Describing composite urban workspaces
In this paper we present an appearance-based method for augmenting maps of outdoor urban environments with higher-order, semantic labels. Our motivation is to increase the value and utility of the typically low-level representations built by contemporary SLAM algorithms. A supervised learning scheme...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Published: |
2007
|
| _version_ | 1797100935537754112 |
|---|---|
| author | Posner, I Schroeter, D Newman, P IEEE |
| author_facet | Posner, I Schroeter, D Newman, P IEEE |
| author_sort | Posner, I |
| collection | OXFORD |
| description | In this paper we present an appearance-based method for augmenting maps of outdoor urban environments with higher-order, semantic labels. Our motivation is to increase the value and utility of the typically low-level representations built by contemporary SLAM algorithms. A supervised learning scheme is employed to train a set of classifiers to respond to common scene attributes given a mixture of geometric and visual scene information. The union of classifier responses yields a composite description of the local workspace. We apply our method to three large data sets. © 2007 IEEE. |
| first_indexed | 2024-03-07T05:44:46Z |
| format | Conference item |
| id | oxford-uuid:e6dabe80-c079-4b84-af85-a27c6f8f1af7 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T05:44:46Z |
| publishDate | 2007 |
| record_format | dspace |
| spelling | oxford-uuid:e6dabe80-c079-4b84-af85-a27c6f8f1af72022-03-27T10:33:55ZDescribing composite urban workspacesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:e6dabe80-c079-4b84-af85-a27c6f8f1af7Symplectic Elements at Oxford2007Posner, ISchroeter, DNewman, PIEEEIn this paper we present an appearance-based method for augmenting maps of outdoor urban environments with higher-order, semantic labels. Our motivation is to increase the value and utility of the typically low-level representations built by contemporary SLAM algorithms. A supervised learning scheme is employed to train a set of classifiers to respond to common scene attributes given a mixture of geometric and visual scene information. The union of classifier responses yields a composite description of the local workspace. We apply our method to three large data sets. © 2007 IEEE. |
| spellingShingle | Posner, I Schroeter, D Newman, P IEEE Describing composite urban workspaces |
| title | Describing composite urban workspaces |
| title_full | Describing composite urban workspaces |
| title_fullStr | Describing composite urban workspaces |
| title_full_unstemmed | Describing composite urban workspaces |
| title_short | Describing composite urban workspaces |
| title_sort | describing composite urban workspaces |
| work_keys_str_mv | AT posneri describingcompositeurbanworkspaces AT schroeterd describingcompositeurbanworkspaces AT newmanp describingcompositeurbanworkspaces AT ieee describingcompositeurbanworkspaces |