Skip to main content
main-content

Über dieses Buch

Mapping and localization are two essential tasks in autonomous mobile robotics. Due to the unavoidable noise that sensors present, mapping algorithms usually rely on loop closure detection techniques, which entail the correct identification of previously seen places to reduce the uncertainty of the resulting maps. This book deals with the problem of generating topological maps of the environment using efficient appearance-based loop closure detection techniques. Since the quality of a visual loop closure detection algorithm is related to the image description method and its ability to index previously seen images, several methods for loop closure detection adopting different approaches are developed and assessed. Then, these methods are used in three novel topological mapping algorithms. The results obtained indicate that the solutions proposed attain a better performance than several state-of-the-art approaches. To conclude, given that loop closure detection is also a key component in other research areas, a multi-threaded image mosaicing algorithm is proposed. This approach makes use of one of the loop closure detection techniques previously introduced in order to find overlapping pairs between images and finally obtain seamless mosaics of different environments in a reasonable amount of time.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract
This chapter serves as an introduction to this book. In the first section, we briefly consider some basic concepts from the robotics field, such as navigation, mapping, localization and SLAM. We also comment on the concept of appearance-based loop closure detection and discuss its importance for mapping and localization tasks. The main contributions are outlined next, once the scope of the book has already been stated.
Emilio Garcia-Fidalgo, Alberto Ortiz

Chapter 2. Background

Abstract
This chapter is intended to provide the reader with a general overview of the most important concepts and terms needed to understand the rest of the book. Main concepts are briefly introduced, making use of examples as they are needed for illustration purposes. More precisely, in the first section, we consider the concept of topological map and define it in a formal way, as well as discuss its main advantages and disadvantages in front of metric approaches. Next, we deal with appearance-based loop closure detection and the factors that more affect the performance of the underlying algorithms.
Emilio Garcia-Fidalgo, Alberto Ortiz

Chapter 3. Literature Review

Abstract
This chapter reviews the main approaches published during the last years with regard to topological mapping and localization by visual means. We classify the different solutions according to the method used to visually describe an image, given the fact that the quality of the resulting map strongly relies on this aspect. Three fundamental categories are distinguished: approaches based on global descriptors, approaches based on local features and approaches based on Bag-Of-Words (BoW) schemes. We also consider different combinations of these methods.
Emilio Garcia-Fidalgo, Alberto Ortiz

Chapter 4. Experimental Setup

Abstract
The topological mapping algorithms presented in this book have been validated using a common framework, featuring several criteria for performance evaluation and a number of relevant public datasets representing different scenarios of operation. The algorithms have as well been compared against some state-of-the-art solutions. The goal of this chapter is to summarize this experimental framework, which will be used to evaluate the solutions proposed in the rest of the book.
Emilio Garcia-Fidalgo, Alberto Ortiz

Chapter 5. Loop Closure Detection Using Local Invariant Features and Randomized KD-Trees

Abstract
This chapter introduces an appearance-based approach for topological mapping and localization named FEATMap (Feature-based Mapping). FEATMap relies on a loop closure detection scheme which makes use of local invariant features to describe images. These features are indexed using a set of randomized kd-trees, which permit seeking for matchings between the current and previous images to detect loop closures in a straightforward way. A discrete Bayes filter is added to the solution to obtain loop candidates while ensuring the temporal coherency between consecutive predictions. Finally, FEATMap comprises a method for refining the resulting maps as they are obtained, removing spurious nodes in accordance to the visual information that they contain.
Emilio Garcia-Fidalgo, Alberto Ortiz

Chapter 6. Loop Closure Detection Using Incremental Bags of Binary Words

Abstract
This chapter introduces a novel method for computing a visual vocabulary online. This binary vocabulary, in combination with an inverted file, conforms an index of images called OBIndex (Online Binary Image Index), which can be used to efficiently retrieve previously seen places. This chapter also presents a topological mapping algorithm called BINMap (Binary Mapping), which makes use of OBIndex as a key component to obtain loop closure candidates during the likelihood computation.
Emilio Garcia-Fidalgo, Alberto Ortiz

Chapter 7. Hierarchical Loop Closure Detection for Topological Mapping

Abstract
This chapter describes a novel appearance-based approach for topological mapping called HTMap (Hierarchical Topological Mapping), which is based on a hierarchical decomposition of the environment. Images with similar appearances are grouped together in locations, taking as a representative of the group the average of the PHOG global descriptors of the represented images, as well as the set of their local features, which are indexed by means of OBIndex (which handles them as explained in the previous chapter). As a main innovation, the algorithm proposes a two-level approach to detect loop candidates: first, the global descriptor of the current image is used to determine the most similar location of the map; next, local image features are employed to determine the most likely image within that location.
Emilio Garcia-Fidalgo, Alberto Ortiz

Chapter 8. Fast Image Mosaicking Using Incremental Bags of Binary Words

Abstract
This chapter introduces a fast and multi-threaded algorithm for image mosaicking called BIMOS (Binary descriptor-based Image MOSaicking) as another example of task where appearance-based loop closure detection is of utmost importance, as it is for vision-based topological mapping. Actually, an image mosaicking process can be seen as a particular case of topological mapping given that the alignment of the images considered, which can be seen as the topology of the image sequence, has to be determined to generate the image composite. To this end, BIMOS makes use of OBIndex to find overlapping pairs. BIMOS has been validated using image sequences from several kinds of environments.
Emilio Garcia-Fidalgo, Alberto Ortiz

Chapter 9. Conclusions and Future Work

Abstract
This chapter summarizes the work done and discusses on the next steps to be undertaken as future work, to further improve the results presented in this book.
Emilio Garcia-Fidalgo, Alberto Ortiz
Weitere Informationen