Book
Data Partitioning Technique for Online and Incremental Visual SLAM.
| Title: | Data Partitioning Technique for Online and Incremental Visual SLAM. |
|---|---|
| Authors: | Tongprasit, Noppharit, Kawewong, Aram, Hasegawa, Osamu |
| Source: | Neural Information Processing (9783642106767); 2009, p769-777, 9p |
| Abstract: | This paper describes a new data partitioning technique for used with a visual SLAM system. Combined with the existing SLAM system, the technique surveys areas to which the input image might belong to. It then retrieves matched images from such areas. The proposed technique can run in parallel with a normal SLAM system, such as FAB-MAP, in an unsupervised and incremental manner. We also introduce usage of Position-Invariant Robust Features (PIRFs) to make the system robust to dynamic changes in scenes such as moving objects. Combining our technique with normal SLAM can markedly increase the localization recall rate. Experiment results showed that the FAB-MAP result recall rate can increase to 30% at the same precision. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Information Processing (9783642106767) is the property of Springer Nature / Books and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| DOI: | 10.1007/978-3-642-10677-4_88 |
| Database: | Complementary Index |
Availability