< Back to list

SemanticTraj: a new approach to interacting with massive taxi trajectories

journalArticle

DOI:10.1109/TVCG.2016.2598416
🔗 Source 🖨️ PDF
Authors: Al-Dohuki Shamal / Wu Yingyu / Kamw Farah / Yang Jing / Li Xin / Zhao Ye / Ye Xinyue / Chen Wei / Ma Chao / Wang Fei

Extracted Abstract:

—Massivetaxitrajectorydataisexploitedforknowledgediscoveryintransportationandurbanplanning.Existingtools typicallyrequireuserstoselectandbrushgeospatialregionsonamapwhenretrievingandexploringtaxitrajectoriesandpassenger trips.Toanswerseeminglysimplequestionssuchas“WhatwerethetaxitripsstartingfromMainStreetandendingatWallStreet inthemorning?”or“WherearethetaxisarrivingattheArtMuseumatnoontypicallycomingfrom?”,tediousandtimeconsuming interactionsareusuallyneededsincethenumericGPSpointsoftrajectoriesarenotdirectlylinkedtothekeywordssuchas“Main Street”,“WallStreet”,and“ArtMuseum”.Inthispaper,wepresentSemanticTraj,anewmethodformanagingandvisualizingtaxi trajectorydatainanintuitive,semanticrich,andefficientmeans.WithSemanticTraj,domainandpublicuserscanfindanswersto theaforementionedquestionseasilythroughdirectqueriesbasedontheterms.Theycanalsointeractivelyexploretheretrieveddata invisualizationsenhancedbysemanticinformationofthetrajectoriesandtrips.Inparticular,taxitrajectoriesareconvertedintotaxi documentsthroughatextualizationtransformationprocess.ThisprocessmapsGPSpointsintoaseriesofstreet/POInamesand pick-up/drop-offlocations.Italsoconvertsvehiclespeedsintouser-defineddescriptiveterms.Then,acorpusoftaxidocuments isformedandindexedtoenableflexiblesemanticqueriesoveratextsearchengine.Semanticlabelsandmeta-summariesofthe resultsareintegratedwithasetofvisualizationsinaSemanticTrajprototype,whichhelpsusersstudytaxitrajectoriesquicklyand easily.Asetofusagescenariosarepresentedtoshowtheusabilityofthesystem.Wealsocollectedfeedbackfromdomainexperts andconductedapreliminaryuserstudytoevaluatethevisualsystem. IndexTerms —TaxiTrajectories,TaxiDocument,Textualization,NameQuery,SemanticInteraction,TextSearchEngine 1

Level 1: Include/Exclude

  • Papers must discuss situated information visualization* (by Willet et al.) in the application domain of CH.
    *A situated data representation is a data representation whose physical presentation is located close to the data’s physical referent(s).
    *A situated visualization is a situated data representation for which the presentation is purely visual – and is typically displayed on a screen.
  • Representation must include abstract data (e.g., metadata).
  • Papers focused solely on digital reconstruction without information visualization aspects are excluded.
  • Posters and workshop papers are excluded to focus on mature research contributions.
Show all meta-data