It can be difficult to guide yourself across a crosswalk when your visual capabilities are limited, which can be an everyday issue for someone with impaired vision. This paper aims to alleviate that issue for zebra stripe crosswalks by proposing an algorithm that incorporates multiple properties of zebra stripe crosswalks with a neural network to assist in quickly and accurately identifying a crosswalk in video and pictures taken from a smartphone camera.
This method improves the accuracy of zebra crosswalk detection in images. In a large dataset, it correctly identified 76.5% of zebra crosswalks, while reducing the false discovery rate (q-value) from 20% without using neural networks to 2.21% using this neural network method. Only 2.04% of non-crosswalk images as crosswalks using the neural network method.
","abstract_html":"<p>It can be difficult to guide yourself across a crosswalk when your visual capabilities are limited, which can be an everyday issue for someone with impaired vision. This paper aims to alleviate that issue for zebra stripe crosswalks by proposing an algorithm that incorporates multiple properties of zebra stripe crosswalks with a neural network to assist in quickly and accurately identifying a crosswalk in video and pictures taken from a smartphone camera.</p> <p>This method improves the accuracy of zebra crosswalk detection in images. In a large dataset, it correctly identified 76.5% of zebra crosswalks, while reducing the false discovery rate (q-value) from 20% without using neural networks to 2.21% using this neural network method. Only 2.04% of non-crosswalk images as crosswalks using the neural network method.</p>","abstract_has_math":false,"creators":["Banich, Jason David"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["John Seng"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016-06-01T07:00:00Z","date_published":"2016-06-01T07:00:00Z","updated_at":"2026-07-24T01:32:37Z","subjects":["Computer Science","Vision","Zebra Crosswalk","Neural Networks","Visually Impaired"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2016.44"],"render_values":[{"text":"10.15368/theses.2016.44","href":"https://doi.org/10.15368/theses.2016.44","code":true}]}]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/1564","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["John Seng"]},{"key":"dc:creator","label":"Author","values":["Banich, Jason David"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2016-06-03T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Science","Vision","Zebra Crosswalk","Neural Networks","Visually Impaired"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/1564","10.15368/theses.2016.44"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["It can be difficult to guide yourself across a crosswalk when your visual capabilities are limited, which can be an everyday issue for someone with impaired vision. This paper aims to alleviate that issue for zebra stripe crosswalks by proposing an algorithm that incorporates multiple properties of zebra stripe crosswalks with a neural network to assist in quickly and accurately identifying a crosswalk in video and pictures taken from a smartphone camera.
This method improves the accuracy of zebra crosswalk detection in images. In a large dataset, it correctly identified 76.5% of zebra crosswalks, while reducing the false discovery rate (q-value) from 20% without using neural networks to 2.21% using this neural network method. Only 2.04% of non-crosswalk images as crosswalks using the neural network method.
"]},{"key":"dc:title","label":"Title","values":["Zebra Crosswalk Detection Assisted by Neural Networks"]}]}],"canonical_facts":{"dc:contributor":["John Seng"],"dc:creator":["Banich, Jason David"],"dc:date.available":["2016-06-03T07:00:00Z"],"dc:description.abstract":["It can be difficult to guide yourself across a crosswalk when your visual capabilities are limited, which can be an everyday issue for someone with impaired vision. This paper aims to alleviate that issue for zebra stripe crosswalks by proposing an algorithm that incorporates multiple properties of zebra stripe crosswalks with a neural network to assist in quickly and accurately identifying a crosswalk in video and pictures taken from a smartphone camera.
This method improves the accuracy of zebra crosswalk detection in images. In a large dataset, it correctly identified 76.5% of zebra crosswalks, while reducing the false discovery rate (q-value) from 20% without using neural networks to 2.21% using this neural network method. Only 2.04% of non-crosswalk images as crosswalks using the neural network method.
"],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/1564","10.15368/theses.2016.44"],"dc:subject":["Computer Science","Vision","Zebra Crosswalk","Neural Networks","Visually Impaired"],"dc:title":["Zebra Crosswalk Detection Assisted by Neural Networks"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-07-24T01:32:37Z"}