Contextual models for object detection using boosted random fields
We seek to both detect and segment objects in images. To exploit both local image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which uses Boosting to learn the graph structure and local evidence of a conditional random field (CRF). The graph structure is learne...
| Main Authors: | , , |
|---|---|
| Language: | en_US |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/30482 |
| _version_ | 1811076979267469312 |
|---|---|
| author | Torralba, Antonio Murphy, Kevin P. Freeman, William T. |
| author_facet | Torralba, Antonio Murphy, Kevin P. Freeman, William T. |
| author_sort | Torralba, Antonio |
| collection | MIT |
| description | We seek to both detect and segment objects in images. To exploit both local image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which uses Boosting to learn the graph structure and local evidence of a conditional random field (CRF). The graph structure is learned by assembling graph fragments in an additive model. The connections between individual pixels are not very informative, but by using dense graphs, we can pool information from large regions of the image; dense models also support efficient inference. We show how contextual information from other objects can improve detection performance, both in terms of accuracy and speed, by using a computational cascade. We apply our system to detect stuff and things in office and street scenes. |
| first_indexed | 2024-09-23T10:33:27Z |
| id | mit-1721.1/30482 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:33:27Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/304822019-04-12T08:37:49Z Contextual models for object detection using boosted random fields Torralba, Antonio Murphy, Kevin P. Freeman, William T. AI Object detection context boosting BP random fields We seek to both detect and segment objects in images. To exploit both local image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which uses Boosting to learn the graph structure and local evidence of a conditional random field (CRF). The graph structure is learned by assembling graph fragments in an additive model. The connections between individual pixels are not very informative, but by using dense graphs, we can pool information from large regions of the image; dense models also support efficient inference. We show how contextual information from other objects can improve detection performance, both in terms of accuracy and speed, by using a computational cascade. We apply our system to detect stuff and things in office and street scenes. 2005-12-22T01:35:14Z 2005-12-22T01:35:14Z 2004-06-25 MIT-CSAIL-TR-2004-043 AIM-2004-013 http://hdl.handle.net/1721.1/30482 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 10 p. 11085755 bytes 604755 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI Object detection context boosting BP random fields Torralba, Antonio Murphy, Kevin P. Freeman, William T. Contextual models for object detection using boosted random fields |
| title | Contextual models for object detection using boosted random fields |
| title_full | Contextual models for object detection using boosted random fields |
| title_fullStr | Contextual models for object detection using boosted random fields |
| title_full_unstemmed | Contextual models for object detection using boosted random fields |
| title_short | Contextual models for object detection using boosted random fields |
| title_sort | contextual models for object detection using boosted random fields |
| topic | AI Object detection context boosting BP random fields |
| url | http://hdl.handle.net/1721.1/30482 |
| work_keys_str_mv | AT torralbaantonio contextualmodelsforobjectdetectionusingboostedrandomfields AT murphykevinp contextualmodelsforobjectdetectionusingboostedrandomfields AT freemanwilliamt contextualmodelsforobjectdetectionusingboostedrandomfields |