Advanced vision-based localization and mapping

• Main Author: Foo, Sheng Cong
• Other Authors: Xie Lihua
• Format: Final Year Project
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/78132
• Institution: Nanyang Technological University

Simultaneous localisation and mapping (SLAM) is the computational problem of constructing or updating a map of an unknown environment while simultaneously keeping track of an agent’s location within it, usually a robot. This project aims to build and implement a visual based localization system with just using a Red Blue Green Depth (RGB-D) camera and an Altitude and Heading Reference System (AHRS). Real-Time Appearance-Based Mapping (RTAB-Map) was the chosen SLAM solution after a brief comparison with the rest. Within RTAB-Map, we researched and implemented various SLAM algorithms like SURF, ORB, etc. This system will only be tested in an indoor environment, as it makes full use of the RGB-D camera’s capabilities. The results will then be compared with other SLAM algorithms provided in RTAB-Map and the RTAB-Map parameters will be adjusted to improve the accuracy of the results.