Vehicle trajectory data, as the foundation of scientific research in the field of autonomous driving, contains nearly all macro and micro traffic flow information. In this paper, we propose a dataset of vehicle trajectories that captures the vehicle’s individual characteristics based on multi-sensor fusion, which combines the data of UAV and radar vehicle detector, and applies Kalman filter for accuracy correction. Drones provide a bird’s-eye view of a wide range of road areas and capture the vehicle’s global trajectory, while radar detectors are mounted on pedestrian overpasses to provide precise data on vehicle personalization and speed. By taking advantage of the advantages of both sensors, the limitations of a single sensor in complex environments are effectively overcome. In addition, radar is able to capture personalized information such as vehicle type, size, license plate number, license plate color, and vehicle brand and sub-brand logos. The experimental results show that the multi-sensor fusion method based on Kalman filter achieves higher detection accuracy and robustness in various environments, and significantly improves the effect of vehicle data acquisition. This dataset provides key data support for analyzing driving behavior patterns, developing interaction strategies for autonomous vehicles, and advancing research into autonomous driving and advanced driver assistance systems (ADAS).