West Virginia University
Single Field of View Calibration Through Estimating Three Mutually Orthogonal Vanishing Points for Spatial Data Collection in Traffic Scenes
Abstract
dc:description.abstractAccurately 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.
Degree
thesis:*- Name thesis:degree_name
- MS
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Civil and Environmental Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Dutta, Sourav
- Contributors dc:contributor
-
- Fei Dai
- Xin Li
- Yoojung Yoon
Subjects
dc:subject × 5Identifiers
dc:identifier.*- Identifier
-
<p><a href="https://orcid.org/0009-0003-5340-8034">https://orcid.org/0009-0003-5340-8034</a></p>
https://researchrepository.wvu.edu/etd/12210