Toward a Computer Vision-based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments.
Identifieur interne : 000022 ( PubMed/Corpus ); précédent : 000021; suivant : 000023Toward a Computer Vision-based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments.
Auteurs : Yingli Tian ; Xiaodong Yang ; Chucai Yi ; Aries ArditiSource :
- Machine vision and applications [ 0932-8092 ] ; 2013.
Abstract
Independent travel is a well known challenge for blind and visually impaired persons. In this paper, we propose a proof-of-concept computer vision-based wayfinding aid for blind people to independently access unfamiliar indoor environments. In order to find different rooms (e.g. an office, a lab, or a bathroom) and other building amenities (e.g. an exit or an elevator), we incorporate object detection with text recognition. First we develop a robust and efficient algorithm to detect doors, elevators, and cabinets based on their general geometric shape, by combining edges and corners. The algorithm is general enough to handle large intra-class variations of objects with different appearances among different indoor environments, as well as small inter-class differences between different objects such as doors and door-like cabinets. Next, in order to distinguish intra-class objects (e.g. an office door from a bathroom door), we extract and recognize text information associated with the detected objects. For text recognition, we first extract text regions from signs with multiple colors and possibly complex backgrounds, and then apply character localization and topological analysis to filter out background interference. The extracted text is recognized using off-the-shelf optical character recognition (OCR) software products. The object type, orientation, location, and text information are presented to the blind traveler as speech.
DOI: 10.1007/s00138-012-0431-7
PubMed: 23630409
Links to Exploration step
pubmed:23630409Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Toward a Computer Vision-based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments.</title><author><name sortKey="Tian, Yingli" sort="Tian, Yingli" uniqKey="Tian Y" first="Yingli" last="Tian">Yingli Tian</name><affiliation><nlm:affiliation>Electrical Engineering Department, The City College, and Graduate Center, City University of New York, New York, NY 10031.</nlm:affiliation></affiliation></author><author><name sortKey="Yang, Xiaodong" sort="Yang, Xiaodong" uniqKey="Yang X" first="Xiaodong" last="Yang">Xiaodong Yang</name></author><author><name sortKey="Yi, Chucai" sort="Yi, Chucai" uniqKey="Yi C" first="Chucai" last="Yi">Chucai Yi</name></author><author><name sortKey="Arditi, Aries" sort="Arditi, Aries" uniqKey="Arditi A" first="Aries" last="Arditi">Aries Arditi</name></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2013">2013</date><idno type="doi">10.1007/s00138-012-0431-7</idno><idno type="RBID">pubmed:23630409</idno><idno type="pmid">23630409</idno><idno type="wicri:Area/PubMed/Corpus">000022</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Toward a Computer Vision-based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments.</title><author><name sortKey="Tian, Yingli" sort="Tian, Yingli" uniqKey="Tian Y" first="Yingli" last="Tian">Yingli Tian</name><affiliation><nlm:affiliation>Electrical Engineering Department, The City College, and Graduate Center, City University of New York, New York, NY 10031.</nlm:affiliation></affiliation></author><author><name sortKey="Yang, Xiaodong" sort="Yang, Xiaodong" uniqKey="Yang X" first="Xiaodong" last="Yang">Xiaodong Yang</name></author><author><name sortKey="Yi, Chucai" sort="Yi, Chucai" uniqKey="Yi C" first="Chucai" last="Yi">Chucai Yi</name></author><author><name sortKey="Arditi, Aries" sort="Arditi, Aries" uniqKey="Arditi A" first="Aries" last="Arditi">Aries Arditi</name></author></analytic><series><title level="j">Machine vision and applications</title><idno type="ISSN">0932-8092</idno><imprint><date when="2013" type="published">2013</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Independent travel is a well known challenge for blind and visually impaired persons. In this paper, we propose a proof-of-concept computer vision-based wayfinding aid for blind people to independently access unfamiliar indoor environments. In order to find different rooms (e.g. an office, a lab, or a bathroom) and other building amenities (e.g. an exit or an elevator), we incorporate object detection with text recognition. First we develop a robust and efficient algorithm to detect doors, elevators, and cabinets based on their general geometric shape, by combining edges and corners. The algorithm is general enough to handle large intra-class variations of objects with different appearances among different indoor environments, as well as small inter-class differences between different objects such as doors and door-like cabinets. Next, in order to distinguish intra-class objects (e.g. an office door from a bathroom door), we extract and recognize text information associated with the detected objects. For text recognition, we first extract text regions from signs with multiple colors and possibly complex backgrounds, and then apply character localization and topological analysis to filter out background interference. The extracted text is recognized using off-the-shelf optical character recognition (OCR) software products. The object type, orientation, location, and text information are presented to the blind traveler as speech.</div></front></TEI><pubmed><MedlineCitation Status="Publisher" Owner="NLM"><PMID Version="1">23630409</PMID><DateCreated><Year>2013</Year><Month>4</Month><Day>30</Day></DateCreated><Article PubModel="Print"><Journal><ISSN IssnType="Print">0932-8092</ISSN><JournalIssue CitedMedium="Print"><Volume>24</Volume><Issue>3</Issue><PubDate><Year>2013</Year><Month>Apr</Month><Day>1</Day></PubDate></JournalIssue><Title>Machine vision and applications</Title><ISOAbbreviation>Mach Vis Appl</ISOAbbreviation></Journal><ArticleTitle>Toward a Computer Vision-based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments.</ArticleTitle><Pagination><MedlinePgn>521-535</MedlinePgn></Pagination><Abstract><AbstractText>Independent travel is a well known challenge for blind and visually impaired persons. In this paper, we propose a proof-of-concept computer vision-based wayfinding aid for blind people to independently access unfamiliar indoor environments. In order to find different rooms (e.g. an office, a lab, or a bathroom) and other building amenities (e.g. an exit or an elevator), we incorporate object detection with text recognition. First we develop a robust and efficient algorithm to detect doors, elevators, and cabinets based on their general geometric shape, by combining edges and corners. The algorithm is general enough to handle large intra-class variations of objects with different appearances among different indoor environments, as well as small inter-class differences between different objects such as doors and door-like cabinets. Next, in order to distinguish intra-class objects (e.g. an office door from a bathroom door), we extract and recognize text information associated with the detected objects. For text recognition, we first extract text regions from signs with multiple colors and possibly complex backgrounds, and then apply character localization and topological analysis to filter out background interference. The extracted text is recognized using off-the-shelf optical character recognition (OCR) software products. The object type, orientation, location, and text information are presented to the blind traveler as speech.</AbstractText></Abstract><AuthorList><Author><LastName>Tian</LastName><ForeName>Yingli</ForeName><Initials>Y</Initials><AffiliationInfo><Affiliation>Electrical Engineering Department, The City College, and Graduate Center, City University of New York, New York, NY 10031.</Affiliation></AffiliationInfo></Author><Author><LastName>Yang</LastName><ForeName>Xiaodong</ForeName><Initials>X</Initials></Author><Author><LastName>Yi</LastName><ForeName>Chucai</ForeName><Initials>C</Initials></Author><Author><LastName>Arditi</LastName><ForeName>Aries</ForeName><Initials>A</Initials></Author></AuthorList><Language>ENG</Language><GrantList><Grant><GrantID>R21 EY020990</GrantID><Acronym>EY</Acronym><Agency>NEI NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>R21 EY020990-01</GrantID><Acronym>EY</Acronym><Agency>NEI NIH HHS</Agency><Country>United States</Country></Grant></GrantList><PublicationTypeList><PublicationType UI="">JOURNAL ARTICLE</PublicationType></PublicationTypeList></Article><MedlineJournalInfo><MedlineTA>Mach Vis Appl</MedlineTA><NlmUniqueID>101562623</NlmUniqueID><ISSNLinking>0932-8092</ISSNLinking></MedlineJournalInfo><KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">Indoor wayfinding</Keyword><Keyword MajorTopicYN="N">blind/visually impaired persons</Keyword><Keyword MajorTopicYN="N">computer vision</Keyword><Keyword MajorTopicYN="N">object detection</Keyword><Keyword MajorTopicYN="N">optical character recognition (OCR)</Keyword><Keyword MajorTopicYN="N">text extraction</Keyword></KeywordList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="entrez"><Year>2013</Year><Month>5</Month><Day>1</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2013</Year><Month>5</Month><Day>1</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2013</Year><Month>5</Month><Day>1</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>ppublish</PublicationStatus><ArticleIdList><ArticleId IdType="doi">10.1007/s00138-012-0431-7</ArticleId><ArticleId IdType="pubmed">23630409</ArticleId><ArticleId IdType="pmc">PMC3636776</ArticleId><ArticleId IdType="mid">NIHMS371367</ArticleId></ArticleIdList><pmc-dir>nihms</pmc-dir>
</PubmedData></pubmed></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000022 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000022 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= PubMed
|étape= Corpus
|type= RBID
|clé= pubmed:23630409
|texte= Toward a Computer Vision-based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:23630409" \
| HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a OcrV1
| This area was generated with Dilib version V0.6.32. |  |