave Zhenyu and Festag, Andreas and Trinitis, Carsten and Schulz, Martin and Knoll, Alois}, title = {Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments}, booktitle = {IJCNN 2023 Conference Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-8867-9}, doi = {https://doi.org/10.1109/IJCNN54540.2023.10191879}, year = {2023}, language = {en} } @inproceedings{MeessGernerHeinetal.2022, author = {Meess, Henri and Gerner, Jeremias and Hein, Daniel and Schmidtner, Stefanie and Elger, Gordon}, title = {Reinforcement Learning for Traffic Signal Control Optimization: A Concept for Real-World Implementation}, booktitle = {AAMAS '22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, address = {Richland}, isbn = {978-1-4503-9213-6}, doi = {https://dl.acm.org/doi/10.5555/3535850.3536081}, pages = {1699 -- 1701}, year = {2022}, language = {en} } @inproceedings{FritzscheFestag2018, author = {Fritzsche, Richard and Festag, Andreas}, title = {Reliability Maximization with Location-Based Scheduling for Cellular-V2X Communications in Highway Scenarios}, booktitle = {2018 16th International Conference on Intelligent Transportation Systems Telecommunications (ITST) Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-5386-5544-3}, doi = {https://doi.org/10.1109/ITST.2018.8566935}, year = {2018}, 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{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} } @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} } @article{DaRosaZanattaCarvalhoLustosadaCostaAntreichetal.2020, author = {Da Rosa Zanatta, Mateus and Carvalho Lustosa da Costa, Joao Paulo and Antreich, Felix and Haardt, Martin and Elger, Gordon and Lopes de Mendon{\c{c}}a, F{\´a}bio L{\´u}cio and de Sousa Junior, Rafael Tim{\´o}teo}, title = {Tensor-based framework with model order selection and high accuracy factor decomposition for time-delay estimation in dynamic multipath scenarios}, volume = {8}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2020.3024597}, pages = {174931 -- 174942}, year = {2020}, abstract = {Global Navigation Satellite Systems (GNSS) are crucial for applications that demand very accurate positioning. Tensor-based time-delay estimation methods, such as CPD-GEVD, DoA/KRF, and SECSI, combined with the GPS3 L1C signal, are capable of, significantly, mitigating the positioning degradation caused by multipath components. However, even though these schemes require an estimated model order, they assume that the number of multipath components is constant. In GNSS applications, the number of multipath components is time-varying in dynamic scenarios. Thus, in this paper, we propose a tensor-based framework with model order selection and high accuracy factor decomposition for time-delay estimation in dynamic multipath scenarios. Our proposed approach exploits the estimates of the model order for each slice by grouping the data tensor slices into sub-tensors to provide high accuracy factor decomposition. We further enhance the proposed approach by incorporating the tensor-based Multiple Denoising (MuDe).}, language = {en} } @article{DeloozWilleckeGarlichsetal.2022, author = {Delooz, Quentin and Willecke, Alexander and Garlichs, Keno and Hagau, Andreas-Christian and Wolf, Lars and Vinel, Alexey and Festag, Andreas}, title = {Analysis and Evaluation of Information Redundancy Mitigation for V2X Collective Perception}, volume = {10}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2022.3170029}, pages = {47076 -- 47093}, year = {2022}, abstract = {Sensor data sharing enables vehicles to exchange locally perceived sensor data among each other and with the roadside infrastructure to increase their environmental awareness. It is commonly regarded as a next-generation vehicular communication service beyond the exchange of highly aggregated messages in the first generation. The approach is being considered in the European standardization process, where it relies on the exchange of locally detected objects representing anything safety-relevant, such as other vehicles or pedestrians, in periodically broadcasted messages to vehicles in direct communication range. Objects filtering methods for inclusion in a message are necessary to avoid overloading a channel and provoking unnecessary data processing. Initial studies provided in a pre-standardization report about sensor data sharing elaborated a first set of rules to filter objects based on their characteristics, such as their dynamics or type. However, these rules still lack the consideration of information received by other stations to operate. Specifically, to address the problem of information redundancy, several rules have been proposed, but their performance has not been evaluated yet comprehensively. In the present work, the rules are further analyzed, assessed, and compared. Functional and operational requirements are investigated. A performance evaluation is realized by discrete-event simulations in a scenario for a representative city with realistic vehicle densities and mobility patterns. A score and other redundancy-level metrics are elaborated to ease the evaluation and comparison of the filtering rules. Finally, improvements and future works to the filtering methods are proposed.}, language = {en} } @article{SongZhouLyuetal.2023, author = {Song, Rui and Zhou, Liguo and Lyu, Lingjuan and Festag, Andreas and Knoll, Alois}, title = {ResFed: Communication-Efficient Federated Learning With Deep Compressed Residuals}, volume = {11}, journal = {IEEE Internet of Things Journal}, number = {6}, publisher = {IEEE}, address = {New York}, issn = {2327-4662}, doi = {https://doi.org/10.1109/JIOT.2023.3324079}, pages = {9458 -- 9472}, year = {2023}, abstract = {Federated learning allows for cooperative training among distributed clients by sharing their locally learned model parameters, such as weights or gradients. However, as model size increases, the communication bandwidth required for deployment in wireless networks becomes a bottleneck. To address this, we propose a residual-based federated learning framework (ResFed) that transmits residuals instead of gradients or weights in networks. By predicting model updates at both clients and the server, residuals are calculated as the difference between updated and predicted models and contain more dense information than weights or gradients. We find that the residuals are less sensitive to an increasing compression ratio than other parameters, and hence use lossy compression techniques on residuals to improve communication efficiency for training in federated settings. With the same compression ratio, ResFed outperforms current methods (weight- or gradient-based federated learning) by over 1.4× on federated data sets, including MNIST, FashionMNIST, SVHN, CIFAR-10, CIFAR-100, and FEMNIST, in client-to-server communication, and can also be applied to reduce communication costs for server-to-client communication.}, language = {en} } @article{HegdeSongFestag2023, author = {Hegde, Anupama and Song, Rui and Festag, Andreas}, title = {Radio Resource Allocation in 5G-NR V2X: A Multi-Agent Actor-Critic Based Approach}, volume = {11}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2023.3305267}, pages = {87225 -- 87244}, year = {2023}, abstract = {The efficiency of radio resource allocation and scheduling procedures in Cellular Vehicle-to-X (Cellular V2X) communication networks directly affects link quality in terms of latency and reliability. However, owing to the continuous movement of vehicles, it is impossible to have a centralized coordinating unit at all times to manage the allocation of radio resources. In the unmanaged mode of the fifth generation new radio (5G-NR) V2X, the sensing-based semi-persistent scheduling (SB-SPS) loses its effectiveness when V2X data messages become aperiodic with varying data sizes. This leads to misinformed resource allocation decisions among vehicles and frequent resource collisions. To improve resource selection, this study formulates the Cellular V2X communication network as a decentralized multi-agent networked markov decision process (MDP) where each vehicle agent executes an actor-critic-based radio resource scheduler. Developing further the actor-critic methodology for the radio resource allocation problem in Cellular V2X, two variants are derived: independent actor-critic (IAC) and shared experience actor-critic (SEAC). Results from simulation studies indicate that the actor-critic schedulers improve reliability, achieving a 15-20\% higher probability of reception under high vehicular density scenarios with aperiodic traffic patterns.}, 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} } @unpublished{SongZhouLyuetal.2022, author = {Song, Rui and Zhou, Liguo and Lyu, Lingjuan and Festag, Andreas and Knoll, Alois}, title = {ResFed: Communication Efficient Federated Learning by Transmitting Deep Compressed Residuals}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2212.05602}, year = {2022}, language = {en} } @inproceedings{FestagUdupaGarciaetal.2021, author = {Festag, Andreas and Udupa, Shrivatsa and Garcia, Lourdes and Wellens, Ralf and Hecht, Matthias and Ulfig, Pierre}, title = {End-to-End Performance Measurements of Drone Communications in 5G Cellular Networks}, booktitle = {2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall): Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-1368-8}, doi = {https://doi.org/10.1109/VTC2021-Fall52928.2021.9625429}, year = {2021}, language = {en} } @inproceedings{FestagSong2021, author = {Festag, Andreas and Song, Rui}, title = {Analysis of Existing Approaches for Information Sharing in Cooperative Intelligent Transport Systems}, booktitle = {FISITA World Congress 2021}, subtitle = {SENSORIS and V2X Messaging}, publisher = {FISITA}, address = {Bishops Stortford}, url = {https://www.fisita.com/library/f2020-acm-012}, year = {2021}, language = {en} }