{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/32351"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/32351","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Improved Radar Data Clustering for Extended Target Tracking with Camera Fusion and Micro-Doppler Effect","abstract":"High-resolution automotive radars widely used nowadays yield multiple measurements per frame from a single target, which contrasts with the point target assumption in most tracking algorithms. Clustering radar detections based on their sources is a crucial step for subsequent tracking. It will significantly impact the environmental perception capability of autonomous driving systems, which in turn affects their overall performance. However, accurate clustering is challenging in complex automotive driving scenarios with miss detections, false alarms and clutter. Many clustering methods have been proposed for this topic in the literature. In this thesis, an improved DBSCAN with range-adaptive extended criteria is first presented to reduce clustering error. Based on this, we further developed a camera-assisted clustering method to enhance the clustering process with target class and bounding box information from camera data. This method also addresses several issues in radar-camera fusion, including object occlusion and partial visibility, uncertainty in radar measurements, overlapping bounding boxes, and coverage discrepancy between radar and camera. In addition, the effect of micro-Doppler motion has been ignored in most Doppler-assisted clustering algorithms, which may introduce significant splitting errors. In this thesis, the distribution of micro-Doppler measurements is formulated to predict the possible measurements from the tires. A two-step iterative clustering approach is first proposed to reduce the splitting error caused by the micro-Doppler effect in Doppler-assisted clustering, but its computational time is significant. Therefore, another clustering approach with tire position and range rate probability constraint is developed accordingly, which improves clustering accuracy and significantly reduces computational time compared with the two-step iterative method.","abstract_html":"High-resolution automotive radars widely used nowadays yield multiple measurements per frame from a single target, which contrasts with the point target assumption in most tracking algorithms. Clustering radar detections based on their sources is a crucial step for subsequent tracking. It will significantly impact the environmental perception capability of autonomous driving systems, which in turn affects their overall performance. However, accurate clustering is challenging in complex automotive driving scenarios with miss detections, false alarms and clutter. Many clustering methods have been proposed for this topic in the literature. In this thesis, an improved DBSCAN with range-adaptive extended criteria is first presented to reduce clustering error. Based on this, we further developed a camera-assisted clustering method to enhance the clustering process with target class and bounding box information from camera data. This method also addresses several issues in radar-camera fusion, including object occlusion and partial visibility, uncertainty in radar measurements, overlapping bounding boxes, and coverage discrepancy between radar and camera. In addition, the effect of micro-Doppler motion has been ignored in most Doppler-assisted clustering algorithms, which may introduce significant splitting errors. In this thesis, the distribution of micro-Doppler measurements is formulated to predict the possible measurements from the tires. A two-step iterative clustering approach is first proposed to reduce the splitting error caused by the micro-Doppler effect in Doppler-assisted clustering, but its computational time is significant. Therefore, another clustering approach with tire position and range rate probability constraint is developed accordingly, which improves clustering accuracy and significantly reduces computational time compared with the two-step iterative method.","abstract_has_math":false,"creators":["Zeng, Jing Jr"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":["Tharmarasa, Ratnasingham Jr"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-11-19T05:57:29Z","subjects":["Autonomous driving","micro-Doppler","extended target","radar data clustering","tire position estimation","Clustering","autonomous vehicle","radar data","sensor fusion","camera data"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/14447"],"render_values":[{"text":"https://doi.org/10.71548/14447","href":"https://doi.org/10.71548/14447","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/32351","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/32351","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F32351","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Tharmarasa, Ratnasingham Jr"]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Zeng, Jing Jr"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-23T13:58:42Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-23T13:58:42Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Autonomous driving","micro-Doppler","extended target","radar data clustering","tire position estimation","Clustering","autonomous vehicle","radar data","sensor fusion","camera data"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11375/32351","https://doi.org/10.71548/14447"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["High-resolution automotive radars widely used nowadays yield multiple measurements per frame from a single target, which contrasts with the point target assumption in most tracking algorithms. Clustering radar detections based on their sources is a crucial step for subsequent tracking. It will significantly impact the environmental perception capability of autonomous driving systems, which in turn affects their overall performance. However, accurate clustering is challenging in complex automotive driving scenarios with miss detections, false alarms and clutter. Many clustering methods have been proposed for this topic in the literature. In this thesis, an improved DBSCAN with range-adaptive extended criteria is first presented to reduce clustering error. Based on this, we further developed a camera-assisted clustering method to enhance the clustering process with target class and bounding box information from camera data. This method also addresses several issues in radar-camera fusion, including object occlusion and partial visibility, uncertainty in radar measurements, overlapping bounding boxes, and coverage discrepancy between radar and camera. In addition, the effect of micro-Doppler motion has been ignored in most Doppler-assisted clustering algorithms, which may introduce significant splitting errors. In this thesis, the distribution of micro-Doppler measurements is formulated to predict the possible measurements from the tires. A two-step iterative clustering approach is first proposed to reduce the splitting error caused by the micro-Doppler effect in Doppler-assisted clustering, but its computational time is significant. Therefore, another clustering approach with tire position and range rate probability constraint is developed accordingly, which improves clustering accuracy and significantly reduces computational time compared with the two-step iterative method."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Nowadays, high-resolution radars provide multiple measurements for each target. Correctly clustering radar measurements based on their source is essential for better autonomous driving performance. In this thesis, we propose several algorithms to enhance clustering progress by utilizing different kinds of information in radar detections, combining images from the camera, and considering different velocity measurements from tires. These methods could improve object detection accuracy in various driving scenarios, thereby effectively avoiding collisions."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Applied Science (MASc)"]},{"key":"dc:title","label":"Title","values":["Improved Radar Data Clustering for Extended Target Tracking with Camera Fusion and Micro-Doppler Effect"]},{"key":"dc:title.alternative","label":"Alternative Title","values":["Improved Radar Data Clustering"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Tharmarasa, Ratnasingham Jr"],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["Zeng, Jing Jr"],"dc:date.accessioned":["2025-09-23T13:58:42Z"],"dc:date.available":["2025-09-23T13:58:42Z"],"dc:date.issued":["2025"],"dc:description.abstract":["High-resolution automotive radars widely used nowadays yield multiple measurements per frame from a single target, which contrasts with the point target assumption in most tracking algorithms. Clustering radar detections based on their sources is a crucial step for subsequent tracking. It will significantly impact the environmental perception capability of autonomous driving systems, which in turn affects their overall performance. However, accurate clustering is challenging in complex automotive driving scenarios with miss detections, false alarms and clutter. Many clustering methods have been proposed for this topic in the literature. In this thesis, an improved DBSCAN with range-adaptive extended criteria is first presented to reduce clustering error. Based on this, we further developed a camera-assisted clustering method to enhance the clustering process with target class and bounding box information from camera data. This method also addresses several issues in radar-camera fusion, including object occlusion and partial visibility, uncertainty in radar measurements, overlapping bounding boxes, and coverage discrepancy between radar and camera. In addition, the effect of micro-Doppler motion has been ignored in most Doppler-assisted clustering algorithms, which may introduce significant splitting errors. In this thesis, the distribution of micro-Doppler measurements is formulated to predict the possible measurements from the tires. A two-step iterative clustering approach is first proposed to reduce the splitting error caused by the micro-Doppler effect in Doppler-assisted clustering, but its computational time is significant. Therefore, another clustering approach with tire position and range rate probability constraint is developed accordingly, which improves clustering accuracy and significantly reduces computational time compared with the two-step iterative method."],"dc:description.abstractgeneral":["Nowadays, high-resolution radars provide multiple measurements for each target. Correctly clustering radar measurements based on their source is essential for better autonomous driving performance. In this thesis, we propose several algorithms to enhance clustering progress by utilizing different kinds of information in radar detections, combining images from the camera, and considering different velocity measurements from tires. These methods could improve object detection accuracy in various driving scenarios, thereby effectively avoiding collisions."],"dc:description.degree":["Master of Applied Science (MASc)"],"dc:identifier.uri":["http://hdl.handle.net/11375/32351","https://doi.org/10.71548/14447"],"dc:language.iso":["en"],"dc:subject":["Autonomous driving","micro-Doppler","extended target","radar data clustering","tire position estimation","Clustering","autonomous vehicle","radar data","sensor fusion","camera data"],"dc:title":["Improved Radar Data Clustering for Extended Target Tracking with Camera Fusion and Micro-Doppler Effect"],"dc:title.alternative":["Improved Radar Data Clustering"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-19T05:57:29Z"}