{"id":{"repo_id":"sdstate","oai_identifier":"oai:openprairie.sdstate.edu:etd-4669"},"canonical_url":"https://search.ndltd.org/etd/sdstate/oai:openprairie.sdstate.edu:etd-4669","repository":{"repo_id":"sdstate","name":"South Dakota State University","base_url":"https://openprairie.sdstate.edu/do/oai/"},"display":{"title":"Instance Segmentation and Object Detection in Road Scenes using Inverse Perspective Mapping of 3D Point Clouds and 2D Images","abstract":"The instance segmentation and object detection are important tasks in smart car applications. Recently, a variety of neural network-based approaches have been proposed. One of the challenges is that there are various scales of objects in a scene, and it requires the neural network to have a large receptive field to deal with the scale variations. In other words, the neural network must have deep architectures which slow down computation. In smart car applications, the accuracy of detection and segmentation of vehicle and pedestrian is hugely critical. Besides, 2D images do not have distance information but enough visual appearance. On the other hand, 3D point clouds have strong evidence of existence of objects. The fusion of 2D images and 3D point clouds can provide more information to seek out objects in a scene. This paper proposes a series of fronto-parallel virtual planes and inverse perspective mapping of an input image to the planes, to deal with scale variations. I use 3D point clouds obtained from LiDAR sensor and 2D images obtained from stereo cameras on top of a vehicle to estimate the ground area of the scene and to define virtual planes. Certain height from the ground area in 2D images is cropped to focus on objects on flat roads. Then, the point cloud is used to filter out false-alarms among the over-detection results generated by an off-the-shelf deep neural network, Mask RCNN. The experimental result showed that the proposed approach outperforms Mask RCNN without pre-processing on a benchmark dataset, KITTI dataset [9].","abstract_html":"The instance segmentation and object detection are important tasks in smart car applications. Recently, a variety of neural network-based approaches have been proposed. One of the challenges is that there are various scales of objects in a scene, and it requires the neural network to have a large receptive field to deal with the scale variations. In other words, the neural network must have deep architectures which slow down computation. In smart car applications, the accuracy of detection and segmentation of vehicle and pedestrian is hugely critical. Besides, 2D images do not have distance information but enough visual appearance. On the other hand, 3D point clouds have strong evidence of existence of objects. The fusion of 2D images and 3D point clouds can provide more information to seek out objects in a scene. This paper proposes a series of fronto-parallel virtual planes and inverse perspective mapping of an input image to the planes, to deal with scale variations. I use 3D point clouds obtained from LiDAR sensor and 2D images obtained from stereo cameras on top of a vehicle to estimate the ground area of the scene and to define virtual planes. Certain height from the ground area in 2D images is cropped to focus on objects on flat roads. Then, the point cloud is used to filter out false-alarms among the over-detection results generated by an off-the-shelf deep neural network, Mask RCNN. The experimental result showed that the proposed approach outperforms Mask RCNN without pre-processing on a benchmark dataset, KITTI dataset [9].","abstract_has_math":false,"creators":["Lee, Chungyup"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis - Open Access","degree_discipline":"Electrical Engineering and Computer Science","degree_department":null,"school":null,"contributors":["Kwanghee Won"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:00:17Z","subjects":["Computer Engineering","Computer Sciences"],"languages":["en"],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://openprairie.sdstate.edu/etd/3661","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://openprairie.sdstate.edu/etd/3661","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://openprairie.sdstate.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopenprairie.sdstate.edu%3Aetd-4669","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kwanghee Won"]},{"key":"dc:creator","label":"Author","values":["Lee, Chungyup"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-12-05T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2019-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering and Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Engineering","Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://openprairie.sdstate.edu/etd/3661"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The instance segmentation and object detection are important tasks in smart car applications. Recently, a variety of neural network-based approaches have been proposed. One of the challenges is that there are various scales of objects in a scene, and it requires the neural network to have a large receptive field to deal with the scale variations. In other words, the neural network must have deep architectures which slow down computation. In smart car applications, the accuracy of detection and segmentation of vehicle and pedestrian is hugely critical. Besides, 2D images do not have distance information but enough visual appearance. On the other hand, 3D point clouds have strong evidence of existence of objects. The fusion of 2D images and 3D point clouds can provide more information to seek out objects in a scene. This paper proposes a series of fronto-parallel virtual planes and inverse perspective mapping of an input image to the planes, to deal with scale variations. I use 3D point clouds obtained from LiDAR sensor and 2D images obtained from stereo cameras on top of a vehicle to estimate the ground area of the scene and to define virtual planes. Certain height from the ground area in 2D images is cropped to focus on objects on flat roads. Then, the point cloud is used to filter out false-alarms among the over-detection results generated by an off-the-shelf deep neural network, Mask RCNN. The experimental result showed that the proposed approach outperforms Mask RCNN without pre-processing on a benchmark dataset, KITTI dataset [9]."]},{"key":"dc:title","label":"Title","values":["Instance Segmentation and Object Detection in Road Scenes using Inverse Perspective Mapping of 3D Point Clouds and 2D Images"]}]}],"canonical_facts":{"dc:contributor":["Kwanghee Won"],"dc:creator":["Lee, Chungyup"],"dc:date.available":["2019-12-05T08:00:00Z"],"dc:date.created":["2019-01-01T08:00:00Z"],"dc:description.abstract":["The instance segmentation and object detection are important tasks in smart car applications. Recently, a variety of neural network-based approaches have been proposed. One of the challenges is that there are various scales of objects in a scene, and it requires the neural network to have a large receptive field to deal with the scale variations. In other words, the neural network must have deep architectures which slow down computation. In smart car applications, the accuracy of detection and segmentation of vehicle and pedestrian is hugely critical. Besides, 2D images do not have distance information but enough visual appearance. On the other hand, 3D point clouds have strong evidence of existence of objects. The fusion of 2D images and 3D point clouds can provide more information to seek out objects in a scene. This paper proposes a series of fronto-parallel virtual planes and inverse perspective mapping of an input image to the planes, to deal with scale variations. I use 3D point clouds obtained from LiDAR sensor and 2D images obtained from stereo cameras on top of a vehicle to estimate the ground area of the scene and to define virtual planes. Certain height from the ground area in 2D images is cropped to focus on objects on flat roads. Then, the point cloud is used to filter out false-alarms among the over-detection results generated by an off-the-shelf deep neural network, Mask RCNN. The experimental result showed that the proposed approach outperforms Mask RCNN without pre-processing on a benchmark dataset, KITTI dataset [9]."],"dc:identifier":["https://openprairie.sdstate.edu/etd/3661"],"dc:language":["en"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Computer Engineering","Computer Sciences"],"dc:title":["Instance Segmentation and Object Detection in Road Scenes using Inverse Perspective Mapping of 3D Point Clouds and 2D Images"],"thesis:degree_discipline":["Electrical Engineering and Computer Science"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T09:00:17Z"}