{"id":{"repo_id":"unt","oai_identifier":"info:ark/67531/metadc801901"},"canonical_url":"https://search.ndltd.org/etd/unt/info:ark/67531/metadc801901","repository":{"repo_id":"unt","name":"University of North Texas","base_url":"https://digital.library.unt.edu/oai/"},"display":{"title":"Classifying Pairwise Object Interactions: A Trajectory Analytics Approach","abstract":"We have a huge amount of video data from extensively available surveillance cameras and increasingly growing technology to record the motion of a moving object in the form of trajectory data. With proliferation of location-enabled devices and ongoing growth in smartphone penetration as well as advancements in exploiting image processing techniques, tracking moving objects is more flawlessly achievable. In this work, we explore some domain-independent qualitative and quantitative features in raw trajectory (spatio-temporal) data in videos captured by a fixed single wide-angle view camera sensor in outdoor areas. We study the efficacy of those features in classifying four basic high level actions by employing two supervised learning algorithms and show how each of the features affect the learning algorithms’ overall accuracy as a single factor or confounded with others.","abstract_html":"We have a huge amount of video data from extensively available surveillance cameras and increasingly growing technology to record the motion of a moving object in the form of trajectory data. With proliferation of location-enabled devices and ongoing growth in smartphone penetration as well as advancements in exploiting image processing techniques, tracking moving objects is more flawlessly achievable. In this work, we explore some domain-independent qualitative and quantitative features in raw trajectory (spatio-temporal) data in videos captured by a fixed single wide-angle view camera sensor in outdoor areas. We study the efficacy of those features in classifying four basic high level actions by employing two supervised learning algorithms and show how each of the features affect the learning algorithms’ overall accuracy as a single factor or confounded with others.","abstract_has_math":false,"creators":["Janmohammadi, Siamak"],"institution":"University of North Texas","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Buckles, Bill P., 1942-","Huang, Yan","Namuduri, Kamesh"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-05","date_published":"2015-05","updated_at":"2026-11-19T08:54:28Z","subjects":["action recognition","machine learning","trajectory analysis","supervised classification methods","activity recognition","Human activity recognition.","Pattern recognition systems.","Machine learning.","Electronic surveillance."],"languages":["English"],"rights":["Public","Janmohammadi, Siamak","Copyright","Copyright is held by the author, unless otherwise noted. All rights reserved."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digital.library.unt.edu/ark:/67531/metadc801901/","ark: ark:/67531/metadc801901"],"render_values":[{"text":"https://digital.library.unt.edu/ark:/67531/metadc801901/","href":"https://digital.library.unt.edu/ark:/67531/metadc801901/","code":true},{"text":"ark: ark:/67531/metadc801901","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.12794/metadc801901","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.12794/metadc801901","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digital.library.unt.edu/oai/?verb=GetRecord&metadataPrefix=oai_dc&identifier=info%3Aark%2F67531%2Fmetadc801901","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Buckles, Bill P., 1942-","Huang, Yan","Namuduri, Kamesh"]},{"key":"dc:creator","label":"Author","values":["Janmohammadi, Siamak"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-05"]},{"key":"dc:publisher","label":"Institution","values":["University of North Texas"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["action recognition","machine learning","trajectory analysis","supervised classification methods","activity recognition","Human activity recognition.","Pattern recognition systems.","Machine learning.","Electronic surveillance."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["Public","Janmohammadi, Siamak","Copyright","Copyright is held by the author, unless otherwise noted. All rights reserved."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["doi: 10.12794/metadc801901","https://digital.library.unt.edu/ark:/67531/metadc801901/","ark: ark:/67531/metadc801901"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["We have a huge amount of video data from extensively available surveillance cameras and increasingly growing technology to record the motion of a moving object in the form of trajectory data. With proliferation of location-enabled devices and ongoing growth in smartphone penetration as well as advancements in exploiting image processing techniques, tracking moving objects is more flawlessly achievable. In this work, we explore some domain-independent qualitative and quantitative features in raw trajectory (spatio-temporal) data in videos captured by a fixed single wide-angle view camera sensor in outdoor areas. We study the efficacy of those features in classifying four basic high level actions by employing two supervised learning algorithms and show how each of the features affect the learning algorithms’ overall accuracy as a single factor or confounded with others."]},{"key":"dc:format","label":"Dc Format","values":["vii, 27 pages : illustrations (some color)","Text"]},{"key":"dc:title","label":"Title","values":["Classifying Pairwise Object Interactions: A Trajectory Analytics Approach"]}]}],"canonical_facts":{"dc:contributor":["Buckles, Bill P., 1942-","Huang, Yan","Namuduri, Kamesh"],"dc:creator":["Janmohammadi, Siamak"],"dc:date":["2015-05"],"dc:description":["We have a huge amount of video data from extensively available surveillance cameras and increasingly growing technology to record the motion of a moving object in the form of trajectory data. With proliferation of location-enabled devices and ongoing growth in smartphone penetration as well as advancements in exploiting image processing techniques, tracking moving objects is more flawlessly achievable. In this work, we explore some domain-independent qualitative and quantitative features in raw trajectory (spatio-temporal) data in videos captured by a fixed single wide-angle view camera sensor in outdoor areas. We study the efficacy of those features in classifying four basic high level actions by employing two supervised learning algorithms and show how each of the features affect the learning algorithms’ overall accuracy as a single factor or confounded with others."],"dc:format":["vii, 27 pages : illustrations (some color)","Text"],"dc:identifier":["doi: 10.12794/metadc801901","https://digital.library.unt.edu/ark:/67531/metadc801901/","ark: ark:/67531/metadc801901"],"dc:language":["English"],"dc:publisher":["University of North Texas"],"dc:rights":["Public","Janmohammadi, Siamak","Copyright","Copyright is held by the author, unless otherwise noted. All rights reserved."],"dc:subject":["action recognition","machine learning","trajectory analysis","supervised classification methods","activity recognition","Human activity recognition.","Pattern recognition systems.","Machine learning.","Electronic surveillance."],"dc:title":["Classifying Pairwise Object Interactions: A Trajectory Analytics Approach"],"dc:type":["Thesis or Dissertation"]},"updated_at":"2026-11-19T08:54:28Z"}