Abstract | ||
---|---|---|
A semantic-map building method is proposed to localize a robot in the semantic-map. Our semantic-map is organized by using SIFT feature-based object representation. In addition to semantic map, a vision-based relative localization is employed as a process model of extended Kalman filters, where optical flows and Levenberg-Marquardt least square minimization are incorporated to predict relative robot locations. Thus, robust SLAM performances can be obtained even under poor conditions in which localization cannot be achieved by classical odometry-based SLAM. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11892960_68 | KES (1) |
Keywords | Field | DocType |
process model,poor condition,sift feature-based object representation,vision-based relative localization,classical odometry-based slam,extended kalman filter,relative robot location,vision-based semantic-map building,optical flow,semantic-map building method,robust slam performance,least square,levenberg marquardt | Scale-invariant feature transform,Stereo camera,Computer vision,Extended Kalman filter,Corner detection,Computer science,Odometry,Kalman filter,Artificial intelligence,Robot,Optical flow | Conference |
Volume | ISSN | ISBN |
4251 | 0302-9743 | 3-540-46535-9 |
Citations | PageRank | References |
0 | 0.34 | 8 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seungdo Jeong | 1 | 25 | 8.82 |
Jounghoon Lim | 2 | 0 | 0.68 |
Hong Il Suh | 3 | 0 | 0.34 |
Byung-Uk Choi | 4 | 50 | 14.62 |