TY - CHAP A1 - Wurst, Jonas A1 - Balasubramanian, Lakshman A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios T2 - 2022 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV51971.2022.9827187 KW - clustering KW - novelty detection KW - scenario-based testing KW - deep learning Y1 - 2022 UR - https://doi.org/10.1109/IV51971.2022.9827187 SN - 978-1-6654-8821-1 SP - 484 EP - 491 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Kruber, Friedrich A1 - Wurst, Jonas A1 - Botsch, Michael T1 - An Unsupervised Random Forest Clustering Technique for Automatic Traffic Scenario Categorization UR - https://doi.org/10.48550/arXiv.2004.02121 Y1 - 2020 UR - https://doi.org/10.48550/arXiv.2004.02121 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Balasubramanian, Lakshman A1 - Wurst, Jonas A1 - Botsch, Michael A1 - Deng, Ke T1 - Traffic scenario clustering by iterative optimisation of self-supervised networks using a random forest activation pattern similarity T2 - 2021 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV48863.2021.9575615 Y1 - 2021 UR - https://doi.org/10.1109/IV48863.2021.9575615 SN - 978-1-7281-5394-0 SP - 682 EP - 689 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Kruber, Friedrich A1 - Wurst, Jonas A1 - Botsch, Michael T1 - An Unsupervised Random Forest Clustering Technique for Automatic Traffic Scenario Categorization T2 - 2018 IEEE Intelligent Transportation Systems Conference UR - https://doi.org/10.1109/ITSC.2018.8569682 Y1 - 2018 UR - https://doi.org/10.1109/ITSC.2018.8569682 SN - 978-1-7281-0323-5 SP - 2811 EP - 2818 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Balasubramanian, Lakshman A1 - Wurst, Jonas A1 - Egolf, Robin A1 - Botsch, Michael A1 - Utschick, Wolfgang A1 - Deng, Ke T1 - ExAgt: Expert-guided Augmentation for Representation Learning of Traffic Scenarios T2 - 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC55140.2022.9922453 KW - Representation learning KW - Visualization KW - Codes KW - Self-supervised learning KW - Prediction methods KW - Distortion KW - Stability analysis Y1 - 2022 UR - https://doi.org/10.1109/ITSC55140.2022.9922453 SN - 978-1-6654-6880-0 SP - 1471 EP - 1478 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Kruber, Friedrich A1 - Sánchez Morales, Eduardo A1 - Egolf, Robin A1 - Wurst, Jonas A1 - Chakraborty, Samarjit A1 - Botsch, Michael T1 - Micro- and Macroscopic Road Traffic Analysis using Drone Image Data JF - Leibniz Transactions on Embedded Systems N2 - The current development in the drone technology, alongside with machine learning based image processing, open new possibilities for various applications. Thus, the market volume is expected to grow rapidly over the next years. The goal of this paper is to demonstrate the capabilities and limitations of drone based image data processing for the purpose of road traffic analysis. In the first part a method for generating microscopic traffic data is proposed. More precisely, the state of vehicles and the resulting trajectories are estimated. The method is validated by conducting experiments with reference sensors and proofs to achieve precise vehicle state estimation results. It is also shown, how the computational effort can be reduced by incorporating the tracking information into a neural network. A discussion on current limitations supplements the findings. By collecting a large number of vehicle trajectories, macroscopic statistics, such as traffic flow and density can be obtained from the data. In the second part, a publicly available drone based data set is analyzed to evaluate the suitability for macroscopic traffic modeling. The results show that the method is well suited for gaining detailed information about macroscopic statistics, such as traffic flow dependent time headway or lane change occurrences. In conclusion, this paper presents methods to exploit the remarkable opportunities of drone based image processing for joint macro- and microscopic traffic analysis. UR - https://doi.org/10.4230/LITES.8.1.2 KW - traffic data analysis KW - trajectory data KW - drone image data Y1 - 2022 UR - https://doi.org/10.4230/LITES.8.1.2 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-29704 SN - 2199-2002 VL - 8 IS - 1 SP - 02:1 EP - 02:27 PB - Schloss Dagstuhl CY - Wadern ER - TY - JOUR A1 - Flores Fernández, Alberto A1 - Wurst, Jonas A1 - Sánchez Morales, Eduardo A1 - Botsch, Michael A1 - Facchi, Christian A1 - García Higuera, Andrés T1 - Probabilistic Traffic Motion Labeling for Multi-Modal Vehicle Route Prediction JF - Sensors N2 - The prediction of the motion of traffic participants is a crucial aspect for the research and development of Automated Driving Systems (ADSs). Recent approaches are based on multi-modal motion prediction, which requires the assignment of a probability score to each of the multiple predicted motion hypotheses. However, there is a lack of ground truth for this probability score in the existing datasets. This implies that current Machine Learning (ML) models evaluate the multiple predictions by comparing them with the single real trajectory labeled in the dataset. In this work, a novel data-based method named Probabilistic Traffic Motion Labeling (PROMOTING) is introduced in order to (a) generate probable future routes and (b) estimate their probabilities. PROMOTING is presented with the focus on urban intersections. The generation of probable future routes is (a) based on a real traffic dataset and consists of two steps: first, a clustering of intersections with similar road topology, and second, a clustering of similar routes that are driven in each cluster from the first step. The estimation of the route probabilities is (b) based on a frequentist approach that considers how traffic participants will move in the future given their motion history. PROMOTING is evaluated with the publicly available Lyft database. The results show that PROMOTING is an appropriate approach to estimate the probabilities of the future motion of traffic participants in urban intersections. In this regard, PROMOTING can be used as a labeling approach for the generation of a labeled dataset that provides a probability score for probable future routes. Such a labeled dataset currently does not exist and would be highly valuable for ML approaches with the task of multi-modal motion prediction. The code is made open source. UR - https://doi.org/10.3390/s22124498 KW - PROMOTING KW - automated driving systems KW - autonomous vehicles KW - multi-modal KW - motion prediction KW - route prediction KW - machine learning KW - real traffic data Y1 - 2022 UR - https://doi.org/10.3390/s22124498 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-24341 SN - 1424-8220 VL - 22 IS - 12 PB - MDPI CY - Basel ER - TY - INPR A1 - Kruber, Friedrich A1 - Wurst, Jonas A1 - Botsch, Michael A1 - Chakraborty, Samarjit T1 - Highway traffic data: macroscopic, microscopic and criticality analysis for capturing relevant traffic scenarios and traffic modeling based on the highD data set UR - https://doi.org/10.48550/arXiv.1903.04249 KW - Time-To-Collision KW - Time-Headway KW - Risk Perception KW - traffic stream KW - traffic density KW - traffic flow rate KW - driver behavior KW - traffic simulation KW - highway traffic KW - highD Y1 - 2019 UR - https://doi.org/10.48550/arXiv.1903.04249 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Balasubramanian, Lakshman A1 - Wurst, Jonas A1 - Botsch, Michael A1 - Deng, Ke T1 - Open-World Learning for Traffic Scenarios Categorisation JF - IEEE Transactions on Intelligent Vehicles UR - https://doi.org/10.1109/TIV.2023.3260270 KW - self-supervised learning KW - open-world learning KW - traffic scenarios Y1 - 2023 UR - https://doi.org/10.1109/TIV.2023.3260270 SN - 2379-8904 VL - 8 IS - 5 SP - 3506 EP - 3521 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Kruber, Friedrich A1 - Wurst, Jonas A1 - Botsch, Michael A1 - Chakraborty, Samarjit ED - Kukkala, Vipin Kumar ED - Pasricha, Sudeep T1 - Unsupervised Random Forest Learning for Traffic Scenario Categorization T2 - Machine Learning and Optimization Techniques for Automotive Cyber-Physical Systems UR - https://doi.org/10.1007/978-3-031-28016-0_20 KW - Random forest KW - Unsupervised learning KW - Traffic scenarios KW - Categorization and clustering Y1 - 2023 UR - https://doi.org/10.1007/978-3-031-28016-0_20 SN - 978-3-031-28016-0 SN - 978-3-031-28015-3 SP - 565 EP - 590 PB - Springer CY - Cham ER - TY - CHAP A1 - Balasubramanian, Lakshman A1 - Wurst, Jonas A1 - Egolf, Robin A1 - Botsch, Michael A1 - Utschick, Wolfgang A1 - Deng, Ke T1 - SceneDiffusion: Conditioned Latent Diffusion Models for Traffic Scene Prediction T2 - 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC57777.2023.10422482 Y1 - 2024 UR - https://doi.org/10.1109/ITSC57777.2023.10422482 SN - 979-8-3503-9946-2 SP - 3914 EP - 3921 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Kruber, Friedrich A1 - Wurst, Jonas A1 - Sánchez Morales, Eduardo A1 - Chakraborty, Samarjit A1 - Botsch, Michael T1 - Unsupervised and Supervised Learning with the Random Forest Algorithm for Traffic Scenario Clustering and Classification T2 - 2019 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IVS.2019.8813994 Y1 - 2019 UR - https://doi.org/10.1109/IVS.2019.8813994 SN - 978-1-7281-0560-4 SP - 2463 EP - 2470 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Wurst, Jonas A1 - Flores Fernandez, Alberto A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - An Entropy Based Outlier Score and its Application to Novelty Detection for Road Infrastructure Images T2 - 2020 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV47402.2020.9304733 Y1 - 2021 UR - https://doi.org/10.1109/IV47402.2020.9304733 SN - 978-1-7281-6673-5 SP - 1436 EP - 1443 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Wurst, Jonas A1 - Flores Fernandez, Alberto A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - An Entropy Based Outlier Score and its Application to Novelty Detection for Road Infrastructure Images UR - https://doi.org/10.48550/arXiv.2005.13288 Y1 - 2020 UR - https://doi.org/10.48550/arXiv.2005.13288 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Wurst, Jonas A1 - Balasubramanian, Lakshman A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder T2 - 2021 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV48863.2021.9575730 Y1 - 2021 UR - https://doi.org/10.1109/IV48863.2021.9575730 SN - 978-1-7281-5394-0 SP - 1304 EP - 1311 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Wurst, Jonas A1 - Balasubramanian, Lakshman A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder UR - https://doi.org/10.48550/arXiv.2105.01924 Y1 - 2021 UR - https://doi.org/10.48550/arXiv.2105.01924 PB - arXiv CY - Ithaca ER -