We present TUMTraf VideoQA, a novel dataset and benchmark designed for spatio-temporal video understanding in complex roadside traffic scenarios. The dataset comprises 1,000 videos, featuring 85,000 multiple-choice QA pairs, 2,300 object captioning, and 5,700 object grounding annotations, encompassing diverse real-world conditions such as adverse weather and traffic anomalies. By incorporating tuple-based spatio-temporal object expressions, TUMTraf VideoQA unifies three essential tasks—multiple-choice video question answering, referred object captioning, and spatio-temporal object grounding—within a cohesive evaluation framework. We further introduce the TraffiX-Qwen baseline model, enhanced with visual token sampling strategies, providing valuable insights into the challenges of fine-grained spatio-temporal reasoning. Extensive experiments demonstrate the dataset’s complexity, highlight the limitations of existing models, and position TUMTraf VideoQA as a robust foundation for advancing research in intelligent transportation systems. The dataset and benchmark are publicly available to facilitate further exploration.

Most vision-based sensing and localization infrastructure today employ conventional area scanning cameras due to the high information density and cost efficiency offered by them. While the information-rich two-dimensional images provided by such sensors make it easier to detect and classify traffic objects with the help of deep neural networks, their accurate localization in the three-dimensional real world also calls for a reliable calibration methodology, that maintains accuracy not just during installation, but also under continuous operation over time. In this paper, we propose a camera calibration architecture that extracts and uses corresponding targets from high definition maps, augment it with an efficient stabilization mechanism in order to compensate for the errors arising out of fast transient vibrations and slow orientational drifts. Finally, we evaluate its performance on a real-world test site.

Open source system level simulators play a crucial role in the early stage research and optimization of cellular V2X communication networks and cooperative intelligent transportation systems by providing for accurate virtual modelling, rapid evaluation of system level design and algorithm development, and by offering the possibility to build-up on previous research. Amidst the various architectures under consideration for future cellular V2X, small moving cells or moving network convoys are promising candidates, considering their inherent mobility. The orchestration of such architectures in combination with the availability of precise information about the vehicles from road side infrastructure open up new possibilities for a cost-optimal deployment and a resource-optimal operation of the cellular V2X networks. Towards this goal, we propose and present an open source simulation framework for moving-network-convoy based cellular V2X applications, and make it available for wider use at https://github.com/tum-air/ConvoyV2X

Radar is among the most popular sensors in modern Intelligent Transportation Systems (ITSs), enabling weather-robust perception. The orientation and position of the traffic radar relative to the ITS coordinate system are necessary for the perception fusion in ITSs. However, due to the unknown target association, sparseness and noisiness of traffic radar measurements, the robust and accurate extrinsic calibration of traffic radar is challenging. In this paper, we propose a targetless traffic radar calibration method based on GPS to overcome the inconvenience during ITS operation, because the installation of a dedicated calibration target on the highway is impractical and dangerous. On the other hand, the high-precision GPS device installed on the moving vehicle can provide traffic radar with accurate positioning information of the detection target. Furthermore, during the optimization process of extrinsic calibration, we propose a globally optimal registration method, which is robust to noise and outliers in radar measurements, and is called Gaussian Mixture Robust Branch and Bound (GMRBnB). Specifically, we first construct the robust objective function by utilizing the Gaussian Mixture Model (GMM). Then, we derive novel relaxation bounds and present the GMRBnB algorithm that overcomes the susceptibility to local minima and the dependence on initialization of traditional optimization methods. Compared with existing methods, extensive experiments in synthetic and real-world data demonstrate that our method is not only globally optimal, but also more accurate and robust.

Data-intensive machine learning based techniques increasingly play a prominent role in the development of future mobility solutions - from driver assistance and automation functions in vehicles, to real-time traffic management systems realized through dedicated infrastructure. The availability of high quality real-world data is often an important prerequisite for the development and reliable deployment of such systems in large scale. Towards this endeavour, we present the A9-Dataset based on roadside sensor infrastructure from the 3 km long Providentia++ test field near Munich in Germany. The dataset includes anonymized and precision-timestamped multi-modal sensor and object data in high resolution, covering a variety of traffic situations. As part of the first set of data, which we describe in this paper, we provide camera and LiDAR frames from two overhead gantry bridges on the A9 autobahn with the corresponding objects labeled with 3D bounding boxes. The first set includes in total more than 1000 sensor frames and 14000 traffic objects. The dataset is available for download at https://a9-dataset.com.

A reliable and all-pervading information-sharing mechanism between traffic participants and infrastructure systems, widely termed V2X communication, is crucial to realize the goals of future cooperative intelligent transportation systems - that of improving traffic safety and efficiency. The need to maintain high reliability and availability amidst a permanentlychanging network topology caused by the moving vehicles translate into an increased demand for network management infrastructure and radio resources. Such capital-intensive demands can act as significant deterrents in the quest for a rapid large-scale deployment of V2X technologies. With the goal to reduce the demand for fixed infrastructure and radio resources, we propose an alternate network deployment architecture based on the concept of moving network convoys, deploy it in a distributed C-ITS simulation environment, and provide a quantitative assessment of the potential benefits in comparison to conventional network deployment architectures.