Room Categorization Based on a Hierarchical Representation of Space
For successful operation in real-world environments, a mobile robot requires an effective spatial model. The model should be compact, should possess large expressive power and should scale well with respect to the number of modelled categories. In this paper we propose a new compositional hierarchic...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2013-02-01
|
| Series: | International Journal of Advanced Robotic Systems |
| Online Access: | https://doi.org/10.5772/55534 |
| _version_ | 1818759970136522752 |
|---|---|
| author | Peter Uršič Domen Tabernik Marko Boben Danijel Skočaj Aleš Leonardis Matej Kristan |
| author_facet | Peter Uršič Domen Tabernik Marko Boben Danijel Skočaj Aleš Leonardis Matej Kristan |
| author_sort | Peter Uršič |
| collection | DOAJ |
| description | For successful operation in real-world environments, a mobile robot requires an effective spatial model. The model should be compact, should possess large expressive power and should scale well with respect to the number of modelled categories. In this paper we propose a new compositional hierarchical representation of space that is based on learning statistically significant observations, in terms of the frequency of occurrence of various shapes in the environment. We have focused on a two-dimensional space, since many robots perceive their surroundings in two dimensions with the use of a laser range finder or sonar. We also propose a new low-level image descriptor, by which we demonstrate the performance of our representation in the context of a room categorization problem. Using only the lower layers of the hierarchy, we obtain state-of-the-art categorization results in two different experimental scenarios. We also present a large, freely available, dataset, which is intended for room categorization experiments based on data obtained with a laser range finder. |
| first_indexed | 2024-12-18T06:51:11Z |
| format | Article |
| id | doaj.art-bb0814ddeaf84e5cbd644a1d392225e8 |
| institution | Directory Open Access Journal |
| issn | 1729-8814 |
| language | English |
| last_indexed | 2024-12-18T06:51:11Z |
| publishDate | 2013-02-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | International Journal of Advanced Robotic Systems |
| spelling | doaj.art-bb0814ddeaf84e5cbd644a1d392225e82022-12-21T21:17:19ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142013-02-011010.5772/5553410.5772_55534Room Categorization Based on a Hierarchical Representation of SpacePeter Uršič0Domen Tabernik1Marko Boben2Danijel Skočaj3Aleš Leonardis4Matej Kristan5 Vicos Laboratory, Faculty of Computer and Information Science, University of Ljubljana, Slovenia Vicos Laboratory, Faculty of Computer and Information Science, University of Ljubljana, Slovenia Vicos Laboratory, Faculty of Computer and Information Science, University of Ljubljana, Slovenia Vicos Laboratory, Faculty of Computer and Information Science, University of Ljubljana, Slovenia Vicos Laboratory, Faculty of Computer and Information Science, University of Ljubljana, Slovenia Vicos Laboratory, Faculty of Computer and Information Science, University of Ljubljana, SloveniaFor successful operation in real-world environments, a mobile robot requires an effective spatial model. The model should be compact, should possess large expressive power and should scale well with respect to the number of modelled categories. In this paper we propose a new compositional hierarchical representation of space that is based on learning statistically significant observations, in terms of the frequency of occurrence of various shapes in the environment. We have focused on a two-dimensional space, since many robots perceive their surroundings in two dimensions with the use of a laser range finder or sonar. We also propose a new low-level image descriptor, by which we demonstrate the performance of our representation in the context of a room categorization problem. Using only the lower layers of the hierarchy, we obtain state-of-the-art categorization results in two different experimental scenarios. We also present a large, freely available, dataset, which is intended for room categorization experiments based on data obtained with a laser range finder.https://doi.org/10.5772/55534 |
| spellingShingle | Peter Uršič Domen Tabernik Marko Boben Danijel Skočaj Aleš Leonardis Matej Kristan Room Categorization Based on a Hierarchical Representation of Space International Journal of Advanced Robotic Systems |
| title | Room Categorization Based on a Hierarchical Representation of Space |
| title_full | Room Categorization Based on a Hierarchical Representation of Space |
| title_fullStr | Room Categorization Based on a Hierarchical Representation of Space |
| title_full_unstemmed | Room Categorization Based on a Hierarchical Representation of Space |
| title_short | Room Categorization Based on a Hierarchical Representation of Space |
| title_sort | room categorization based on a hierarchical representation of space |
| url | https://doi.org/10.5772/55534 |
| work_keys_str_mv | AT peterursic roomcategorizationbasedonahierarchicalrepresentationofspace AT domentabernik roomcategorizationbasedonahierarchicalrepresentationofspace AT markoboben roomcategorizationbasedonahierarchicalrepresentationofspace AT danijelskocaj roomcategorizationbasedonahierarchicalrepresentationofspace AT alesleonardis roomcategorizationbasedonahierarchicalrepresentationofspace AT matejkristan roomcategorizationbasedonahierarchicalrepresentationofspace |