TY - GEN
T1 - SAMSLAM: Simulated annealing monocular SLAM
AU - Bellavia, Fabio
AU - Bellavia, Fabio
AU - Fanfani, Marco
AU - Pazzaglia, Fabio
AU - Colombo, Carlo
PY - 2013
Y1 - 2013
N2 - This paper proposes a novel monocular SLAM approach. For a triplet of successive keyframes, the approach inteleaves the registration of the three 3D maps associated to each image pair in the triplet and the refinement of the corresponding poses, by progressively limiting the allowable reprojection error according to a simulated annealing scheme. This approach computes only local overlapping maps of almost constant size, thus avoiding problems of 3D map growth. It does not require global optimization, loop closure and back-correction of the poses
AB - This paper proposes a novel monocular SLAM approach. For a triplet of successive keyframes, the approach inteleaves the registration of the three 3D maps associated to each image pair in the triplet and the refinement of the corresponding poses, by progressively limiting the allowable reprojection error according to a simulated annealing scheme. This approach computes only local overlapping maps of almost constant size, thus avoiding problems of 3D map growth. It does not require global optimization, loop closure and back-correction of the poses
UR - http://hdl.handle.net/10447/385531
M3 - Conference contribution
SN - 978-3-642-40245-6; 978-3-642-40246-3
T3 - LECTURE NOTES IN COMPUTER SCIENCE
SP - 515
EP - 522
BT - Computer Analysis of Images and Patterns
ER -