01628206

Component

Detailed road features (e.g., lane marks and stop bars) are crucial for many recent intelligent transportation system applications, especially for automated or autonomous driving systems. In this paper, a crowdsourcing based method is proposed to mark intersection areas and map stop bar positions without prior knowledge of road information. The proposed method includes an efficient approach for marking intersection areas by analyzing the entropy of moving direction, as well as a statistical model of stop positions for estimating the number and coordinates of stop bars. The proposed method is applied to the real-world dataset collected for the Safety Pilot Model Deployment Program (SPMDP). The numerical analysis results prove its applicability and robustness in processing GPS trajectories of an urban region (a 1.2 km by 2 km rectangular area). For the intersections covered well by trajectories, the accuracy of marking intersections is 95.7%. For stop bar positioning, the mean and standard deviation of the errors are 0.25 m and 0.32 m.

This paper was sponsored by TRB committee ABJ30 Standing Committee on Urban Transportation Data and Information Systems.

01618707

17-06670

English

18p

2017

Transportation Research Board 96th Annual Meeting

Digital/other

Figures; References; Tables

Accuracy; Crowdsourcing; Data collection; Detection and identification systems; Floating car data; Intersections; Vehicle trajectories

Stop lines

Data and Information Technology; Highways

Transportation Research Board Annual Meeting 2017 Paper #17-06670

PRP, TRIS, TRB, ATRI

Dec 8 2016 12:44PM