Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회지)

Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회)
권호 표지
DOI QR코드

DOI QR Code

Three-dimensional Map Construction of Indoor Environment Based on RGB-D SLAM Scheme

  • Huang, He (School of Geomatics and Urban Spatial Information, Beijing University of Civil Engineering and Architecture) ;
  • Weng, FuZhou (School of Geomatics and Urban Spatial Information, Beijing University of Civil Engineering and Architecture) ;
  • Hu, Bo (School of Geomatics and Urban Spatial Information, Beijing University of Civil Engineering and Architecture)
  • Received : 2018.12.24
  • Accepted : 2019.04.28
  • Published : 2019.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

RGB-D SLAM (Simultaneous Localization and Mapping) refers to the technology of using deep camera as a visual sensor for SLAM. In view of the disadvantages of high cost and indefinite scale in the construction of maps for laser sensors and traditional single and binocular cameras, a method for creating three-dimensional map of indoor environment with deep environment data combined with RGB-D SLAM scheme is studied. The method uses a mobile robot system equipped with a consumer-grade RGB-D sensor (Kinect) to acquire depth data, and then creates indoor three-dimensional point cloud maps in real time through key technologies such as positioning point generation, closed-loop detection, and map construction. The actual field experiment results show that the average error of the point cloud map created by the algorithm is 0.0045m, which ensures the stability of the construction using deep data and can accurately create real-time three-dimensional maps of indoor unknown environment.

Keywords

GCRHBD_2019_v37n2_45_f0001.png 이미지

Fig. 1. RGB-D SLAM mapping process

GCRHBD_2019_v37n2_45_f0002.png 이미지

Fig. 2. Principle of RGB-D SLAM algorithm

GCRHBD_2019_v37n2_45_f0003.png 이미지

Fig. 3. Generation process of locating points

GCRHBD_2019_v37n2_45_f0004.png 이미지

Fig. 4. Map construction and closed-loop detection process

GCRHBD_2019_v37n2_45_f0005.png 이미지

Fig. 5. Hardware platform of mobile robot system

GCRHBD_2019_v37n2_45_f0006.png 이미지

Fig. 6. Exploration experiment: (a) corridor 1, (b) corridor 2, and (c) classroom

GCRHBD_2019_v37n2_45_f0007.png 이미지

Fig. 7. Experimental scenarios and results: (a) scene diagram, (b) point cloud map

GCRHBD_2019_v37n2_45_f0008.png 이미지

Fig. 8. 3D reconstruction effect: (a) 2D image, (b) 3D point cloud

GCRHBD_2019_v37n2_45_f0009.png 이미지

Fig. 9. Coordinate acquisition: (a) Total Station Acquisition, (b) SLAM Point Cloud Acquisition

GCRHBD_2019_v37n2_45_f0010.png 이미지

Fig. 10. Coordinate acquisition: (a) Total Station Acquisition, (b) SLAM Point Cloud Acquisition

Table 1. Contrast of coordinates of control points （Unit : m）

GCRHBD_2019_v37n2_45_t0001.png 이미지

References

  1. Angeli, A., Filliat, D., and Doncieux, S. (2008), Fast and incremental method for loop-closure detection using bags of visual words, IEEE Transactions on Robotics, Vol. 24, No. 5, pp. 1027-1037. https://doi.org/10.1109/TRO.2008.2004514
  2. Endres, F., Hess, J., and Sturm, J. (2017), 3-D mapping with an RGB-D camera, IEEE Transactions on Robotics, Vol. 30, No. 1, pp. 177-187. https://doi.org/10.1109/TRO.2013.2279412
  3. Huang, H., Wang. L., and Jiang B. (2016), Accuracy verification of 3D SLAM laser image knapsack surveying robot, Surveying and mapping Bulletin, Vol. 12, No. 5, pp. 68-73.
  4. Man, C. T., Cao, M., and Li, W. (2017), SLAM algorithm evaluation based on depth camera , Journal of Electrical Machinery and Control, Vol. 21, No. 12, pp. 60-65.
  5. Newcombe, R. A., Izadi, S., and Hilliges, O. (2012), KinectFusion: real-time dense surface mapping and tracking, IEEE International Symposium on Mixed and Augmented Reality. IEEE, Vol. 38, No. 6, pp. 127-136.
  6. Niessner, M., Zollhofe, M., Izadi, S., and Stamminger, M. (2013), Real-time 3D reconstruction at scale using voxel hashing, Acm Transactions on Graphics, Vol. 32, No.6, pp. 1-11.
  7. Whelan, T., Kaess, M., and Fallon, M. (2012), Kintinuous: spatially extended KinectFusion, Robotics & Autonomous Systems, Vol. 69, No. 5, pp. 3-14. https://doi.org/10.1016/j.robot.2014.08.019
  8. Yu, N. B., Wang, S. R., and Xu, C. (2017), A RGB-D based method for autonomous exploration and mapping of unknown indoor environment for mobile robots, Robot, Vol. 39, No. 6, pp. 860-871.