| The ImageCLEF Robot Vision Challenge Workshop 2010 |
| Workshop Date | October 18, 2010 |
| Location |
Taipei, Taiwan |
| Organizers |
|
The ability to represent knowledge about space and its position therein is crucial for a mobile robot. To this end, topological and semantic descriptions are gaining popularity for augmenting purely metric space representations. In the concrete case of indoor environments, the ability to understand the existing topological relations and associate semantics terms such as ``corridor" or ``office" with places, gives a much more intuitive idea of the position of the robot than global metric coordinates. Vision has become in the last years the preferred sensor for capturing this type of information, as a large shar eof the semantic description of a place is encoded in its visual appearance. A large instrument promoting this research has been so far the creation of several publicly available databases, imaging indoor places such as offices or private houses. This instrument can be promoted further by organizing a challenge evaluation, targeting every year different aspects of the problem on expanding collection of data. The goal of this workshop is to present and discuss the results of the ImageCLEF2010 robot vision task. This challenge has arrived at its third edition and it has been consistently gaining popularity since its first edition in 2009.
The objective of this workshop is to present and discuss the results of the ImageCLEF2010 robot vision task. The task was presented for the first time in 2009, when participants were asked to determine the topological location of a robot based on images acquired with a perspective camera mounted on the robot platform. The task attracted considerable attention, with 7 participating groups and a total of 27 submitted runs. The second edition of the challenge was held in conjunction with ICPR2010 and addressed the problem of visual place classification. Specifically, participants were asked to classify rooms and functional areas on the basis of image sequences, captured by a stereo camera mounted on a mobile robot within an office environment. The test sequence consisted of rooms seen during training plus anumber of additional rooms not imaged in the training sequence. This second edition of the task saw an increase in participation, with 9 participating groups and 34 submitted runs. The third, currently ongoing edition of the robot vision challenge will continue addressing the problem of visual place classification, with a special focus on generalization. Participants will be asked to classify rooms and functional areas on thebasis of image sequences, captured by a stereo camera mounted on amobile robot within an office environment. The test sequence will be acquired within the same building but at a different floor than the training sequence. It will contain rooms of the same categorical type(corridor, office, bathroom) and it will also contain room categories not seen in the training sequence(meetingroom, library). The system built by participants should be able to answer the question ``where are you" when presented with a test sequence imaging a room category seen during training, and it should be able to answer ``I don't know this category" when presented with a new room category. for more informations on the robot vision task at ImageCLEF2010 please look here
All group that will register to the robot vision task at ImageCLEF 2010 will be able to present a paper at the workshop. All groups that will submit at least one run to the task will be invited to submit a paper and to present it at the workshop. All the groups that will register but will not submit a run to the robot vision task will have the possibility to submit a paper that will go under review. Further details on the submission format will be posted soon.