File Download
  Links for fulltext
     (May Require Subscription)

Article: Big Data-Driven Pedestrian Analytics: Unsupervised Clustering and Relational Query Based on Tencent Street View Photographs

TitleBig Data-Driven Pedestrian Analytics: Unsupervised Clustering and Relational Query Based on Tencent Street View Photographs
Authors
Keywordsurban informatics
big data
pedestrian activity
streetscape
Tencent street view (TSV)
Issue Date2021
PublisherMDPI AG. The Journal's web site is located at http://www.mdpi.com/journal/ijgi
Citation
ISPRS International Journal of Geo-Information, 2021, v. 10 n. 8, p. article no. 561 How to Cite?
AbstractRecent technological advancements in geomatics and mobile sensing have led to various urban big data, such as Tencent street view (TSV) photographs; yet, the urban objects in the big dataset have hitherto been inadequately exploited. This paper aims to propose a pedestrian analytics approach named vectors of uncountable and countable objects for clustering and analysis (VUCCA) for processing 530,000 TSV photographs of Hong Kong Island. First, VUCCA transductively adopts two pre-trained deep models to TSV photographs for extracting pedestrians and surrounding pixels into generalizable semantic vectors of features, including uncountable objects such as vegetation, sky, paved pedestrian path, and guardrail and countable objects such as cars, trucks, pedestrians, city animals, and traffic lights. Then, the extracted pedestrians are semantically clustered using the vectors, e.g., for understanding where they usually stand. Third, pedestrians are semantically indexed using relations and activities (e.g., walking behind a guardrail, road-crossing, carrying a backpack, or walking a pet) for queries of unstructured photographic instances or natural language clauses. The experiment results showed that the pedestrians detected in the TSV photographs were successfully clustered into meaningful groups and indexed by the semantic vectors. The presented VUCCA can enrich eye-level urban features into computational semantic vectors for pedestrians to enable smart city research in urban geography, urban planning, real estate, transportation, conservation, and other disciplines.
Persistent Identifierhttp://hdl.handle.net/10722/302030
ISSN
2018 Impact Factor: 1.84
2020 SCImago Journal Rankings: 0.684

 

DC FieldValueLanguage
dc.contributor.authorXue, F-
dc.contributor.authorLi, X-
dc.contributor.authorLu, W-
dc.contributor.authorWebster, CJ-
dc.contributor.authorChen, Z-
dc.contributor.authorLin, L-
dc.date.accessioned2021-08-21T03:30:33Z-
dc.date.available2021-08-21T03:30:33Z-
dc.date.issued2021-
dc.identifier.citationISPRS International Journal of Geo-Information, 2021, v. 10 n. 8, p. article no. 561-
dc.identifier.issn2220-9964-
dc.identifier.urihttp://hdl.handle.net/10722/302030-
dc.description.abstractRecent technological advancements in geomatics and mobile sensing have led to various urban big data, such as Tencent street view (TSV) photographs; yet, the urban objects in the big dataset have hitherto been inadequately exploited. This paper aims to propose a pedestrian analytics approach named vectors of uncountable and countable objects for clustering and analysis (VUCCA) for processing 530,000 TSV photographs of Hong Kong Island. First, VUCCA transductively adopts two pre-trained deep models to TSV photographs for extracting pedestrians and surrounding pixels into generalizable semantic vectors of features, including uncountable objects such as vegetation, sky, paved pedestrian path, and guardrail and countable objects such as cars, trucks, pedestrians, city animals, and traffic lights. Then, the extracted pedestrians are semantically clustered using the vectors, e.g., for understanding where they usually stand. Third, pedestrians are semantically indexed using relations and activities (e.g., walking behind a guardrail, road-crossing, carrying a backpack, or walking a pet) for queries of unstructured photographic instances or natural language clauses. The experiment results showed that the pedestrians detected in the TSV photographs were successfully clustered into meaningful groups and indexed by the semantic vectors. The presented VUCCA can enrich eye-level urban features into computational semantic vectors for pedestrians to enable smart city research in urban geography, urban planning, real estate, transportation, conservation, and other disciplines.-
dc.languageeng-
dc.publisherMDPI AG. The Journal's web site is located at http://www.mdpi.com/journal/ijgi-
dc.relation.ispartofISPRS International Journal of Geo-Information-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjecturban informatics-
dc.subjectbig data-
dc.subjectpedestrian activity-
dc.subjectstreetscape-
dc.subjectTencent street view (TSV)-
dc.titleBig Data-Driven Pedestrian Analytics: Unsupervised Clustering and Relational Query Based on Tencent Street View Photographs-
dc.typeArticle-
dc.identifier.emailXue, F: xuef@hku.hk-
dc.identifier.emailLi, X: xl1991@hku.hk-
dc.identifier.emailLu, W: wilsonlu@hku.hk-
dc.identifier.emailWebster, CJ: cwebster@hku.hk-
dc.identifier.emailChen, Z: chenzhe@hku.hk-
dc.identifier.authorityXue, F=rp02189-
dc.identifier.authorityLu, W=rp01362-
dc.identifier.authorityWebster, CJ=rp01747-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.3390/ijgi10080561-
dc.identifier.hkuros324565-
dc.identifier.volume10-
dc.identifier.issue8-
dc.identifier.spagearticle no. 561-
dc.identifier.epagearticle no. 561-
dc.publisher.placeSwitzerland-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats