CYCLIST+IMU

CYCLIST+IMU is a synchronized visual–inertial dataset for cyclist orientation and perception in urban environments. The dataset integrates monocular RGB images captured from a vehicle-mounted camera with inertial measurements acquired from bicycle-mounted and vehicle-mounted IMU units. Each sample provides frame-level temporal alignment between visual data and orientation metadata, including cyclist yaw and roll angles. In addition to RGB images, the dataset includes polygon-based semantic segmentation annotations, region-of-interest detection files, relative depth maps estimated from RGB data, and acquisition-level inertial metadata files. The dataset was collected during multiple real-world urban acquisition sessions and is intended to support research on cyclist detection, orientation estimation, semantic segmentation, and multimodal sensor fusion for intelligent transportation systems.