ORCID

0009-0002-3898-4079

Keywords

Traffic monitoring, UAV, CCTV, Spatial Tracking, Perspective Transformation, Reidentification

Abstract

This study integrates Unmanned Aerial Vehicles (UAVs) and Closed-Circuit Television (CCTV) cameras to enhance traffic monitoring through a Multi-Object Multi-Camera Multi-View Tracking (MOMCMVT) framework. By combining UAV and CCTV data, the framework provides a more comprehensive and accurate representation of traffic dynamics. The Automated Roadway Conflict Identification System (ARCIS) is utilized to stabilize UAV footage using the Scale-Invariant Feature Transform (SIFT) algorithm, while the Channel and Spatial Reliability Tracking (CSRT) algorithm ensures robust vehicle tracking in CCTV footage. To address perspective disparities and limited overlapping coverage, perspective transformations and GPS adjustments are applied, aligning image coordinates with real-world locations. The system was evaluated on a 975-meter freeway segment over two days using four UAVs and multiple CCTV cameras. Experimental results indicate high accuracy in vehicle detection and tracking, achieving an F1 score of 0.869 and accuracy of 0.909 for overlapping coverage, and an F1 score of 0.9478 with accuracy of 0.9009 for non-overlapping coverage. These findings demonstrate the effectiveness of integrating UAV and CCTV data for large-scale traffic monitoring, offering improved vehicle tracking and reallocation across multiple camera views. The proposed approach enhances real-time traffic management, congestion analysis, and safety assessment by providing reliable and precise vehicle movement data. This research contributes to advancing multi-camera multi-view tracking methodologies, offering a scalable and adaptable solution for traffic surveillance. The integration of UAV and CCTV data presents a promising direction for improving traffic monitoring accuracy and efficiency, with potential applications in intelligent transportation systems and smart city initiatives.

Completion Date

2025

Semester

Spring

Committee Chair

Abdel-Aty, Mohamed

Degree

Master of Science in Civil Engineering (M.S.C.E.)

College

College of Engineering and Computer Science

Department

Department of Civil, Environmental and Construction Engineering

Identifier

DP0029403

Document Type

Dissertation/Thesis

Campus Location

Orlando (Main) Campus

Download

Share

COinS