| dc.date.accessioned | 2006-01-10T18:51:59Z | |
| dc.date.accessioned | 2018-11-24T10:24:43Z | |
| dc.date.available | 2006-01-10T18:51:59Z | |
| dc.date.available | 2018-11-24T10:24:43Z | |
| dc.date.issued | 2006-01-09 | |
| dc.identifier.uri | http://hdl.handle.net/1721.1/30605 | |
| dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/30605 | |
| dc.description.abstract | We describe an algorithm that takes as inputs a coarse3D model of an environment, and a video sequence acquiredwithin the environment, and produces as output an estimateof the camera s 6-DOF egomotion expressed in the coordinatesof the 3D model. Our method has several novelaspects: it performs line-based structure-from-motion; italigns the local line constellation to the known model; andit uses off-line visibility analysis to dramatically acceleratethe alignment process.We present simulation results demonstrating themethod s operation in a multi-room environment. We showthat the method can estimate metric egomotion accuratelyand could be used for for many minutes of operation andthousands of video frames. | |
| dc.format.extent | 8 p. | |
| dc.format.extent | 20452907 bytes | |
| dc.format.extent | 718869 bytes | |
| dc.language.iso | en_US | |
| dc.subject | computer vision,visual geometry,omnivision,3D | |
| dc.title | Wide-Area Egomotion Estimation from Known 3D Structure | |
