Review on 3D Mapping and Segmentation
Akash Kuamr Ghanate1, Aashish M2, Santhosh M Patil3, Sowmyarani C N4, Ramakanth Kumar P5
1Akash Kumar Ghanate*, B.E., Department of Computer Science and Engineering, R.V College of Engineering, Bangalore, India.
2Aashish M, B.E., Department of Computer Science and Engineering, R.V College of Engineering, Bangalore, India.
3Santhosh M Patil, B.E., Department of Computer Science and Engineering, R.V College of Engineering, Bangalore, India.
4Dr. Sowmyarani C N, Associate Professor, Department of Computer Science and Engineering, R.V College of Engineering, Bangalore, India.
5Dr. Ramakanth Kumar P, Professor & HoD, Department of Computer Science and Engineering, R.V College of Engineering, Bangalore, India. E-mail: ramakanthkp@rvce.edu.in
Manuscript received on July 02, 2020. | Revised Manuscript received on July 05, 2020. | Manuscript published on August 30, 2020. | PP: 22-29 | Volume-9 Issue-6, August 2020. | Retrieval Number: E1020069520/2020©BEIESP | DOI: 10.35940/ijeat.E1020.089620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The deployment of a robot in a remote environment is a field of research that has huge applications. The robotic system must have the capability of sensing its surroundings and being aware of what it is around. We concluded two key tasks for this purpose, which are 3D mapping and segmentation. This paper shows a comprehensive review of the different 3D mapping and segmentation methods. Mapping techniques include those using RGB images, RGBD images and LIDAR. Segmentation techniques include PointNet, PointNet++, 3D semantic and instance segmentation and joint instance segmentation. We also describe two end-to-end approaches for mapping and segmentation. These methods are reviewed elaborately, comparisons are drawn between them, challenges are presented and future directions in addressing these challenges are pointed out.
Keywords: 3D Mapping, JSNet, Segmentation, SLAM, Sfm, PointNet