{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/155914"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/155914","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Using Markerless Motion Capture and Principal Component Analysis to Classify BMX Freestyle Tricks","abstract":"This thesis presents a novel Bicycle Motocross (BMX) Freestyle (FS) trick classification technique developed for the Australian Cycling Team. The first step is tracking six key points on the athlete and their bike using DeepLabCut, an opensource markerless motion capture software. Next, a Principal Component Analysis (PCA) is applied to the tracking data to calculate metrics to identify each trick type. Finally, a classifier is trained to learn these metrics. The dataset used in this paper focused on three common BMX Freestyle tricks: 360, backflip, and flair. The Logistic Regression model achieved the highest accuracy among the classifiers, correctly predicting the trick for 94.2% of the instances. This thesis discusses other ways to apply this data, such as novel trick generation. It also examines the robustness and cost benefit trade off of the classifier.","abstract_html":"This thesis presents a novel Bicycle Motocross (BMX) Freestyle (FS) trick classification technique developed for the Australian Cycling Team. The first step is tracking six key points on the athlete and their bike using DeepLabCut, an opensource markerless motion capture software. Next, a Principal Component Analysis (PCA) is applied to the tracking data to calculate metrics to identify each trick type. Finally, a classifier is trained to learn these metrics. The dataset used in this paper focused on three common BMX Freestyle tricks: 360, backflip, and flair. The Logistic Regression model achieved the highest accuracy among the classifiers, correctly predicting the trick for 94.2% of the instances. This thesis discusses other ways to apply this data, such as novel trick generation. It also examines the robustness and cost benefit trade off of the classifier.","abstract_has_math":false,"creators":["Nates, Eva"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Mechanical Engineering","school":null,"contributors":[],"advisors":["Hosoi, Anette \"Peko\""],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:20:54Z","subjects":[],"languages":[],"rights":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"],"rights_urls":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/155914","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Hosoi, Anette \"Peko\""]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Mechanical Engineering"]},{"key":"dc:creator","label":"Author","values":["Nates, Eva"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-08-01T19:07:10Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-08-01T19:07:10Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Mechanical Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/155914"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis presents a novel Bicycle Motocross (BMX) Freestyle (FS) trick classification technique developed for the Australian Cycling Team. The first step is tracking six key points on the athlete and their bike using DeepLabCut, an opensource markerless motion capture software. Next, a Principal Component Analysis (PCA) is applied to the tracking data to calculate metrics to identify each trick type. Finally, a classifier is trained to learn these metrics. The dataset used in this paper focused on three common BMX Freestyle tricks: 360, backflip, and flair. The Logistic Regression model achieved the highest accuracy among the classifiers, correctly predicting the trick for 94.2% of the instances. This thesis discusses other ways to apply this data, such as novel trick generation. It also examines the robustness and cost benefit trade off of the classifier."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Using Markerless Motion Capture and Principal Component Analysis to Classify BMX Freestyle Tricks"]}]}],"canonical_facts":{"dc:contributor.advisor":["Hosoi, Anette \"Peko\""],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Mechanical Engineering"],"dc:creator":["Nates, Eva"],"dc:date.accessioned":["2024-08-01T19:07:10Z"],"dc:date.available":["2024-08-01T19:07:10Z"],"dc:date.issued":["2024-05"],"dc:description.abstract":["This thesis presents a novel Bicycle Motocross (BMX) Freestyle (FS) trick classification technique developed for the Australian Cycling Team. The first step is tracking six key points on the athlete and their bike using DeepLabCut, an opensource markerless motion capture software. Next, a Principal Component Analysis (PCA) is applied to the tracking data to calculate metrics to identify each trick type. Finally, a classifier is trained to learn these metrics. The dataset used in this paper focused on three common BMX Freestyle tricks: 360, backflip, and flair. The Logistic Regression model achieved the highest accuracy among the classifiers, correctly predicting the trick for 94.2% of the instances. This thesis discusses other ways to apply this data, such as novel trick generation. It also examines the robustness and cost benefit trade off of the classifier."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/155914"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"],"dc:rights.uri":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:title":["Using Markerless Motion Capture and Principal Component Analysis to Classify BMX Freestyle Tricks"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Mechanical Engineering"]},"updated_at":"2026-07-22T22:20:54Z"}