Data-Driven Mobility and Transport Planning in Municipalities: Smart Solutions for Limited Resources

The research paper highlights the importance of data-driven approaches in urban and mobility development for local communities. Tailor-made solutions, based on a precise understanding of local challenges, are essential, especially for smaller or financially weaker municipalities. Implementing a data-gathering infrastructure, particularly within Smart City concepts, often presents challenges due to limited technical and financial resources, as well as a lack of expertise. To address these issues, a video-based traffic detector was developed to enable flexible and minimally invasive traffic measurement. This technology differs from traditional AI models through its miniaturization and application to less powerful embedded systems. The ‘Machine Learning on the edge’ approach was tested in Zwickau, Saxony, Germany, where its robustness and reliability were confirmed by comparison with manual traffic counts. The field study demonstrated that reliable data collection is possible even with minimal technical resources. This contrasts with traditional traffic detection technologies, which rely on induction loops and compute-intensive systems. The novel approach offers a cost-efficient alternative, particularly suitable for minor townships with limited fiscal capacity. The study's conclusions recommend promoting data-based approaches in municipal planning, investing in cost-effective technologies like video-based traffic detectors, emphasizing scalability and adaptability, and continuously monitoring and improving data solutions. This enables the implementation of Smart City concepts even in financially challenged municipalities, contributing to the improvement of local quality of life.