Author ORCID Identifier

https://orcid.org/0009-0003-5340-8034

Semester

Fall

Date of Graduation

2023

Document Type

Thesis

Degree Type

MS

College

Statler College of Engineering and Mineral Resources

Department

Civil and Environmental Engineering

Committee Chair

Fei Dai

Committee Co-Chair

Xin Li

Committee Member

Yoojung Yoon

Abstract

Accurately extracting the three mutually orthogonal vanishing points plays a vital role in the field of view calibration for many surveillance-based traffic applications. However, the paucity of parallel lines along the dominant directions in many traffic scenes engenders the inapplicability of the current methods for a successful calibration. This research proposed a novel vanishing point estimating method for traffic scenes. This method capitalizes on both the road scene and moving vehicles for the determination of the dominant directions of the real-world coordinate frame. It also exploits distinctive edgelets for the direct identification of vanishing point candidates. Both lab and field experiments were undertaken to assess the performance of the proposed method. The results signified the advances of the method in traffic scenes with scarce parallel line features and eliminating the need for trial-and-error parameter tuning in different scenes.

Embargo Reason

Publication Pending

Available for download on Saturday, December 06, 2025

Share

COinS