Date of Award

6-18-2024

Document Type

Thesis

Publisher

Santa Clara : Santa Clara University, 2024

Department

Computer Science and Engineering

First Advisor

David Anastasiu

Abstract

Information on traffic patterns is essential for identifying and addressing sources of traffic congestion and informing future road layouts to create safer and more efficient roads. To this end, we develop a Corridor Counting, or Multi- Camera Vehicle Counting, algorithm that quantifies the number of vehicles traveling along a specific stretch of road. Our work builds upon the related problem of Multi-Camera Vehicle Tracking and draws inspiration from methods used for Single-Camera Counting. We propose a six-step solution comprising Vehicle Detection, Feature Extraction, Single- Camera Vehicle Tracking, Re-Identification, Movement Matching, and Multi-Camera Vehicle Counting. Finally, we adapt an evaluation metric from Single-Camera Vehicle Counting to assess the effectiveness of our solution.

Share

COinS