Monocular SLAM with locally planar landmarks via geometric rao-blackwellized particle filtering on Lie groups

Abstract

We propose a novel geometric Rao-Blackwellized particle

Geometric particle swarm optimization for robust visual ego-motion estimation via particle filtering

“…The discretized stochastic differential equation on SE(3) previously employed in Ref. [29] is suitable for our purpose. Since we assume hand-held cameras whose odometry information is not available, we employ the auto-regressive (AR) process on SE(3) as the state dynamics, which is similar to the smooth motion models used in other previous work [8,14].…”

Realtime multibody visual SLAM with a smoothly moving monocular camera

“…Also the Jacobians of the above equations needed in the optimization process can be readily obtained in closed form. Due to this advantages, the Lie theory based representation of rigid body motion is becoming popular among recent VSLAM solutions [9,23]. We again use this Lie group formulation in tracking of the moving object described in section 4.…”

“…Vision based SLAM [4,7,9,14,23] and SfM systems [6] have been the subject of much research and are finding applications in many areas like robotics, augmented reality, city mapping. But almost all these approaches assume a static environment, containing only rigid, non-moving objects.…”

Simultaneous localization, mapping and deblurring

“…The camera pose P k t is defined on the Special Euclidean group SE (3), which represents the rigid transformation of camera composed of 3-D translation and 3-D rotation from the origin [12], and g(·) is a perspective camera projection function with camera intrinsic parameters. Then, we can rewrite the equation (1) as…”