Symmetry-based monocular 3D vehicle ground-truthing for traffic analytics

Simple item page
dc.contributor.advisorJames Elder
dc.contributor.authorTrong Thao Tran
dc.date.accessioned2024-11-07T11:14:26Z
dc.date.available2024-11-07T11:14:26Z
dc.date.copyright2024-09-03
dc.date.issued2024-11-07
dc.date.updated2024-11-07T11:14:24Z
dc.degree.disciplineComputer Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstract3D object detection is critical for autonomous driving and traffic analytics. Current research relies on LiDAR-derived ground truth for training and evaluation. However, LiDAR ground truth is expensive and usually inaccurate in the far field due to sparse LiDAR returns. Assuming a fully calibrated camera and a 3D terrain model, we explore whether inexpensive RGB imagery can be used to obtain 3D ground truth based on the bilateral symmetry of motor vehicles. From manually annotated symmetry points and tire-ground contact points, we infer a vertical symmetry plane and 3D point cloud to estimate vehicle location, pose, and dimensions. These estimates are input into a probabilistic model derived from a standard public motor vehicle dataset to form maximum a posteriori estimates of remaining dimensions. Evaluations on a public traffic dataset show that this novel symmetry-based approach is more accurate than LiDAR-based ground-truthing on single frames and comparable to LiDAR-based methods that propagate information across frames.
dc.identifier.urihttps://hdl.handle.net/10315/42488
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subject.keywords3D vehicle ground truthing
dc.subject.keywords3D object detection
dc.subject.keywordsautonomous driving
dc.subject.keywordstraffic analytics
dc.subject.keywordsLiDAR limitations
dc.subject.keywordsRGB imagery
dc.subject.keywordsvehicle symmetry
dc.subject.keywordspose estimation
dc.subject.keywordsprobabilistic modeling
dc.subject.keywordssymmetry-based approach
dc.subject.keywordsvehicle dimensions
dc.subject.keywords3D from a single image
dc.subject.keywordssingle-image 3D reconstruction
dc.subject.keywords3D feature learning
dc.subject.keywordsdataset creation
dc.titleSymmetry-based monocular 3D vehicle ground-truthing for traffic analytics
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Tran_TrongThao_2024_Masters.pdf
Size:
47.86 MB
Format:
Adobe Portable Document Format
Download

Collections

ETD SWORD Deposit

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.