Towards training-free appearance-based localization : probabilistic models for whole-image descriptors


Autoria(s): Lowry, Stephanie; Wyeth, Gordon; Milford, Michael
Data(s)

2014

Resumo

Whole image descriptors have recently been shown to be remarkably robust to perceptual change especially compared to local features. However, whole-image-based localization systems typically rely on heuristic methods for determining appropriate matching thresholds in a particular environment. These environment-specific tuning requirements and the lack of a meaningful interpretation of these arbitrary thresholds limits the general applicability of these systems. In this paper we present a Bayesian model of probability for whole-image descriptors that can be seamlessly integrated into localization systems designed for probabilistic visual input. We demonstrate this method using CAT-Graph, an appearance-based visual localization system originally designed for a FAB-MAP-style probabilistic input. We show that using whole-image descriptors as visual input extends CAT-Graph’s functionality to environments that experience a greater amount of perceptual change. We also present a method of estimating whole-image probability models in an online manner, removing the need for a prior training phase. We show that this online, automated training method can perform comparably to pre-trained, manually tuned local descriptor methods.

Formato

application/pdf

Identificador

http://eprints.qut.edu.au/68141/

Publicador

IEEE

Relação

http://eprints.qut.edu.au/68141/1/lowrywyethmilford_icra2014a_final_v2.pdf

DOI:10.1109/ICRA.2014.6906932

Lowry, Stephanie, Wyeth, Gordon, & Milford, Michael (2014) Towards training-free appearance-based localization : probabilistic models for whole-image descriptors. In Proceedings of the 2014 IEEE International Conference on Robotics and Automation (ICRA 2014), IEEE, Hong Kong Convention and Exhibition Center, Hong Kong, pp. 711-717.

Direitos

Copyright 2014 IEEE

Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

Fonte

School of Electrical Engineering & Computer Science; Faculty of Science and Technology

Tipo

Conference Paper