<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In the 3d dense map construction system of indoor scene by mobile robot, the existing single sensor method cannot improve the positioning accuracy and reconstruction accuracy of robot, as well as the requirement of rapidity. Therefore, it is applied to THE ORB-SLAM with three parallel threads of track tracking, map reconstruction and loopback detection. Through depth camera pose to splice point cloud of building three-dimensional dense point cloud, in the 3 d reconstruction, a computer can not rely on GPU parallel computing, using only the CPU recovery environment three-dimensional dense scene map method, further reduce the time of the map construction, improve the efficiency of the reconstruction, thus improve the overall performance. Since only the ORB features were retained in the map during the construction of ORB-SLAM2, sparse point cloud map was established. Fortunately, the framework structure of ORB-SlAM2 was relatively clear. Only one thread needed to be added for the maintenance of point cloud map, and the key frames generated by ORB-SLAM2 were passed into the point cloud map construction thread. Use incoming keyframes to generate a map with dense point clouds.</p>
</abstract>

In the 3d dense map construction system of indoor scene by mobile robot, the existing single sensor method cannot improve the positioning accuracy and reconstruction accuracy of robot, as well as the requirement of rapidity. Therefore, it is applied to THE ORB-SLAM with three parallel threads of track tracking, map reconstruction and loopback detection. Through depth camera pose to splice point cloud of building three-dimensional dense point cloud, in the 3 d reconstruction, a computer can not rely on GPU parallel computing, using only the CPU recovery environment three-dimensional dense scene map method, further reduce the time of the map construction, improve the efficiency of the reconstruction, thus improve the overall performance. Since only the ORB features were retained in the map during the construction of ORB-SLAM2, sparse point cloud map was established. Fortunately, the framework structure of ORB-SlAM2 was relatively clear. Only one thread needed to be added for the maintenance of point cloud map, and the key frames generated by ORB-SLAM2 were passed into the point cloud map construction thread. Use incoming keyframes to generate a map with dense point clouds.

3D Reconstruction System Based on Multi Sensor

School of Computer Science and Engineering

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"3D Reconstruction System Based on Multi Sensor"}

In the 3d dense map construction system of indoor scene by mobile robot, the existing single sensor method cannot improve the positioning accuracy and...

Sensor	Track the percentage of partial breaks caused by loss
Without IMU	35%
With IMU	10%

The camera parameters	The calibration results
Internal	605.894	0	317.887
	0	606.856	256.416
	0	0	1
Distortion parameter 1	0.15689
Distortion parameter 2	−0.3425
Mean reprojection difference	0.28213

The name of the software	Model and Version
The operating system	Ubuntu18.04
Robot operating system	ROS-Melodic
Development programming language	c/c++
	opencv
Visual library to use Point cloud library	PCL

The camera parameters	The calibration results
Rotation matrix of camera and IMU	0.9999524	0.0042236	0.0012432
	−0.0054268	0.9995236	0.00158425
	−0.001426238	0.0017052	0.9999842
Translation matrix of camera and IMU	0.01238847	0.00842635	−0.02145263

Hardware	Model
Upper-computer workstation	Lenovo Air15
IMU sensor	MPU9250
Depth sensor	Realsense D435

3D Reconstruction System Based on Multi Sensor

Pubblicato online: 26 mag 2023

Pagine: 58 - 66

DOI: https://doi.org/10.2478/ijanmc-2022-0016

Parole chiave
Mobilerobot, Three-Dimensional Reconstruction, The ORB-SLAM, Depth Sensor, Inertial Sensor

© 2022 Fan Yu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

Figure 12.

Figure 13.

Figure 14.

Figure 15.

Experimental results of 3D reconstruction for different sensors

Calibration results of the realsense D435 camera

Software system configuration

Calibration results of multiple sensors

Hardware configuration parameters of the robot

3D Reconstruction System Based on Multi Sensor

Pubblicato online: 26 mag 2023

Pagine: 58 - 66

DOI: https://doi.org/10.2478/ijanmc-2022-0016

Parole chiaveMobilerobot, Three-Dimensional Reconstruction, The ORB-SLAM, Depth Sensor, Inertial Sensor

© 2022 Fan Yu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

Figure 12.

Figure 13.

Figure 14.

Figure 15.

Experimental results of 3D reconstruction for different sensors

Calibration results of the realsense D435 camera

Software system configuration

Calibration results of multiple sensors

Hardware configuration parameters of the robot

Parole chiave
Mobilerobot, Three-Dimensional Reconstruction, The ORB-SLAM, Depth Sensor, Inertial Sensor