OP-SLAM: An RGB-D SLAMMOT Method Leveraging the Constraints of Object Planar Features | Wuhan University Journal of Natural Sciences

Open Access

Table 1

Object pose estimation results in different object planar constraint modes on the synthetic dataset

seq	obj.id	w/o planar constraints			w/ point-to-plane constraint			w/ plane-to-plane constraint			w/ two planar constraints
seq	obj.id	$A T E$	$R P E_{t}$	$R P E_{R}$	$A T E$	$R P E_{t}$	$R P E_{R}$	$A T E$	$R P E_{t}$	$R P E_{R}$	$A T E$	$R P E_{t}$	$R P E_{R}$
cube_3dof_cam_static	0	0.046	0.006	0.143	0.042	0.006	0.045	0.045	0.006	0.134	0.042	0.006	0.126
cube_3dof_cam_static	1	0.142	0.041	0.244	0.138	0.038	0.218	0.195	0.038	0.233	0.122	0.035	0.202
cube_3dof_cam_moving	0	0.046	0.007	0.182	0.040	0.007	0.179	0.044	0.006	0.071	0.041	0.007	0.179
cube_3dof_cam_moving	1	0.133	0.095	0.567	0.137	0.105	0.570	0.140	0.054	0.395	0.136	0.052	0.445
cube_6dof_cam_static	0	0.303	0.013	0.310	0.302	0.011	0.220	0.301	0.014	0.294	0.297	0.013	0.250
cube_6dof_cam_static	1	0.267	0.021	0.340	0.265	0.021	0.375	0.268	0.018	0.332	0.256	0.021	0.370
cube_6dof_cam_moving	0	0.729	0.017	0.315	0.739	0.017	0.304	0.724	0.017	0.309	0.738	0.017	0.303
cube_6dof_cam_moving	1	0.614	0.040	0.529	0.618	0.036	0.450	0.606	0.037	0.483	0.627	0.036	0.448
box_cam_ moving	0	1.079	0.045	2.228	1.049	0.043	1.600	1.063	0.048	2.087	1.041	0.039	1.581
box_cam_ moving	1	2.036	0.025	1.268	1.997	0.027	1.274	2.041	0.024	1.232	1.951	0.026	1.268

Note： The units in the table are as follows. ATE： m， RPE_t： m/frame， RPE_R： (°)/frame. The best results are highlighted in bold.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.