A Comparison of Appearance-Based Descriptors in a Visual SLAM Approach

A Comparison of Appearance-Based Descriptors in a Visual SLAM Approach

L. Fernández (Miguel Hernández University, Elche (Alicante), Spain), L. Payá (Miguel Hernández University, Elche (Alicante), Spain), F. Amorós (Miguel Hernández University, Elche (Alicante), Spain) and O. Reinoso (Miguel Hernández University, Elche (Alicante), Spain)
Copyright: © 2015 |Pages: 10
DOI: 10.4018/978-1-4666-5888-2.ch313
OnDemand PDF Download:
No Current Special Offers

Chapter Preview



The SLAM problem is a task studied extensively in the field of mobile robotics. One of the first works we find corresponds to Moravec and Elfes (1985), where a metric map is built by means of wide-angle sonar range measurements and a probabilistic approach. Subsequently laser sensors are introduced to improve the accuracy and velocity in the algorithms created. For example, Thrun (2001) presents an algorithm for the SLAM problem in which a team of robots builds a map online using laser sensors and a Monte Carlo approach. However, the use of laser sensors implies an important contribution of radiation to the environment, and the laser sensors also use mechanical systems, which introduce errors.

Key Terms in this Chapter

Localization: It is the estimation of the position of an autonomous agent in a given map.

SLAM: It is the process of building a map of an environment while simultaneously the localization of the agent that compute the map is estimated.

Gist: It is the meaning of a scene, or in other words, the spatial envelope of the scene.

Omnidirectional Vision: It is a vision system that is capable of capturing all the information surrounding the system with a single image (360º).

Mapping: It is the creation of an internal representation of any given environment.

Mobile Robot: It is an autonomous vehicle that is capable of movement in any given environment.

Appearance Descriptor: It is a descriptor of an image that represents the global information of the same without extracting landmarks.

Topological Map: It is a representation of the environment by means of a list of locations within a graph with connectivity relationships between them.

Probabilistic Localization: It is a localization task, where the information of all previous robot locations is used to estimate its current location.

Metrical Map: It is a representation of the environment through geometrical information with certain accuracy.

Complete Chapter List

Search this Book: