SID-SLAM: Semi-Direct Information-Driven RGB-D SLAM

Fontan, Alejandro ; Giubilato, Riccardo ; Maza, Laura Oliva ; Civera, Javier (Universidad de Zaragoza) ; Triebel, Rudolph

Resumen: This work presents SID-SLAM, a complete SLAM framework for RGB-D cameras. Our main contribution is a semi-direct approach that, for the first time, combines tightly and indistinctly photometric and feature-based image measurements. Additionally, SID-SLAM uses information metrics to reduce the state size with a minimal impact in the accuracy. Our evaluation on several public datasets shows that we achieve state-of-the-art performance regarding accuracy, robustness and computational footprint in CPU real time. In order to facilitate research on semi-direct SLAM, we record the Minimal Texture dataset, composed by RGB-D sequences challenging for current baselines and in which our pipeline excels.

Idioma: Inglés

DOI: 10.1109/LRA.2023.3251722

Año: 2023

Publicado en: IEEE Robotics and Automation Letters 8, 10 (2023), 6387-6394
ISSN: 2377-3766

Factor impacto JCR: 4.6 (2023)

Categ. JCR: ROBOTICS rank: 12 / 46 = 0.261 (2023) - Q2 - T1

Factor impacto CITESCORE: 9.6 - Computer Science Applications (Q1) - Control and Systems Engineering (Q1) - Artificial Intelligence (Q1) - Mechanical Engineering (Q1) - Biomedical Engineering (Q1) - Computer Vision and Pattern Recognition (Q1) - Human-Computer Interaction (Q1) - Control and Optimization (Q1)

Factor impacto SCIMAGO: 2.119 - Artificial Intelligence (Q1) - Biomedical Engineering (Q1) - Computer Science Applications (Q1) - Mechanical Engineering (Q1) - Control and Optimization (Q1) - Control and Systems Engineering (Q1) - Human-Computer Interaction (Q1) - Computer Vision and Pattern Recognition (Q1)

Financiación: info:eu-repo/grantAgreement/ES/DGA/T45-20R
Financiación: info:eu-repo/grantAgreement/ES/MICINN/PID2021-127685NB-I00
Financiación: info:eu-repo/grantAgreement/EUR/MICINN/TED2021-131150B-I00

Tipo y forma: Artículo (PostPrint)

Área (Departamento): Área Ingen.Sistemas y Automát. (Dpto. Informát.Ingenie.Sistms.)