ORCID
0009-0004-9906-2136
Keywords
Mid-Block Pedestrian Crossings, Computer Vision, Pedestrian Safety, Traffic Efficiency, Conflict Analysis, Before-After Evaluation
Abstract
This study presents a comprehensive evaluation of midblock pedestrian crossings in terms of safety and traffic efficiency, with a particular focus on the newly implemented Mid-Block Pedestrian Signal (MPS) systems. Extensive CCTV video data were collected across Florida and processed using advanced computer vision techniques, specifically the RT-DETR model for object detection and the ByteTrack algorithm for object tracking, to analyze vehicle-pedestrian interactions in detail. Since there is limited post-implementation crash data available for all locations, Surrogate Safety Measures (SSMs) were employed to assess safety outcomes. Conflict Modification Factors (CoMFs) were estimated using Cross-Sectional (CS), Comparison Group (CG), and Empirical Bayes (EB) approaches. Across all evaluation methods and reference treatments—including Pedestrian Hybrid Beacons (PHBs), Rectangular Rapid Flashing Beacons (RRFBs), and their combinations, MPS installations consistently demonstrated a reduction in both moderate and serious pedestrian-vehicle conflicts. Traffic efficiency was also assessed by calculating Delay Modification Factors (DMFs) for each pedestrian-vehicle interaction using the same methodological framework. Findings revealed that while MPS introduces more vehicle delay than RRFB and Flashing Beacon due to required red-phase stops, they offer reduced delays compared to PHB. Furthermore, a two-stage Joint Selection–Outcome Modeling framework was developed to rigorously assess the effectiveness of MPS implementation. Joint likelihood estimation corrected for selection bias by linking treatment assignment to outcome patterns within a unified likelihood structure. Results confirmed that MPSs significantly reduce both moderate and serious conflicts. Given their superior safety performance and comparatively lower vehicle delays relative to PHBs, MPS systems emerge as a promising and effective treatment for enhancing pedestrian safety at midblock crossings. These findings support the consideration of MPS as a preferred alternative for upgrading existing pedestrian crossings or deploying new pedestrian signal systems.
Completion Date
2025
Semester
Summer
Committee Chair
Mohamed Abdel-Aty
Degree
Doctor of Philosophy (Ph.D.)
College
College of Engineering and Computer Science
Department
Civil, Environmental and Construction Engineering
Format
Release Date
8-15-2026
Document Type
Dissertation
Campus Location
Orlando (Main) Campus
Subjects
Pedestrians--Safety measures; Traffic safety--Evaluation; Pedestrian facilities design--Evaluation; Traffic conflicts--Research; Traffic safety--Econometric models
STARS Citation
Ahsan, Md Jamil, "Quantifying Surrogate Safety Measures and Traffic Delays at Mid-Block Pedestrian Crossings Using Video-Based Data Analytics" (2025). Graduate Thesis and Dissertation post-2024. 548.
https://stars.library.ucf.edu/etd2024/548
Accessibility Statement
This item was created or digitized prior to April 24, 2027, or is a reproduction of legacy media created before that date. It is preserved in its original, unmodified state specifically for research, reference, or historical recordkeeping. In accordance with the ADA Title II Final Rule, the University Libraries provides accessible versions of archival materials upon request. To request an accommodation for this item, please submit an accessibility request form.