WUT-NGSIM: A High-precision and Trustworthy Vehicle Trajectory Dataset

Citation Author(s):
Yi
He
Bo
Cao
Ching-Yao
Chan
Submitted by:
Yi HE
Last updated:
Thu, 12/01/2022 - 10:53
DOI:
10.21227/hmsb-ka76
Data Format:
Links:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

The high-precision and long-distance extraction and construction of vehicle trajectory data and microscopic traffic flow characteristics are critical for traffic safety studies. Current research typically relies on a limited number of datasets which suffer from vehicle detection inaccuracy and limitation of the coverage area. Therefore, we establish a high-precision and long-distance vehicle trajectory dataset of urban scenarios. Primary features of the established dataset: (1) the trajectory data are extracted based on a trajectory extraction framework that contains the video stabilization, vehicle detection, vehicle tracking, data repair and smoothing. (2) The broken trajectory data caused by occlusion are connected through fusing tracking results at different frame rates based on the Kalman filter and Hungarian Algorithm. (2) Long-distance trajectory data from multi-videos are constructed based on video stitching, video fusion and trajectory fusion. The vehicle detection accuracy can reach to 99.1% and  the trajectory longth can reach to 620 meters. This trajectory dataset can provide the high-precision and long-distance vehicle trajectory data for those data-driven studies in transportation.

Instructions: 

This dataset can  support the data-driven researches in transportation.