Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Overall architecture diagram.

More »

Fig 1 Expand

Fig 2.

Schematic diagram of point-to-plane association strategy.

More »

Fig 2 Expand

Fig 3.

Flowchart of plane feature construction and matching.

More »

Fig 3 Expand

Fig 4.

Flowchart of posture decoupling based on Manhattan coordinate system.

More »

Fig 4 Expand

Fig 5.

The specific definitions of MF and MP, as well as the relationship between them.

More »

Fig 5 Expand

Fig 6.

The relationship between the world coordinate system (W), the historical frame camera coordinate system (L), the Manhattan coordinate system (M), and the current frame camera coordinate system (C).

More »

Fig 6 Expand

Fig 7.

Two parallel orthogonal plane features.

More »

Fig 7 Expand

Fig 8.

One parallel or orthogonal plane feature and another orthogonal vertical plane feature.

More »

Fig 8 Expand

Fig 9.

Decoupling of the translation matrix.

More »

Fig 9 Expand

Fig 10.

Pseudocode implementation of pose matrix decoupling.

More »

Fig 10 Expand

Fig 11.

Constructing imaginary plane features using common points in frame.

More »

Fig 11 Expand

Fig 12.

Constructing imaginary plane features using common points in frame.

More »

Fig 12 Expand

Fig 13.

Pose estimation model based on joint optimization of points, lines and planes and vanishing point constraints.

More »

Fig 13 Expand

Fig 14.

Scene of long corridor.

More »

Fig 14 Expand

Fig 15.

Line feature classification based on vanishing points.

More »

Fig 15 Expand

Fig 16.

Iteration between Manhattan coordinate system and vanishing point.

More »

Fig 16 Expand

Table 1.

The module comparison of related classical algorithms.

More »

Table 1 Expand

Table 2.

Evaluation results of translation ATE RMSE (unit: m) on ICL-NUIM and TUM datasets. Bold numbers represent the best performances. ‘×’ represents tracking lost.

More »

Table 2 Expand

Fig 17.

RMSE comparison of different algorithms in the ICL dataset living_room_traj1_frei.

More »

Fig 17 Expand

Fig 18.

RMSE comparison of different algorithms in the ICL dataset living_room_traj2_frei.

More »

Fig 18 Expand

Fig 19.

Trajectory comparison of different algorithms in the ICL dataset living_room_traj1_frei.

More »

Fig 19 Expand

Fig 20.

Trajectory comparison of different algorithms in the ICL dataset living_room_traj2_frei.

More »

Fig 20 Expand

Fig 21.

Trajectory comparison of different algorithms in the TUM dataset 2_desk_with_person.

More »

Fig 21 Expand

Fig 22.

Trajectory comparison of different algorithms in the TUM dataset 2_xyz.

More »

Fig 22 Expand

Fig 23.

Trajectory comparison of different algorithms in the TUM dataset 3_long_office_household.

More »

Fig 23 Expand

Fig 24.

Trajectory comparison of different algorithms in the TUM dataset 3_structure_texture_near.

More »

Fig 24 Expand

Fig 25.

RMSE comparison of different algorithms in the TUM dataset 2_desk_with_person.

More »

Fig 25 Expand

Fig 26.

RMSE comparison of different algorithms s in the TUM dataset 2_xyz.

More »

Fig 26 Expand

Fig 27.

RMSE comparison of different algorithms in the TUM dataset 3_long_office_household.

More »

Fig 27 Expand

Fig 28.

RMSE comparison of different algorithms in the TUM dataset 3_structure_texture_near.

More »

Fig 28 Expand

Table 3.

Frame counts for MF extraction in the experimental datasets.

More »

Table 3 Expand

Fig 29.

Box plot of ATE of 1_rpy for different algorithms.

More »

Fig 29 Expand

Fig 30.

Box plot of ATE of living_room_traj1_frei for different algorithms.

More »

Fig 30 Expand

Fig 31.

Average ATE Comparison of SLAM Algorithms on TUM and ICL Datasets.

More »

Fig 31 Expand

Fig 32.

Comparison of the number of plane feature extractions between scenarios in structure_texture_far.

More »

Fig 32 Expand

Fig 33.

Comparison of the number of plane feature extractions between scenarios in structure_texture_near.

More »

Fig 33 Expand

Fig 34.

Extraction of line features in the structure_texture_far sequence.

More »

Fig 34 Expand

Fig 35.

Classification based on vanishing points in the structure_texture_far sequence.

More »

Fig 35 Expand

Fig 36.

Orthogonal plane features extracted from the current frame in the structure_texture_far sequence.

More »

Fig 36 Expand

Fig 37.

Orthogonal plane features extracted from orthogonal plane features matched in the historical frame in the structure_texture_far sequence.

More »

Fig 37 Expand

Fig 38.

ZED2i camera-based test equipment.

More »

Fig 38 Expand

Fig 39.

Scene of long corridor scene.

More »

Fig 39 Expand

Fig 40.

Scene of underground parking scene.

More »

Fig 40 Expand

Table 4.

Evaluation results of translation ATE RMSE (unit: m) on long corridor scene and the underground garage scene. Bold numbers represent the best performances.

More »

Table 4 Expand

Fig 41.

Trajectory comparison of Data_1-1 based on the actual scene measured by ZED2i camera.

More »

Fig 41 Expand

Fig 42.

Trajectory comparison of Data_2-2 based on the actual scene measured by ZED2i camera.

More »

Fig 42 Expand

Fig 43.

Trajectory comparison of Data_2-3 based on the actual scene measured by ZED2i camera.

More »

Fig 43 Expand

Fig 44.

RMSE comparison of Data_1-1 based on the actual scene measured by ZED2i camera.

More »

Fig 44 Expand

Fig 45.

RMSE comparison of Data_2-2 based on the actual scene measured by ZED2i camera.

More »

Fig 45 Expand

Fig 46.

RMSE comparison of Data_2-3 based on the actual scene measured by ZED2i camera.

More »

Fig 46 Expand

Fig 47.

Comparison of the number of extracted plane features in scenes Data_1-1.

More »

Fig 47 Expand

Fig 48.

Comparison of the number of extracted plane features in scenes Data_1-2.

More »

Fig 48 Expand

Fig 49.

Comparison of the number of extracted plane features in scenes Data_2-1.

More »

Fig 49 Expand

Fig 50.

Comparison of the number of extracted plane features in scenes Data_2-2.

More »

Fig 50 Expand