The problem of degeneracy in structure and motion recovery from uncalibrated image sequences
The aim of this work is the recovery of 3D structure and camera projection matrices for each frame of an uncalibrated image sequence. In order to achieve this, correspondences are required throughout the sequence. A significant and successful mechanism for automatically establishing these correspond...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
1999
|
| _version_ | 1826315157775581184 |
|---|---|
| author | Torr, PHS Fitzgibbon, AW Zisserman, A |
| author_facet | Torr, PHS Fitzgibbon, AW Zisserman, A |
| author_sort | Torr, PHS |
| collection | OXFORD |
| description | The aim of this work is the recovery of 3D structure and camera projection matrices for each frame of an uncalibrated image sequence. In order to achieve this, correspondences are required throughout the sequence. A significant and successful mechanism for automatically establishing these correspondences is by the use of geometric constraints arising from scene rigidity. However, problems arise with such geometry guided matching if general viewpoint and general structure are assumed whilst frames in the sequence and/or scene structure do not conform to these assumptions. Such cases are termed degenerate. In this paper we describe two important cases of degeneracy and their effects on geometry guided matching. The cases are a motion degeneracy where the camera does not translate between frames, and a structure degeneracy where the viewed scene structure is planar. The effects include the loss of correspondences due to under or over fitting of geometric models estimated from image data, leading to the failure of the tracking method. These degeneracies are not a theoretical curiosity, but commonly occur in real sequences where models are statistically estimated from image points with measurement error. We investigate two strategies for tackling such degeneracies: the first uses a statistical model selection test to identify when degeneracies occur; the second uses multiple motion models to overcome the degeneracies. The strategies are evaluated on real sequences varying in motion, scene type, and length from 13 to 120 frames. |
| first_indexed | 2024-12-09T03:20:37Z |
| format | Conference item |
| id | oxford-uuid:b2abf4ad-059a-487f-a90e-976efe6b6726 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:20:37Z |
| publishDate | 1999 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:b2abf4ad-059a-487f-a90e-976efe6b67262024-11-05T14:17:42ZThe problem of degeneracy in structure and motion recovery from uncalibrated image sequencesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:b2abf4ad-059a-487f-a90e-976efe6b6726EnglishSymplectic ElementsSpringer1999Torr, PHSFitzgibbon, AWZisserman, AThe aim of this work is the recovery of 3D structure and camera projection matrices for each frame of an uncalibrated image sequence. In order to achieve this, correspondences are required throughout the sequence. A significant and successful mechanism for automatically establishing these correspondences is by the use of geometric constraints arising from scene rigidity. However, problems arise with such geometry guided matching if general viewpoint and general structure are assumed whilst frames in the sequence and/or scene structure do not conform to these assumptions. Such cases are termed degenerate. In this paper we describe two important cases of degeneracy and their effects on geometry guided matching. The cases are a motion degeneracy where the camera does not translate between frames, and a structure degeneracy where the viewed scene structure is planar. The effects include the loss of correspondences due to under or over fitting of geometric models estimated from image data, leading to the failure of the tracking method. These degeneracies are not a theoretical curiosity, but commonly occur in real sequences where models are statistically estimated from image points with measurement error. We investigate two strategies for tackling such degeneracies: the first uses a statistical model selection test to identify when degeneracies occur; the second uses multiple motion models to overcome the degeneracies. The strategies are evaluated on real sequences varying in motion, scene type, and length from 13 to 120 frames. |
| spellingShingle | Torr, PHS Fitzgibbon, AW Zisserman, A The problem of degeneracy in structure and motion recovery from uncalibrated image sequences |
| title | The problem of degeneracy in structure and motion recovery from uncalibrated image sequences |
| title_full | The problem of degeneracy in structure and motion recovery from uncalibrated image sequences |
| title_fullStr | The problem of degeneracy in structure and motion recovery from uncalibrated image sequences |
| title_full_unstemmed | The problem of degeneracy in structure and motion recovery from uncalibrated image sequences |
| title_short | The problem of degeneracy in structure and motion recovery from uncalibrated image sequences |
| title_sort | problem of degeneracy in structure and motion recovery from uncalibrated image sequences |
| work_keys_str_mv | AT torrphs theproblemofdegeneracyinstructureandmotionrecoveryfromuncalibratedimagesequences AT fitzgibbonaw theproblemofdegeneracyinstructureandmotionrecoveryfromuncalibratedimagesequences AT zissermana theproblemofdegeneracyinstructureandmotionrecoveryfromuncalibratedimagesequences AT torrphs problemofdegeneracyinstructureandmotionrecoveryfromuncalibratedimagesequences AT fitzgibbonaw problemofdegeneracyinstructureandmotionrecoveryfromuncalibratedimagesequences AT zissermana problemofdegeneracyinstructureandmotionrecoveryfromuncalibratedimagesequences |