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.

Pipeline of LIO-CSI.

More »

Fig 1 Expand

Fig 2.

Schematic diagram of label correction.

More »

Fig 2 Expand

Fig 3.

Visualization of dynamic object filtering.

More »

Fig 3 Expand

Fig 4.

Comparison of feature points and constraint relationships between frames: (a) edge feature points and loss le, (b) planar feature points and loss lp. Different color points represent different semantic labels.

More »

Fig 4 Expand

Fig 5.

Semantic-assisted scan-context image encoding process.

More »

Fig 5 Expand

Fig 6.

The sensor setup used in our experiments: (a) a Velodyne HDL-32E surround LiDAR sensor, (b) a 3DM-GX5 IMU, and (c) a Trimble BD982 GNSS receiver module with antennas.

More »

Fig 6 Expand

Fig 7.

Recording platform (Volkswagen Tiguan) with sensors.

More »

Fig 7 Expand

Table 1.

KITTI dataset details.

More »

Table 1 Expand

Table 2.

JLU Campus dataset details.

More »

Table 2 Expand

Table 3.

Relative pose error on KITTI dataset.

More »

Table 3 Expand

Fig 8.

Trajectory comparison on sequence 05 of the KITTI dataset.

More »

Fig 8 Expand

Fig 9.

Trajectory comparison on sequence 06 of the KITTI dataset.

More »

Fig 9 Expand

Fig 10.

Trajectory comparison and semantic maps of sequence 09.

More »

Fig 10 Expand

Fig 11.

Vertical global consistency comparison.

More »

Fig 11 Expand

Table 4.

Relative pose error of LIO-SAM and LIO-SAM-ODOM.

More »

Table 4 Expand

Table 5.

Relative pose error of LIO-SAM-ODOM and LIO-CSI.

More »

Table 5 Expand

Fig 12.

USGS national map imagery and mapping results of LIO-CSI.

The green track in USGS National Map imagery is the actual trajectory of Tiguan Volkswagen movement.

More »

Fig 12 Expand

Table 6.

Relative pose error on JLU campus dataset.

More »

Table 6 Expand