{"id":{"repo_id":"ets-quebec","oai_identifier":"oai:espace.etsmtl.ca:3698"},"canonical_url":"https://search.ndltd.org/etd/ets-quebec/oai:espace.etsmtl.ca:3698","repository":{"repo_id":"ets-quebec","name":"ETS (Quebec)","base_url":"https://espace.etsmtl.ca/cgi/oai2"},"display":{"title":"Direct estimation of the knee flexion angle from a monocular image during walking","abstract":"The recent use of deep learning techniques in biomechanical applications has opened new avenues for non-invasive image-based motion capture and assessment. With the growing importance of deep learning-based computer vision models, the healthcare innovation company Emovi aims to replace KneeKG-based MoCap Marker-based methods with markerless-based strategies to estimate and assess certain anatomical landmarks of the lower limbs. This thesis proposes a novel deep regression model built with a ResNet backbone enhanced with feature map constraints to directly estimate lower limb anatomical landmarks, specifically knee flexion angles; by enforcing spatial consistency through internal feature map supervision; from monocular RGB images of defined functional movement sequences. A dataset was collected in a controlled laboratory environment using the KneeKG system, which provides clinically validated kinematic reference data. Unlike prior methods that rely on multi-view setups or complex marker-based systems, this work introduces an approach to infer knee joint angles from a RGB image. This works also introduces image inpainting strategies to help with a more focused model training. Quantitative evaluations demonstrate a test mean absolute error of 2.4◦ in flexion angle estimation, indicating a potential use for clinical applications where cost-effective and accessible motion analysis tools are needed.","abstract_html":"The recent use of deep learning techniques in biomechanical applications has opened new avenues for non-invasive image-based motion capture and assessment. With the growing importance of deep learning-based computer vision models, the healthcare innovation company Emovi aims to replace KneeKG-based MoCap Marker-based methods with markerless-based strategies to estimate and assess certain anatomical landmarks of the lower limbs. This thesis proposes a novel deep regression model built with a ResNet backbone enhanced with feature map constraints to directly estimate lower limb anatomical landmarks, specifically knee flexion angles; by enforcing spatial consistency through internal feature map supervision; from monocular RGB images of defined functional movement sequences. A dataset was collected in a controlled laboratory environment using the KneeKG system, which provides clinically validated kinematic reference data. Unlike prior methods that rely on multi-view setups or complex marker-based systems, this work introduces an approach to infer knee joint angles from a RGB image. This works also introduces image inpainting strategies to help with a more focused model training. Quantitative evaluations demonstrate a test mean absolute error of 2.4◦ in flexion angle estimation, indicating a potential use for clinical applications where cost-effective and accessible motion analysis tools are needed.","abstract_has_math":false,"creators":["Fakhfakh, Anis"],"institution":"École de technologie supérieure","degree_name":"Mémoire de maîtrise électronique","degree_level":"masters","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-08-18","date_published":"2025-08-18","updated_at":"2026-11-18T22:10:50Z","subjects":["vision par ordinateur, apprentissage profond, MoCap, flexion, KneeKG, cartes de caractéristiques, inpainting d’image"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["INSERT-YOUR-LIBRARY-ID-HERE3698"],"render_values":[{"text":"INSERT-YOUR-LIBRARY-ID-HERE3698","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null,"record_url":null,"record_label":null,"record_kind":null,"record_source":null,"download_url":"https://espace.etsmtl.ca/id/eprint/3698/1/Fakhfakh_Anis.pdf","download_label":"Download PDF","download_source":"dc:identifier","access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://espace.etsmtl.ca/cgi/oai2?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aespace.etsmtl.ca%3A3698","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Fakhfakh, Anis"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-08-18"]},{"key":"dc:publisher","label":"Institution","values":["École de technologie supérieure"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Mémoire de maîtrise électronique"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["École de technologie supérieure"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["vision par ordinateur, apprentissage profond, MoCap, flexion, KneeKG, cartes de caractéristiques, inpainting d’image"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["INSERT-YOUR-LIBRARY-ID-HERE3698","https://espace.etsmtl.ca/id/eprint/3698/1/Fakhfakh_Anis.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The recent use of deep learning techniques in biomechanical applications has opened new avenues for non-invasive image-based motion capture and assessment. With the growing importance of deep learning-based computer vision models, the healthcare innovation company Emovi aims to replace KneeKG-based MoCap Marker-based methods with markerless-based strategies to estimate and assess certain anatomical landmarks of the lower limbs. This thesis proposes a novel deep regression model built with a ResNet backbone enhanced with feature map constraints to directly estimate lower limb anatomical landmarks, specifically knee flexion angles; by enforcing spatial consistency through internal feature map supervision; from monocular RGB images of defined functional movement sequences. A dataset was collected in a controlled laboratory environment using the KneeKG system, which provides clinically validated kinematic reference data. Unlike prior methods that rely on multi-view setups or complex marker-based systems, this work introduces an approach to infer knee joint angles from a RGB image. This works also introduces image inpainting strategies to help with a more focused model training. Quantitative evaluations demonstrate a test mean absolute error of 2.4◦ in flexion angle estimation, indicating a potential use for clinical applications where cost-effective and accessible motion analysis tools are needed."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Direct estimation of the knee flexion angle from a monocular image during walking"]}]}],"canonical_facts":{"dc:creator":["Fakhfakh, Anis"],"dc:date":["2025-08-18"],"dc:description":["The recent use of deep learning techniques in biomechanical applications has opened new avenues for non-invasive image-based motion capture and assessment. With the growing importance of deep learning-based computer vision models, the healthcare innovation company Emovi aims to replace KneeKG-based MoCap Marker-based methods with markerless-based strategies to estimate and assess certain anatomical landmarks of the lower limbs. This thesis proposes a novel deep regression model built with a ResNet backbone enhanced with feature map constraints to directly estimate lower limb anatomical landmarks, specifically knee flexion angles; by enforcing spatial consistency through internal feature map supervision; from monocular RGB images of defined functional movement sequences. A dataset was collected in a controlled laboratory environment using the KneeKG system, which provides clinically validated kinematic reference data. Unlike prior methods that rely on multi-view setups or complex marker-based systems, this work introduces an approach to infer knee joint angles from a RGB image. This works also introduces image inpainting strategies to help with a more focused model training. Quantitative evaluations demonstrate a test mean absolute error of 2.4◦ in flexion angle estimation, indicating a potential use for clinical applications where cost-effective and accessible motion analysis tools are needed."],"dc:format":["application/pdf"],"dc:identifier":["INSERT-YOUR-LIBRARY-ID-HERE3698","https://espace.etsmtl.ca/id/eprint/3698/1/Fakhfakh_Anis.pdf"],"dc:language":["en"],"dc:publisher":["École de technologie supérieure"],"dc:subject":["vision par ordinateur, apprentissage profond, MoCap, flexion, KneeKG, cartes de caractéristiques, inpainting d’image"],"dc:title":["Direct estimation of the knee flexion angle from a monocular image during walking"],"dc:type":["Electronic Thesis or Dissertation"],"thesis:degree_level":["masters"],"thesis:degree_name":["Mémoire de maîtrise électronique"],"thesis:institution_name":["École de technologie supérieure"]},"updated_at":"2026-11-18T22:10:50Z"}