Image-based querying of urban knowledge databases
We extend recent automated computer vision algorithms to reconstruct the global three-dimensional structures for photos and videos shot at fixed points in outdoor city environments. Mosaics of digital stills and embedded videos are georegistered by matching a few of their 2D features with 3D counter...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
The International Society for Optical Engineering
2010
|
| Online Access: | http://hdl.handle.net/1721.1/52662 https://orcid.org/0000-0001-9919-069X |
| _version_ | 1826200714580328448 |
|---|---|
| author | Bae, Soonmin Cho, Peter L. Durand, Fredo |
| author2 | Lincoln Laboratory |
| author_facet | Lincoln Laboratory Bae, Soonmin Cho, Peter L. Durand, Fredo |
| author_sort | Bae, Soonmin |
| collection | MIT |
| description | We extend recent automated computer vision algorithms to reconstruct the global three-dimensional structures for photos and videos shot at fixed points in outdoor city environments. Mosaics of digital stills and embedded videos are georegistered by matching a few of their 2D features with 3D counterparts in aerial ladar imagery. Once image planes are aligned with world maps, abstract urban knowledge can propagate from the latter into the former. We project geotagged annotations from a 3D map into a 2D video stream and demonstrate their tracking buildings and streets in a clip with significant panning motion. We also present an interactive tool which enables users to select city features of interest in video frames and retrieve their geocoordinates and ranges. Implications of this work for future augmented reality systems based upon mobile smart phones are discussed. |
| first_indexed | 2024-09-23T11:40:42Z |
| format | Article |
| id | mit-1721.1/52662 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:40:42Z |
| publishDate | 2010 |
| publisher | The International Society for Optical Engineering |
| record_format | dspace |
| spelling | mit-1721.1/526622022-10-01T05:11:52Z Image-based querying of urban knowledge databases Bae, Soonmin Cho, Peter L. Durand, Fredo Lincoln Laboratory Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Durand, Fredo Bae, Soonmin Cho, Peter L. Durand, Fredo We extend recent automated computer vision algorithms to reconstruct the global three-dimensional structures for photos and videos shot at fixed points in outdoor city environments. Mosaics of digital stills and embedded videos are georegistered by matching a few of their 2D features with 3D counterparts in aerial ladar imagery. Once image planes are aligned with world maps, abstract urban knowledge can propagate from the latter into the former. We project geotagged annotations from a 3D map into a 2D video stream and demonstrate their tracking buildings and streets in a clip with significant panning motion. We also present an interactive tool which enables users to select city features of interest in video frames and retrieve their geocoordinates and ranges. Implications of this work for future augmented reality systems based upon mobile smart phones are discussed. Departmwent of the Air Force (Air Force Contract No. FA8721-05-C-0002) 2010-03-17T16:04:58Z 2010-03-17T16:04:58Z 2009-05 Article http://purl.org/eprint/type/JournalArticle 0277-786X http://hdl.handle.net/1721.1/52662 Cho, Peter, Soonmin Bae, and Fredo Durand. “Image-based querying of urban knowledge databases.” Signal Processing, Sensor Fusion, and Target Recognition XVIII. Ed. Ivan Kadar. Orlando, FL, USA: SPIE, 2009. 733614-12. © 2009 SPIE--The International Society for Optical Engineering https://orcid.org/0000-0001-9919-069X en_US http://dx.doi.org/10.1117/12.818164 Proceedings of SPIE Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf The International Society for Optical Engineering SPIE |
| spellingShingle | Bae, Soonmin Cho, Peter L. Durand, Fredo Image-based querying of urban knowledge databases |
| title | Image-based querying of urban knowledge databases |
| title_full | Image-based querying of urban knowledge databases |
| title_fullStr | Image-based querying of urban knowledge databases |
| title_full_unstemmed | Image-based querying of urban knowledge databases |
| title_short | Image-based querying of urban knowledge databases |
| title_sort | image based querying of urban knowledge databases |
| url | http://hdl.handle.net/1721.1/52662 https://orcid.org/0000-0001-9919-069X |
| work_keys_str_mv | AT baesoonmin imagebasedqueryingofurbanknowledgedatabases AT chopeterl imagebasedqueryingofurbanknowledgedatabases AT durandfredo imagebasedqueryingofurbanknowledgedatabases |