Learning texton models for real-time scene context
We present a new model for scene context based on the distribution of textons within images. Our approach provides continuous, consistent scene gist throughout a video sequence and is suitable for applications in which the camera regularly views uninformative parts of the scene. We show that our mod...
| Hoofdauteurs: | , , , |
|---|---|
| Formaat: | Conference item |
| Gepubliceerd in: |
2009
|
| _version_ | 1826296881277304832 |
|---|---|
| author | Flint, A Reid, I Murray, D IEEE |
| author_facet | Flint, A Reid, I Murray, D IEEE |
| author_sort | Flint, A |
| collection | OXFORD |
| description | We present a new model for scene context based on the distribution of textons within images. Our approach provides continuous, consistent scene gist throughout a video sequence and is suitable for applications in which the camera regularly views uninformative parts of the scene. We show that our model outperforms the state-of-the-art for place recognition. We further show how to deduce the camera orientation from our scene gist and finally show how our system can be applied to active object search. © 2009 IEEE. |
| first_indexed | 2024-03-07T04:23:09Z |
| format | Conference item |
| id | oxford-uuid:cbb62d76-f1ac-424e-99a2-7fcf641d0f03 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T04:23:09Z |
| publishDate | 2009 |
| record_format | dspace |
| spelling | oxford-uuid:cbb62d76-f1ac-424e-99a2-7fcf641d0f032022-03-27T07:16:44ZLearning texton models for real-time scene contextConference itemhttp://purl.org/coar/resource_type/c_5794uuid:cbb62d76-f1ac-424e-99a2-7fcf641d0f03Symplectic Elements at Oxford2009Flint, AReid, IMurray, DIEEEWe present a new model for scene context based on the distribution of textons within images. Our approach provides continuous, consistent scene gist throughout a video sequence and is suitable for applications in which the camera regularly views uninformative parts of the scene. We show that our model outperforms the state-of-the-art for place recognition. We further show how to deduce the camera orientation from our scene gist and finally show how our system can be applied to active object search. © 2009 IEEE. |
| spellingShingle | Flint, A Reid, I Murray, D IEEE Learning texton models for real-time scene context |
| title | Learning texton models for real-time scene context |
| title_full | Learning texton models for real-time scene context |
| title_fullStr | Learning texton models for real-time scene context |
| title_full_unstemmed | Learning texton models for real-time scene context |
| title_short | Learning texton models for real-time scene context |
| title_sort | learning texton models for real time scene context |
| work_keys_str_mv | AT flinta learningtextonmodelsforrealtimescenecontext AT reidi learningtextonmodelsforrealtimescenecontext AT murrayd learningtextonmodelsforrealtimescenecontext AT ieee learningtextonmodelsforrealtimescenecontext |