Object level grouping for video shots
<p>We describe a method for automatically associating image patches from frames of a movie shot into object-level groups. The method employs both the appearance and motion of the patches.</p> <p>There are two areas of innovation: first, affine invariant regions are used to repair s...
| Autori principali: | , , |
|---|---|
| Natura: | Conference item |
| Lingua: | English |
| Pubblicazione: |
Springer
2004
|
| _version_ | 1826317143677861888 |
|---|---|
| author | Sivic, J Schaffalitzky, F Zisserman, A |
| author_facet | Sivic, J Schaffalitzky, F Zisserman, A |
| author_sort | Sivic, J |
| collection | OXFORD |
| description | <p>We describe a method for automatically associating image patches from frames of a movie shot into object-level groups. The method employs both the appearance and motion of the patches.</p>
<p>There are two areas of innovation: first, affine invariant regions are used to repair short gaps in individual tracks and also to join sets of tracks across occlusions (where many tracks are lost simultaneously); second, a robust affine factorization method is developed which is able to cope with motion degeneracy. This factorization is used to associate tracks into object-level groups.</p>
<p>The outcome is that separate parts of an object that are never visible simultaneously in a single frame are associated together. For example, the front and back of a car, or the front and side of a face. In turn this enables object-level matching and recognition throughout a video.</p>
<p>We illustrate the method for a number of shots from the feature film ‘Groundhog Day’.</p> |
| first_indexed | 2025-02-19T04:33:51Z |
| format | Conference item |
| id | oxford-uuid:df6247d4-4bc2-43fa-a2ac-02e07a9ab24e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:33:51Z |
| publishDate | 2004 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:df6247d4-4bc2-43fa-a2ac-02e07a9ab24e2025-01-20T14:38:50ZObject level grouping for video shotsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:df6247d4-4bc2-43fa-a2ac-02e07a9ab24eEnglishSymplectic ElementsSpringer2004Sivic, JSchaffalitzky, FZisserman, A<p>We describe a method for automatically associating image patches from frames of a movie shot into object-level groups. The method employs both the appearance and motion of the patches.</p> <p>There are two areas of innovation: first, affine invariant regions are used to repair short gaps in individual tracks and also to join sets of tracks across occlusions (where many tracks are lost simultaneously); second, a robust affine factorization method is developed which is able to cope with motion degeneracy. This factorization is used to associate tracks into object-level groups.</p> <p>The outcome is that separate parts of an object that are never visible simultaneously in a single frame are associated together. For example, the front and back of a car, or the front and side of a face. In turn this enables object-level matching and recognition throughout a video.</p> <p>We illustrate the method for a number of shots from the feature film ‘Groundhog Day’.</p> |
| spellingShingle | Sivic, J Schaffalitzky, F Zisserman, A Object level grouping for video shots |
| title | Object level grouping for video shots |
| title_full | Object level grouping for video shots |
| title_fullStr | Object level grouping for video shots |
| title_full_unstemmed | Object level grouping for video shots |
| title_short | Object level grouping for video shots |
| title_sort | object level grouping for video shots |
| work_keys_str_mv | AT sivicj objectlevelgroupingforvideoshots AT schaffalitzkyf objectlevelgroupingforvideoshots AT zissermana objectlevelgroupingforvideoshots |