Return to search

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 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.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/30482
Date25 June 2004
CreatorsTorralba, Antonio, Murphy, Kevin P., Freeman, William T.
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format10 p., 11085755 bytes, 604755 bytes, application/postscript, application/pdf
RelationMassachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory

Page generated in 0.002 seconds