Files in this item



application/pdfSNYDER-THESIS-2020.pdf (5MB)
(no description provided)PDF


Title:STREETS: a benchmark dataset for suburban traffic forecasting
Author(s):Snyder, Corey
Advisor(s):Do, Minh
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
computer vision
graph signal processing
machine learning
traffic forecasting
Abstract:In this work, we introduce and benchmark STREETS, a novel traffic flow dataset from publicly available web cameras in the suburbs of Chicago, IL. STREETS addresses multiple limitations of existing vehicular traffic datasets. Many current datasets lack a coherent traffic network graph to describe the relationship between sensors. The datasets that do provide a graph depict traffic flow in urban population centers or highway systems and use costly sensors like induction loops. These contexts differ from that of a suburban traffic body. Our dataset provides over 4 million still images across 2.5 months and 100 web cameras in suburban Lake County, IL. We divide the cameras into two distinct communities, provide directed and undirected graphical representations of these traffic networks, and count vehicles to aggregate traffic statistics. Our goal is to give researchers a benchmark dataset for exploring the capabilities of inexpensive and non-invasive sensors like web cameras to understand complex traffic bodies in communities of any size. We perform thorough traffic forecasting experiments to benchmark several traffic forecasting models on STREETS and define evaluation metrics that are pertinent to understanding performance on our dataset.
Issue Date:2020-12-04
Rights Information:Copyright 2020 Corey Snyder
Date Available in IDEALS:2021-03-05
Date Deposited:2020-12

This item appears in the following Collection(s)

Item Statistics