Learning to integrate vision data into road network data
This work addresses the problem of improving machine learning applications for connected and autonomous vehicles by enhancing road network embeddings, though it is incremental as it builds on existing methods with new data integration.
The paper tackles the challenge of creating meaningful representations for road networks by integrating remote sensing vision data into road network data, achieving state-of-the-art performance on a road type classification task on the OSM+DiDi Chuxing dataset in Chengdu, China.
Road networks are the core infrastructure for connected and autonomous vehicles, but creating meaningful representations for machine learning applications is a challenging task. In this work, we propose to integrate remote sensing vision data into road network data for improved embeddings with graph neural networks. We present a segmentation of road edges based on spatio-temporal road and traffic characteristics, which allows to enrich the attribute set of road networks with visual features of satellite imagery and digital surface models. We show that both, the segmentation and the integration of vision data can increase performance on a road type classification task, and we achieve state-of-the-art performance on the OSM+DiDi Chuxing dataset on Chengdu, China.