A survey on sensing methods and feature extraction algorithms for SLAM problem

TL;DR

This survey reviews sensing methods and feature extraction algorithms for SLAM, aiming to identify the most suitable techniques for designing a Visual SLAM robot for unstructured environments.

Contribution

It provides a comparative analysis of current sensing and feature extraction methods to guide the development of a Visual SLAM system.

Findings

Identifies key sensing methods used in recent SLAM research

Highlights the importance of environment-specific sensing and feature extraction choices

Suggests optimal combinations for unstructured environment mapping

Abstract

This paper is a survey work for a bigger project for designing a Visual SLAM robot to generate 3D dense map of an unknown unstructured environment. A lot of factors have to be considered while designing a SLAM robot. Sensing method of the SLAM robot should be determined by considering the kind of environment to be modeled. Similarly the type of environment determines the suitable feature extraction method. This paper goes through the sensing methods used in some recently published papers. The main objective of this survey is to conduct a comparative study among the current sensing methods and feature extraction algorithms and to extract out the best for our work.