FAB-MAP: Appearance-based place recognition and mapping using a learned visual vocabulary model

37Citations
Citations of this article
122Readers
Mendeley users who have this article in their library.

Abstract

We present an overview of FAB-MAP, an algorithm for place recognition and mapping developed for infrastructure-free mobile robot navigation in large environments. The system allows a robot to identify when it is revisiting a previously seen location, on the basis of imagery captured by the robot's camera. We outline a complete probabilistic framework for the task, which is applicable even in visually repetitive environments where many locations may appear identical. Our work introduces a number of technical innovations - notably we demonstrate that place recognition performance can be improved by learning an approximation to the joint distribution over visual elements. We also investigate severed principled approaches to making the system robust in visually repetitive environments, and define an efficient bail-out strategy for multi-hypothesis testing to improve system speed. Our model has been shown to substantially outperform standard tf-idf ranking on our task of interest. We demonstrate the system performing reliable online appearance mapping and loop closure detection over a 1,000 km trajectory, with mean filter update times of 14 ms. Copyright 2010 by the author(s)/owner(s).

References Powered by Scopus

SURF: Speeded up robust features

9571Citations
N/AReaders
Get full text

Video google: A text retrieval approach to object matching in videos

5685Citations
N/AReaders
Get full text

Simultaneous localization and mapping: Part I

3661Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Real-time large-scale dense RGB-D SLAM with volumetric fusion

361Citations
N/AReaders
Get full text

Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map

141Citations
N/AReaders
Get full text

Robust Visual Localization Across Seasons

113Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Cummins, M., & Newman, P. (2010). FAB-MAP: Appearance-based place recognition and mapping using a learned visual vocabulary model. In ICML 2010 - Proceedings, 27th International Conference on Machine Learning (pp. 3–10).

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 86

78%

Researcher 19

17%

Professor / Associate Prof. 4

4%

Lecturer / Post doc 1

1%

Readers' Discipline

Tooltip

Computer Science 74

67%

Engineering 35

32%

Agricultural and Biological Sciences 1

1%

Environmental Science 1

1%

Save time finding and organizing research with Mendeley

Sign up for free