Contextual models for object detection using boosted random fields
dc.contributor.author | Torralba, Antonio | en_US |
dc.contributor.author | Murphy, Kevin P. | en_US |
dc.contributor.author | Freeman, William T. | en_US |
dc.date.accessioned | 2004-10-08T20:43:16Z | |
dc.date.available | 2004-10-08T20:43:16Z | |
dc.date.issued | 2004-06-25 | en_US |
dc.identifier.other | AIM-2004-013 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/6740 | |
dc.description.abstract | 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. | en_US |
dc.format.extent | 10 p. | en_US |
dc.format.extent | 2184856 bytes | |
dc.format.extent | 906515 bytes | |
dc.format.mimetype | application/postscript | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.relation.ispartofseries | AIM-2004-013 | en_US |
dc.subject | AI | en_US |
dc.subject | Object detection | en_US |
dc.subject | context | en_US |
dc.subject | boosting | en_US |
dc.subject | BP | en_US |
dc.subject | random fields | en_US |
dc.title | Contextual models for object detection using boosted random fields | en_US |