{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/1673"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/1673","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"Intention prediction of pedestrians in challenging weather conditions using deep learning","abstract":"Assisted and automated driving vehicles have received massive attention over the past few years from the research community to make our roads safer. In this thesis, we introduce a framework for predicting the intention of pedestrians in clear and challenging weather conditions. The framework consists of five deep-learning models, of which two are designed and trained from scratch and three were used pretrained. The framework takes video frames from the dashcam and inputs them to an enhancement pipeline to determine the quality of the images and enhance them if necessary. Then, the framework utilizes pretrained models (MoveNet, Deep-sort, and Deep-Labv3) for feature extraction. Lastly, all the features are fed into a Transformer-based Intention Prediction Model (TIPM) for pedestrian intention prediction. Results show that TIPM outperforms state-of-the-art models yielding an accuracy of 69% on the JAAD behavior dataset, 82% on the JAAD all dataset.","abstract_html":"Assisted and automated driving vehicles have received massive attention over the past few years from the research community to make our roads safer. In this thesis, we introduce a framework for predicting the intention of pedestrians in clear and challenging weather conditions. The framework consists of five deep-learning models, of which two are designed and trained from scratch and three were used pretrained. The framework takes video frames from the dashcam and inputs them to an enhancement pipeline to determine the quality of the images and enhance them if necessary. Then, the framework utilizes pretrained models (MoveNet, Deep-sort, and Deep-Labv3) for feature extraction. Lastly, all the features are fed into a Transformer-based Intention Prediction Model (TIPM) for pedestrian intention prediction. Results show that TIPM outperforms state-of-the-art models yielding an accuracy of 69% on the JAAD behavior dataset, 82% on the JAAD all dataset.","abstract_has_math":false,"creators":["Elgazwy, Ahmed"],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Applied Science (MASc)","degree_level":null,"degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Elgazzar, Khalid","Khamis, Alaa"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-08-01","date_published":"2023-08-01","updated_at":"2026-07-24T05:35:26Z","subjects":["Deep-learning","Transformers","Image-enhancement","Vision transformer","Intention prediction"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/1673","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Elgazzar, Khalid","Khamis, Alaa"]},{"key":"dc:creator","label":"Author","values":["Elgazwy, Ahmed"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-08-29T14:29:54Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-08-29T14:29:54Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-08-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Applied Science (MASc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep-learning","Transformers","Image-enhancement","Vision transformer","Intention prediction"]}]},{"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":["https://hdl.handle.net/10155/1673"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Assisted and automated driving vehicles have received massive attention over the past few years from the research community to make our roads safer. In this thesis, we introduce a framework for predicting the intention of pedestrians in clear and challenging weather conditions. The framework consists of five deep-learning models, of which two are designed and trained from scratch and three were used pretrained. The framework takes video frames from the dashcam and inputs them to an enhancement pipeline to determine the quality of the images and enhance them if necessary. Then, the framework utilizes pretrained models (MoveNet, Deep-sort, and Deep-Labv3) for feature extraction. Lastly, all the features are fed into a Transformer-based Intention Prediction Model (TIPM) for pedestrian intention prediction. Results show that TIPM outperforms state-of-the-art models yielding an accuracy of 69% on the JAAD behavior dataset, 82% on the JAAD all dataset."]},{"key":"dc:title","label":"Title","values":["Intention prediction of pedestrians in challenging weather conditions using deep learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Elgazzar, Khalid","Khamis, Alaa"],"dc:creator":["Elgazwy, Ahmed"],"dc:date.accessioned":["2023-08-29T14:29:54Z"],"dc:date.available":["2023-08-29T14:29:54Z"],"dc:date.issued":["2023-08-01"],"dc:description.abstract":["Assisted and automated driving vehicles have received massive attention over the past few years from the research community to make our roads safer. In this thesis, we introduce a framework for predicting the intention of pedestrians in clear and challenging weather conditions. The framework consists of five deep-learning models, of which two are designed and trained from scratch and three were used pretrained. The framework takes video frames from the dashcam and inputs them to an enhancement pipeline to determine the quality of the images and enhance them if necessary. Then, the framework utilizes pretrained models (MoveNet, Deep-sort, and Deep-Labv3) for feature extraction. Lastly, all the features are fed into a Transformer-based Intention Prediction Model (TIPM) for pedestrian intention prediction. Results show that TIPM outperforms state-of-the-art models yielding an accuracy of 69% on the JAAD behavior dataset, 82% on the JAAD all dataset."],"dc:identifier.uri":["https://hdl.handle.net/10155/1673"],"dc:language.iso":["en"],"dc:subject":["Deep-learning","Transformers","Image-enhancement","Vision transformer","Intention prediction"],"dc:title":["Intention prediction of pedestrians in challenging weather conditions using deep learning"],"dc:type":["Thesis"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_name":["Master of Applied Science (MASc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:26Z"}