RT Journal Article
T1 Appearance-Based Sequential Robot Localization Using a Patchwise Approximation of a Descriptor Manifold
A1 Jaenal, Alberto
A1 Moreno, Francisco-Angel
A1 Gonzalez-Jimenez, Javier
K1 Appearance-based localization
K1 Computer vision
K1 Gaussian processes
K1 Manifold learning
K1 Robot vision systems
K1 Indoor positioning
K1 Image manifold
K1 Descriptor manifold
K1 Aprendizaje
K1 Descriptores
K1 Reconocimiento de normas patrones automatizadas
K1 Ambiente
K1 Métodos
K1 Inteligencia artificial
AB This paper addresses appearance-based robot localization in 2D with a sparse, lightweight map of the environment composed of descriptor-pose image pairs. Based on previous research in the field, we assume that image descriptors are samples of a low-dimensional Descriptor Manifold that is locally articulated by the camera pose. We propose a piecewise approximation of the geometry of such Descriptor Manifold through a tessellation of so-called Patches of Smooth Appearance Change (PSACs), which defines our appearance map. Upon this map, the presented robot localization method applies both a Gaussian Process Particle Filter (GPPF) to perform camera tracking and a Place Recognition (PR) technique for relocalization within the most likely PSACs according to the observed descriptor. A specific Gaussian Process (GP) is trained for each PSAC to regress a Gaussian distribution over the descriptor for any particle pose lying within that PSAC. The evaluation of the observed descriptor in this distribution gives us a likelihood, which is used as the weight for the particle. Besides, we model the impact of appearance variations on image descriptors as a white noise distribution within the GP formulation, ensuring adequate operation under lighting and scene appearance changes with respect to the conditions in which the map was constructed. A series of experiments with both real and synthetic images show that our method outperforms state-of-the-art appearance-based localization methods in terms of robustness and accuracy, with median errors below 0.3 m and 6°.
PB MDPI
YR 2021
FD 2021-04-02
LK http://hdl.handle.net/10668/3818
UL http://hdl.handle.net/10668/3818
LA en
NO Jaenal A, Moreno FA, Gonzalez-Jimenez J. Appearance-Based Sequential Robot Localization Using a Patchwise Approximation of a Descriptor Manifold. Sensors. 2021 Apr 2;21(7):2483
DS RISalud
RD Apr 6, 2025