Open Collections

Bazzaza, Tala

University of British Columbia

Traffic congestion has become a universal phenomenon in metropolitan cities. The prevalence of congested roads not only results in delays, increased fuel consumption, environmental pollution, and a reduced quality of life but also contributes to lowered productivity levels due to the significant time wasted in the search for available parking spaces. Current solutions are either tailored solely for detecting vacant spaces within parking lots or rely on unfeasible street sensors and stationary surveillance cameras, simply falling short in accurately pinpointing individual free street parking spots. In this thesis, we introduce an innovative real-time street parking detection and localization system designed to cater to both human-driven and autonomous vehicles. Our solution is specifically engineered to be integrated into modern vehicles, utilizing the live video feed from the car's built-in navigation and obstacle avoidance cameras. This approach merges convolutional neural networks, video global motion analysis, and a distance measurement technique, enabling accurate detection and precise localization of vacant street parking spaces. Our proposed solution eliminates the influence of car speed, prevents redundant detection of the same parking spot during abrupt stops, and reduces computational costs and complexity. We introduce a unique and comprehensive dataset tailored for this objective, serving as the cornerstone for training and evaluating established object detection network architectures to identify the one that strikes the best balance between accuracy and computational efficiency and thus aligns with the prerequisites of integrating this solution into each vehicle. Performance evaluations confirm the proposed method’s efficacy across all types of scenarios.

Text

2024-10-31

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/86224

Electrical and Computer Engineering

University of British Columbia

UBCV

http://creativecommons.org/licenses/by-nc-nd/4.0/