{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108028"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108028","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Autonomous vehicles that understand road agents: Detection, tracking, and behavior prediction","abstract":"Object detection, object tracking and behavior prediction are three fundamental problems towards human-level road agent understanding. In this thesis, we introduce a joint object detection and tracking model for real-time autonomous driving applications. Comparison with two state-of-the-art models on a research dataset shows that our model has the best detection performance and comparable tracking performance. We implement our algorithm on a real autonomous driving vehicle and conduct public road test to prove the robustness and reliability of our system. We further explore the task of vehicle behavior prediction for high-level understanding of road agents. We introduce the Fusion Seq2Seq model and compare it with two other baseline models. Experiments on a driver behavior dataset shows that our model can reasonably predict ego-vehicle actions.","abstract_html":"Object detection, object tracking and behavior prediction are three fundamental problems towards human-level road agent understanding. In this thesis, we introduce a joint object detection and tracking model for real-time autonomous driving applications. Comparison with two state-of-the-art models on a research dataset shows that our model has the best detection performance and comparable tracking performance. We implement our algorithm on a real autonomous driving vehicle and conduct public road test to prove the robustness and reliability of our system. We further explore the task of vehicle behavior prediction for high-level understanding of road agents. We introduce the Fusion Seq2Seq model and compare it with two other baseline models. Experiments on a driver behavior dataset shows that our model can reasonably predict ego-vehicle actions.","abstract_has_math":false,"creators":["Xu, Ke"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Driggs-Campbell, Katherine Rose"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-26T21:58:00Z","date_published":"2020-08-26T21:58:00Z","updated_at":"2026-07-22T22:24:47Z","subjects":["autonomous vehicles","detection","tracking","behavior prediction","driver behavior"],"languages":["en"],"rights":["Copyright 2020 Ke Xu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108028","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Driggs-Campbell, Katherine Rose"]},{"key":"dc:creator","label":"Author","values":["Xu, Ke"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-26T21:58:00Z","2020-05-12","2020-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["autonomous vehicles","detection","tracking","behavior prediction","driver behavior"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Ke Xu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108028"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Object detection, object tracking and behavior prediction are three fundamental problems towards human-level road agent understanding. In this thesis, we introduce a joint object detection and tracking model for real-time autonomous driving applications. Comparison with two state-of-the-art models on a research dataset shows that our model has the best detection performance and comparable tracking performance. We implement our algorithm on a real autonomous driving vehicle and conduct public road test to prove the robustness and reliability of our system. We further explore the task of vehicle behavior prediction for high-level understanding of road agents. We introduce the Fusion Seq2Seq model and compare it with two other baseline models. Experiments on a driver behavior dataset shows that our model can reasonably predict ego-vehicle actions.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Ke Xu, accepted the attached license on 2020-05-10 at 12:42.","The student, Ke Xu, submitted this Thesis for approval on 2020-05-10 at 12:49.","This Thesis was approved for publication on 2020-05-12 at 10:22.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15312 on 2020-08-25 at 17:13:44","Made available in DSpace on 2020-08-26T21:58:00Z (GMT). No. of bitstreams: 2 XU-THESIS-2020.pdf: 15706943 bytes, checksum: 360aec1cb71122e01babd17ff7300b08 (MD5) LICENSE.txt: 4202 bytes, checksum: 7d0958108ec049f2dd531889372b5c80 (MD5) Previous issue date: 2020-05-12"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Autonomous vehicles that understand road agents: Detection, tracking, and behavior prediction"]}]}],"canonical_facts":{"dc:contributor":["Driggs-Campbell, Katherine Rose"],"dc:creator":["Xu, Ke"],"dc:date":["2020-08-26T21:58:00Z","2020-05-12","2020-05"],"dc:description":["Object detection, object tracking and behavior prediction are three fundamental problems towards human-level road agent understanding. In this thesis, we introduce a joint object detection and tracking model for real-time autonomous driving applications. Comparison with two state-of-the-art models on a research dataset shows that our model has the best detection performance and comparable tracking performance. We implement our algorithm on a real autonomous driving vehicle and conduct public road test to prove the robustness and reliability of our system. We further explore the task of vehicle behavior prediction for high-level understanding of road agents. We introduce the Fusion Seq2Seq model and compare it with two other baseline models. Experiments on a driver behavior dataset shows that our model can reasonably predict ego-vehicle actions.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Ke Xu, accepted the attached license on 2020-05-10 at 12:42.","The student, Ke Xu, submitted this Thesis for approval on 2020-05-10 at 12:49.","This Thesis was approved for publication on 2020-05-12 at 10:22.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15312 on 2020-08-25 at 17:13:44","Made available in DSpace on 2020-08-26T21:58:00Z (GMT). No. of bitstreams: 2 XU-THESIS-2020.pdf: 15706943 bytes, checksum: 360aec1cb71122e01babd17ff7300b08 (MD5) LICENSE.txt: 4202 bytes, checksum: 7d0958108ec049f2dd531889372b5c80 (MD5) Previous issue date: 2020-05-12"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108028"],"dc:language":["en"],"dc:rights":["Copyright 2020 Ke Xu"],"dc:subject":["autonomous vehicles","detection","tracking","behavior prediction","driver behavior"],"dc:title":["Autonomous vehicles that understand road agents: Detection, tracking, and behavior prediction"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:47Z"}