Acquisition of a Large Pose-Mosaic Dataset
We describe the generation of a large pose-mosaic dataset: a collection of several thousand digital images, grouped by spatial position into spherical mosaics, each annotated with estimates of the acquiring camera's 6 DOF pose (3 DOF position and 3 DOF orientation) in an absolute coordinate sys...
Main Authors: | , , |
---|---|
Published: |
2023
|
Online Access: | https://hdl.handle.net/1721.1/149271 |
_version_ | 1811073713393631232 |
---|---|
author | Coorg, Satyan Master, Neel Teller, Seth |
author_facet | Coorg, Satyan Master, Neel Teller, Seth |
author_sort | Coorg, Satyan |
collection | MIT |
description | We describe the generation of a large pose-mosaic dataset: a collection of several thousand digital images, grouped by spatial position into spherical mosaics, each annotated with estimates of the acquiring camera's 6 DOF pose (3 DOF position and 3 DOF orientation) in an absolute coordinate system. The pose-mosaic dataset was generated by acquiring images, grouped by spatial position into nodes (essentially, spherical mosaics). A prototype mechanical pan-tilt head was manually deployed to acquire the data. Manual surverying provided initial position estimates for each node. A back-projecting scheme provided initial rotational estimates. Relative rotations within each node, along with internal camera parameters, were refined automatically by an optimization-correlation scheme. Relative translations and rotations among nodes were refined according to point correspondences, generated automatically and by a human operator. The resulting pose-imagery is self-consistent under a variety of evaluation metrics. Pose-mosaics are useful "first-class" data objects, for example in automatic reconstruction of textured 3D CAD models which represent urban exteriors. |
first_indexed | 2024-09-23T09:37:26Z |
id | mit-1721.1/149271 |
institution | Massachusetts Institute of Technology |
last_indexed | 2024-09-23T09:37:26Z |
publishDate | 2023 |
record_format | dspace |
spelling | mit-1721.1/1492712023-03-30T04:10:01Z Acquisition of a Large Pose-Mosaic Dataset Coorg, Satyan Master, Neel Teller, Seth We describe the generation of a large pose-mosaic dataset: a collection of several thousand digital images, grouped by spatial position into spherical mosaics, each annotated with estimates of the acquiring camera's 6 DOF pose (3 DOF position and 3 DOF orientation) in an absolute coordinate system. The pose-mosaic dataset was generated by acquiring images, grouped by spatial position into nodes (essentially, spherical mosaics). A prototype mechanical pan-tilt head was manually deployed to acquire the data. Manual surverying provided initial position estimates for each node. A back-projecting scheme provided initial rotational estimates. Relative rotations within each node, along with internal camera parameters, were refined automatically by an optimization-correlation scheme. Relative translations and rotations among nodes were refined according to point correspondences, generated automatically and by a human operator. The resulting pose-imagery is self-consistent under a variety of evaluation metrics. Pose-mosaics are useful "first-class" data objects, for example in automatic reconstruction of textured 3D CAD models which represent urban exteriors. 2023-03-29T14:40:31Z 2023-03-29T14:40:31Z 1998-01 https://hdl.handle.net/1721.1/149271 MIT-LCS-TM-568 application/pdf |
spellingShingle | Coorg, Satyan Master, Neel Teller, Seth Acquisition of a Large Pose-Mosaic Dataset |
title | Acquisition of a Large Pose-Mosaic Dataset |
title_full | Acquisition of a Large Pose-Mosaic Dataset |
title_fullStr | Acquisition of a Large Pose-Mosaic Dataset |
title_full_unstemmed | Acquisition of a Large Pose-Mosaic Dataset |
title_short | Acquisition of a Large Pose-Mosaic Dataset |
title_sort | acquisition of a large pose mosaic dataset |
url | https://hdl.handle.net/1721.1/149271 |
work_keys_str_mv | AT coorgsatyan acquisitionofalargeposemosaicdataset AT masterneel acquisitionofalargeposemosaicdataset AT tellerseth acquisitionofalargeposemosaicdataset |