CONF Ullah_ICRA_2008/IDIAP Towards Robust Place Recognition for Robot Localization Ullah, Muhammad Muneeb Pronobis, Andrzej Caputo, Barbara Luo, Jie Jensfelt, Patric Christensen, Henrik I. EXTERNAL https://publications.idiap.ch/attachments/papers/2008/Ullah_ICRA_2008.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Ullah_Idiap-RR-40-2010 Related documents IEEE International Conference on Robotics ad Automation 2008 Localization and context interpretation are two key competences for mobile robot systems. Visual place recognition, as opposed to purely geometrical models, holds promise of higher flexibility and association of semantics to the model. Ideally, a place recognition algorithm should be robust to dynamic changes and it should perform consistently when recognizing a room (for instance a corridor) in different geographical locations. Also, it should be able to categorize places, a crucial capability for transfer of knowledge and continuous learning. In order to test the suitability of visual recognition algorithms for these tasks, this paper presents a new database, acquired in three different labs across Europe. It contains image sequences of several rooms under dynamic changes, acquired at the same time with a perspective and omnidirectional camera, mounted on a socket. We assess this new database with an appearance based algorithm that combines local features with support vector machines through an ad-hoc kernel. Results show the effectiveness of the approach and the value of the database REPORT Ullah_Idiap-RR-40-2010/IDIAP Towards Robust Place Recognition for Robot Localization Ullah, Muhammad Muneeb Pronobis, Andrzej Caputo, Barbara Luo, Jie Jensfelt, Patric Christensen, Henrik I. EXTERNAL https://publications.idiap.ch/attachments/reports/2008/Ullah_Idiap-RR-40-2010.pdf PUBLIC Idiap-RR-40-2010 2010 Idiap November 2010 Localization and context interpretation are two key competences for mobile robot systems. Visual place recognition, as opposed to purely geometrical models, holds promise of higher flexibility and association of semantics to the model. Ideally, a place recognition algorithm should be robust to dynamic changes and it should perform consistently when recognizing a room (for instance a corridor) in different geographical locations. Also, it should be able to categorize places, a crucial capability for transfer of knowledge and continuous learning. In order to test the suitability of visual recognition algorithms for these tasks, this paper presents a new database, acquired in three different labs across Europe. It contains image sequences of several rooms under dynamic changes, acquired at the same time with a perspective and omnidirectional camera, mounted on a socket. We assess this new database with an appearance based algorithm that combines local features with support vector machines through an ad-hoc kernel. Results show the effectiveness of the approach and the value of the database