{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-3284"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-3284","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Detection and recovery from camera bump during automated inspection of automobiles on an assembly line","abstract":"This thesis details the steps taken to detect and compensate for camera bumps while per- forming part identification using VI at the BMW manufacturing plant and on the simulation testbed. For the system presented here to work, the user is required to record a video from the camera before the camera is bumped and one after the camera has been bumped. The premise behind the method suggested here is that the transformation between the background in the pre- and post-bump video will be equal to the transformation in the foreground. A Background extraction program is used to generate a background image from the pre- and post-bump videos. Feature tracking and matching is performed on the background images to find the transformation between them. This transfor- mation is then applied to the templates extracted from the pre-bump video. An additional manual compensation step is needed in cases where the transformation in the background is not equal to the transformation in the foreground. The resultant transformation is applied to all the templates of the pre-bump video and VI is seen to successfully identify parts with sufficient accuracy.","abstract_html":"This thesis details the steps taken to detect and compensate for camera bumps while per- forming part identification using VI at the BMW manufacturing plant and on the simulation testbed. For the system presented here to work, the user is required to record a video from the camera before the camera is bumped and one after the camera has been bumped. The premise behind the method suggested here is that the transformation between the background in the pre- and post-bump video will be equal to the transformation in the foreground. A Background extraction program is used to generate a background image from the pre- and post-bump videos. Feature tracking and matching is performed on the background images to find the transformation between them. This transfor- mation is then applied to the templates extracted from the pre-bump video. An additional manual compensation step is needed in cases where the transformation in the background is not equal to the transformation in the foreground. The resultant transformation is applied to all the templates of the pre-bump video and VI is seen to successfully identify parts with sufficient accuracy.","abstract_has_math":false,"creators":["Mathew, Shawn"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Hoover, Adam","Smith, Melissa","Wang, Yongqiang"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:19Z","subjects":["Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/2279","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/2279","record_label":"Repository record","record_kind":"record","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://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-3284","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hoover, Adam","Smith, Melissa","Wang, Yongqiang"]},{"key":"dc:creator","label":"Author","values":["Mathew, Shawn"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2015-12-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/2279"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis details the steps taken to detect and compensate for camera bumps while per- forming part identification using VI at the BMW manufacturing plant and on the simulation testbed. For the system presented here to work, the user is required to record a video from the camera before the camera is bumped and one after the camera has been bumped. The premise behind the method suggested here is that the transformation between the background in the pre- and post-bump video will be equal to the transformation in the foreground. A Background extraction program is used to generate a background image from the pre- and post-bump videos. Feature tracking and matching is performed on the background images to find the transformation between them. This transfor- mation is then applied to the templates extracted from the pre-bump video. An additional manual compensation step is needed in cases where the transformation in the background is not equal to the transformation in the foreground. The resultant transformation is applied to all the templates of the pre-bump video and VI is seen to successfully identify parts with sufficient accuracy."]},{"key":"dc:title","label":"Title","values":["Detection and recovery from camera bump during automated inspection of automobiles on an assembly line"]}]}],"canonical_facts":{"dc:contributor":["Hoover, Adam","Smith, Melissa","Wang, Yongqiang"],"dc:creator":["Mathew, Shawn"],"dc:date.created":["2015-12-01T08:00:00Z"],"dc:description.abstract":["This thesis details the steps taken to detect and compensate for camera bumps while per- forming part identification using VI at the BMW manufacturing plant and on the simulation testbed. For the system presented here to work, the user is required to record a video from the camera before the camera is bumped and one after the camera has been bumped. The premise behind the method suggested here is that the transformation between the background in the pre- and post-bump video will be equal to the transformation in the foreground. A Background extraction program is used to generate a background image from the pre- and post-bump videos. Feature tracking and matching is performed on the background images to find the transformation between them. This transfor- mation is then applied to the templates extracted from the pre-bump video. An additional manual compensation step is needed in cases where the transformation in the background is not equal to the transformation in the foreground. The resultant transformation is applied to all the templates of the pre-bump video and VI is seen to successfully identify parts with sufficient accuracy."],"dc:identifier":["https://open.clemson.edu/all_theses/2279"],"dc:subject":["Electrical and Computer Engineering"],"dc:title":["Detection and recovery from camera bump during automated inspection of automobiles on an assembly line"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:12:19Z"}