{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/97546"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/97546","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"ArmTrak: tracking arm postures with a smartwatch","abstract":"We aim to track the 3D posture of the entire arm - both wrist and elbow - using the motion and magnetic sensors on smartwatches. We do not intend to employ machine learning to train the system on a specific set of gestures. Instead, we aim to trace the geometric motion of the arm, which can then be used as a generic platform for gesture-based applications. The problem is challenging because the arm posture is a function of both elbow and shoulder motions, whereas the watch is only a single point of (noisy) measurement from the wrist. Moreover, while other tracking systems (like indoor/outdoor localization) often benefit from maps or landmarks to occasionally reset their estimates, such opportunities are almost absent here. While this appears to be an under-constrained problem, we find that the pointing direction of the forearm is strongly coupled to the arm's posture. If the gyroscope and compass on the watch can be made to estimate this direction, the 3D search space can become smaller; the IMU sensors can then be applied to mitigate the remaining uncertainty. We leverage this observation to design ArmTrak, a system that fuses the IMU sensors and the anatomy of arm joints into a modified hidden Markov model (HMM) to continuously estimate state variables. Using Kinect 2.0 as ground truth, we achieve around 9.2 cm of median error for free-form postures; the errors increase to 13.3 cm for a real-time version. We believe this is a step forward in posture tracking, and with some additional work, could become a generic underlay to various practical applications.","abstract_html":"We aim to track the 3D posture of the entire arm - both wrist and elbow - using the motion and magnetic sensors on smartwatches. We do not intend to employ machine learning to train the system on a specific set of gestures. Instead, we aim to trace the geometric motion of the arm, which can then be used as a generic platform for gesture-based applications. The problem is challenging because the arm posture is a function of both elbow and shoulder motions, whereas the watch is only a single point of (noisy) measurement from the wrist. Moreover, while other tracking systems (like indoor/outdoor localization) often benefit from maps or landmarks to occasionally reset their estimates, such opportunities are almost absent here. While this appears to be an under-constrained problem, we find that the pointing direction of the forearm is strongly coupled to the arm's posture. If the gyroscope and compass on the watch can be made to estimate this direction, the 3D search space can become smaller; the IMU sensors can then be applied to mitigate the remaining uncertainty. We leverage this observation to design ArmTrak, a system that fuses the IMU sensors and the anatomy of arm joints into a modified hidden Markov model (HMM) to continuously estimate state variables. Using Kinect 2.0 as ground truth, we achieve around 9.2 cm of median error for free-form postures; the errors increase to 13.3 cm for a real-time version. We believe this is a step forward in posture tracking, and with some additional work, could become a generic underlay to various practical applications.","abstract_has_math":false,"creators":["Shen, Sheng"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Choudhury, Romit Roy"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-08-10T19:51:45Z","date_published":"2017-08-10T19:51:45Z","updated_at":"2026-07-22T22:24:34Z","subjects":["Gesture","Tracking","Smartwatch"],"languages":["en"],"rights":["Copyright 2017 Sheng Shen"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/97546","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Choudhury, Romit Roy"]},{"key":"dc:creator","label":"Author","values":["Shen, Sheng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2017-08-10T19:51:45Z","2019-08-11T09:15:16Z","2017-04-05","2017-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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":["Gesture","Tracking","Smartwatch"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2017 Sheng Shen"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/97546"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["We aim to track the 3D posture of the entire arm - both wrist and elbow - using the motion and magnetic sensors on smartwatches. We do not intend to employ machine learning to train the system on a specific set of gestures. Instead, we aim to trace the geometric motion of the arm, which can then be used as a generic platform for gesture-based applications. The problem is challenging because the arm posture is a function of both elbow and shoulder motions, whereas the watch is only a single point of (noisy) measurement from the wrist. Moreover, while other tracking systems (like indoor/outdoor localization) often benefit from maps or landmarks to occasionally reset their estimates, such opportunities are almost absent here. While this appears to be an under-constrained problem, we find that the pointing direction of the forearm is strongly coupled to the arm's posture. If the gyroscope and compass on the watch can be made to estimate this direction, the 3D search space can become smaller; the IMU sensors can then be applied to mitigate the remaining uncertainty. We leverage this observation to design ArmTrak, a system that fuses the IMU sensors and the anatomy of arm joints into a modified hidden Markov model (HMM) to continuously estimate state variables. Using Kinect 2.0 as ground truth, we achieve around 9.2 cm of median error for free-form postures; the errors increase to 13.3 cm for a real-time version. We believe this is a step forward in posture tracking, and with some additional work, could become a generic underlay to various practical applications.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2019-05-01","The student, Sheng Shen, accepted the attached license on 2017-04-05 at 00:53.","The student, Sheng Shen, submitted this Thesis for approval on 2017-04-05 at 01:04.","This Thesis was approved for publication on 2017-04-05 at 12:05.","DSpace SAF Submission Ingestion Package generated from Vireo submission #10649 on 2017-08-10 at 14:30:06","Made available in DSpace on 2017-08-10T19:51:45Z (GMT). No. of bitstreams: 2 SHEN-THESIS-2017.pdf: 3000266 bytes, checksum: c539db12229347eda0dcf6fa2a5b6a1b (MD5) LICENSE.txt: 4207 bytes, checksum: e60c9945bb1b425709b778a88a32c3b3 (MD5) Previous issue date: 2017-04-05","Embargo set by: Colleen Fallaw for item 102599 Lift date: 2019-08-10T21:25:30Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 102599 on 2019-08-11T09:15:16Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["ArmTrak: tracking arm postures with a smartwatch"]}]}],"canonical_facts":{"dc:contributor":["Choudhury, Romit Roy"],"dc:creator":["Shen, Sheng"],"dc:date":["2017-08-10T19:51:45Z","2019-08-11T09:15:16Z","2017-04-05","2017-05"],"dc:description":["We aim to track the 3D posture of the entire arm - both wrist and elbow - using the motion and magnetic sensors on smartwatches. We do not intend to employ machine learning to train the system on a specific set of gestures. Instead, we aim to trace the geometric motion of the arm, which can then be used as a generic platform for gesture-based applications. The problem is challenging because the arm posture is a function of both elbow and shoulder motions, whereas the watch is only a single point of (noisy) measurement from the wrist. Moreover, while other tracking systems (like indoor/outdoor localization) often benefit from maps or landmarks to occasionally reset their estimates, such opportunities are almost absent here. While this appears to be an under-constrained problem, we find that the pointing direction of the forearm is strongly coupled to the arm's posture. If the gyroscope and compass on the watch can be made to estimate this direction, the 3D search space can become smaller; the IMU sensors can then be applied to mitigate the remaining uncertainty. We leverage this observation to design ArmTrak, a system that fuses the IMU sensors and the anatomy of arm joints into a modified hidden Markov model (HMM) to continuously estimate state variables. Using Kinect 2.0 as ground truth, we achieve around 9.2 cm of median error for free-form postures; the errors increase to 13.3 cm for a real-time version. We believe this is a step forward in posture tracking, and with some additional work, could become a generic underlay to various practical applications.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2019-05-01","The student, Sheng Shen, accepted the attached license on 2017-04-05 at 00:53.","The student, Sheng Shen, submitted this Thesis for approval on 2017-04-05 at 01:04.","This Thesis was approved for publication on 2017-04-05 at 12:05.","DSpace SAF Submission Ingestion Package generated from Vireo submission #10649 on 2017-08-10 at 14:30:06","Made available in DSpace on 2017-08-10T19:51:45Z (GMT). No. of bitstreams: 2 SHEN-THESIS-2017.pdf: 3000266 bytes, checksum: c539db12229347eda0dcf6fa2a5b6a1b (MD5) LICENSE.txt: 4207 bytes, checksum: e60c9945bb1b425709b778a88a32c3b3 (MD5) Previous issue date: 2017-04-05","Embargo set by: Colleen Fallaw for item 102599 Lift date: 2019-08-10T21:25:30Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 102599 on 2019-08-11T09:15:16Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/97546"],"dc:language":["en"],"dc:rights":["Copyright 2017 Sheng Shen"],"dc:subject":["Gesture","Tracking","Smartwatch"],"dc:title":["ArmTrak: tracking arm postures with a smartwatch"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:34Z"}