Extracting curbside storm drain locations from street-level images

This thesis presents a machine vision procedure to identify and extract storm drain locations from natural images along surface street curbsides. Existing storm drain infrastructure information is commonly reposed by managing agencies in either paper or digital format. Access to these data for urban hydrologic and hydraulic modeling purposes may be limited by security protocols and/or the format in which the data may be available. The procedure described in this work uses a novel vision algorithm with Google Street View imagery to identify and extract the locations of curbside storm drains. Results are converted into a tabular format that can be converted into geometric input files for modeling purposes. This fast, approximation approach to assembling storm drain data could be of interest to public works managers, urban hydrology and hydraulics practitioners and researchers, and citizen scientists, to improve general understanding of the civil and environmental infrastructure.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Civil Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Depwe, Elizabeth E.

Contributors dc:contributor

• Peschel, Joshua
• Rutherford, Cassandra

• infrastructure assessment
• computer vision
• Google Street View
• data mining
• stormwater management
• image detection
• image processing

Statement dc:rights

• Copyright 2015 Elizabeth E. Depwe

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/88213

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/88213