{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/50380"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/50380","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Current and future trends in object detection","abstract":"The task of finding objects belonging to classes of interest in images has long been a focus of Computer Vision research. The ability to localize objects is useful in many applications: from self-driving cars, where it allows the car to detect pedestrians, bicyclists, road signs, and other vehicles, to security, where intruding persons can be detected. Though a lot of progress has been made since the conception of the field of Computer Vision more than five decades ago, as always, there is scope for further improvement. This is especially true in the case of object detection where a myriad of factors including variation in object instances through pose and appearance, along with other environmental factors such as the degree of occlusion, and lighting tend to cause failures. In this work we focus on improving object detection through the use of more representative features and better models. We propose new features that are not only more powerful, but also more robust and capture more information than the currently popular features. Further, we propose scalable models which can leverage large amounts of training data to improve performance.","abstract_html":"The task of finding objects belonging to classes of interest in images has long been a focus of Computer Vision research. The ability to localize objects is useful in many applications: from self-driving cars, where it allows the car to detect pedestrians, bicyclists, road signs, and other vehicles, to security, where intruding persons can be detected. Though a lot of progress has been made since the conception of the field of Computer Vision more than five decades ago, as always, there is scope for further improvement. This is especially true in the case of object detection where a myriad of factors including variation in object instances through pose and appearance, along with other environmental factors such as the degree of occlusion, and lighting tend to cause failures. In this work we focus on improving object detection through the use of more representative features and better models. We propose new features that are not only more powerful, but also more robust and capture more information than the currently popular features. Further, we propose scalable models which can leverage large amounts of training data to improve performance.","abstract_has_math":false,"creators":["Mallya, Arun"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Lazebnik, Svetlana"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-09-16T17:12:20Z","date_published":"2014-09-16T17:12:20Z","updated_at":"2026-07-22T22:25:40Z","subjects":["Computer Vision","Object Detection","life-long learning"],"languages":["en"],"rights":["Copyright 2014 Arun Mallya"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/50380","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lazebnik, Svetlana"]},{"key":"dc:creator","label":"Author","values":["Mallya, Arun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-09-16T17:12:20Z","2016-09-22T20:59:18Z","2014-08","2014-09-16"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"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":["Computer Vision","Object Detection","life-long learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2014 Arun Mallya"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/50380"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The task of finding objects belonging to classes of interest in images has long been a focus of Computer Vision research. The ability to localize objects is useful in many applications: from self-driving cars, where it allows the car to detect pedestrians, bicyclists, road signs, and other vehicles, to security, where intruding persons can be detected. Though a lot of progress has been made since the conception of the field of Computer Vision more than five decades ago, as always, there is scope for further improvement. This is especially true in the case of object detection where a myriad of factors including variation in object instances through pose and appearance, along with other environmental factors such as the degree of occlusion, and lighting tend to cause failures. In this work we focus on improving object detection through the use of more representative features and better models. We propose new features that are not only more powerful, but also more robust and capture more information than the currently popular features. Further, we propose scalable models which can leverage large amounts of training data to improve performance.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2014-07-14T15:22:14Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Mallya_Arun.pdf: 12895364 bytes, checksum: aeb50773df21ba9e5bedc343aa0568b3 (MD5)","Made available in DSpace on 2014-09-16T17:12:20Z (GMT). No. of bitstreams: 2 Arun_Mallya.pdf: 12895364 bytes, checksum: aeb50773df21ba9e5bedc343aa0568b3 (MD5) license.txt: 4061 bytes, checksum: 1fa7e8c5c6212b68bc954ab87bb5609f (MD5)","Embargo set by: Seth Robbins for item 50491 Lift date: 2016-09-16T17:13:01Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 50491 on 2016-09-22T20:59:18Z."]},{"key":"dc:title","label":"Title","values":["Current and future trends in object detection"]}]}],"canonical_facts":{"dc:contributor":["Lazebnik, Svetlana"],"dc:creator":["Mallya, Arun"],"dc:date":["2014-09-16T17:12:20Z","2016-09-22T20:59:18Z","2014-08","2014-09-16"],"dc:description":["The task of finding objects belonging to classes of interest in images has long been a focus of Computer Vision research. The ability to localize objects is useful in many applications: from self-driving cars, where it allows the car to detect pedestrians, bicyclists, road signs, and other vehicles, to security, where intruding persons can be detected. Though a lot of progress has been made since the conception of the field of Computer Vision more than five decades ago, as always, there is scope for further improvement. This is especially true in the case of object detection where a myriad of factors including variation in object instances through pose and appearance, along with other environmental factors such as the degree of occlusion, and lighting tend to cause failures. In this work we focus on improving object detection through the use of more representative features and better models. We propose new features that are not only more powerful, but also more robust and capture more information than the currently popular features. Further, we propose scalable models which can leverage large amounts of training data to improve performance.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2014-07-14T15:22:14Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Mallya_Arun.pdf: 12895364 bytes, checksum: aeb50773df21ba9e5bedc343aa0568b3 (MD5)","Made available in DSpace on 2014-09-16T17:12:20Z (GMT). No. of bitstreams: 2 Arun_Mallya.pdf: 12895364 bytes, checksum: aeb50773df21ba9e5bedc343aa0568b3 (MD5) license.txt: 4061 bytes, checksum: 1fa7e8c5c6212b68bc954ab87bb5609f (MD5)","Embargo set by: Seth Robbins for item 50491 Lift date: 2016-09-16T17:13:01Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 50491 on 2016-09-22T20:59:18Z."],"dc:identifier":["http://hdl.handle.net/2142/50380"],"dc:language":["en"],"dc:rights":["Copyright 2014 Arun Mallya"],"dc:subject":["Computer Vision","Object Detection","life-long learning"],"dc:title":["Current and future trends in object detection"],"dc:type":["text"],"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":"2026-07-22T22:25:40Z"}