Shranjeno v:
Bibliografske podrobnosti
Main Authors: Crocetti, Francesco, Dionigi, Alberto, Brilli, Raffaele, Costante, Gabriele, Valigi, Paolo
Format: Preprint
Izdano: 2025
Teme:
Online dostop:https://arxiv.org/abs/2502.13708
Oznake: Označite
Brez oznak, prvi označite!
_version_ 1866914026821255168
author Crocetti, Francesco
Dionigi, Alberto
Brilli, Raffaele
Costante, Gabriele
Valigi, Paolo
author_facet Crocetti, Francesco
Dionigi, Alberto
Brilli, Raffaele
Costante, Gabriele
Valigi, Paolo
contents Visual Odometry (VO) and Visual SLAM (V-SLAM) systems often struggle in low-light and dark environments due to the lack of robust visual features. In this paper, we propose a novel active illumination framework to enhance the performance of VO and V-SLAM algorithms in these challenging conditions. The developed approach dynamically controls a moving light source to illuminate highly textured areas, thereby improving feature extraction and tracking. Specifically, a detector block, which incorporates a deep learning-based enhancing network, identifies regions with relevant features. Then, a pan-tilt controller is responsible for guiding the light beam toward these areas, so that to provide information-rich images to the ego-motion estimation algorithm. Experimental results on a real robotic platform demonstrate the effectiveness of the proposed method, showing a reduction in the pose estimation error up to 75% with respect to a traditional fixed lighting technique.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Active Illumination for Visual Ego-Motion Estimation in the Dark
Crocetti, Francesco
Dionigi, Alberto
Brilli, Raffaele
Costante, Gabriele
Valigi, Paolo
Robotics
Visual Odometry (VO) and Visual SLAM (V-SLAM) systems often struggle in low-light and dark environments due to the lack of robust visual features. In this paper, we propose a novel active illumination framework to enhance the performance of VO and V-SLAM algorithms in these challenging conditions. The developed approach dynamically controls a moving light source to illuminate highly textured areas, thereby improving feature extraction and tracking. Specifically, a detector block, which incorporates a deep learning-based enhancing network, identifies regions with relevant features. Then, a pan-tilt controller is responsible for guiding the light beam toward these areas, so that to provide information-rich images to the ego-motion estimation algorithm. Experimental results on a real robotic platform demonstrate the effectiveness of the proposed method, showing a reduction in the pose estimation error up to 75% with respect to a traditional fixed lighting technique.
title Active Illumination for Visual Ego-Motion Estimation in the Dark
topic Robotics
url https://arxiv.org/abs/2502.13708