Open AccessReview on 3D Mapping and Segmentation
Author(s) -
Akash Kuamr Ghanate,
Menta Sai Aashish,
Santhosh M Patil,
C N Sowmyarani,
Ramakanth Kumar P
Publication year - 2020
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.e1020.089620
Subject(s) - segmentation , computer science , artificial intelligence , computer vision , key (lock) , image segmentation , scale space segmentation , semantic mapping , field (mathematics) , segmentation based object categorization , mathematics , computer security , pure mathematics
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.