Intelligent transportation systems (ITS) change our communities by improving the safety and convenience of people’s daily mobility. The system relies on multimodal traffic monitoring, that needs to provide reliable, efficient and detailed traffic information for traffic safety and planning. How to reliably and intelligently monitor intersection traffic with multimodal information is one of the most critical topics in intelligent transportation research.
In multimodal traffic monitoring, we gather traffic statistics for distinct transportation modes, such as pedestrians, cars and bicycles, in order to analyze and improve people’s daily mobility in terms of safety and convenience.
In this study, we use a high-resolution millimeter-wave (mmWave) radar sensor to obtain a relatively richer radar point cloud representation for a traffic monitoring scenario. Based on a new feature vector, we use the multivariate Gaussian mixture model (GMM) to do the radar point cloud segmentation, i.e. ‘pointwise’ classification, in an unsupervised learning environment.
In our experiment, we collected radar point clouds for pedestrians and cars, which also contained the inevitable clutter from the surroundings. The experimental results using GMM on the new feature vector demonstrated a good segmentation performance in terms of the intersection-over-union (IoU) metrics. The detailed methodology and validation metrics...Read more