Results 91 to 100 of about 13,782 (194)
Semisupervised Vector Quantization in Visual SLAM Using HGCN
International Journal of Intelligent Systems, Volume 2024, Issue 1, 2024.We present a novel vector quantization (VQ) module for the two state‐of‐the‐art long‐range simultaneous localization and mapping (SLAM) algorithms. The VQ task in SLAM is generally performed using unsupervised methods. We provide an alternative approach trough embedding a semisupervised hyperbolic graph convolutional neural network (HGCN) in the VQ ...
Amir Zarringhalam +4 more
wiley +1 more source
IEEE Access, 2019 When mobile robots are working in indoor unknown environments, the surrounding scenes are mainly low texture or repeating texture. This means that image features are easily lost when tracking the robots, and poses are difficult to estimate as the robot ...
Chang Chen, Hua Zhu, Lei Wang, Yu Liu
doaj +1 more source
Non-iterative RGB-D-inertial Odometry
, 2018 This paper presents a non-iterative solution to RGB-D-inertial odometry system. Traditional odometry methods resort to iterative algorithms which are usually computationally expensive or require well-designed initialization.
Hoang, Minh-Chung +3 more
core
An edge awareness-enhanced visual SLAM method for underground coal mines
Meitian dizhi yu kantanObjectiveUnderground coal mines commonly exhibit low illuminance, weak textures, and structuralization-induced feature degradation. These scenes lead to challenges of insufficient effective features and high mismatch rates to the visual simultaneous ...
Qi MU +4 more
doaj +1 more source
Indoor mobile robot localization system based on ORB-SLAM3 and multi-sensor fusion
Alexandria Engineering JournalIndoor localization is a fundamental capability for autonomous mobile robots operating in complex indoor environments, where visual degradation, sensor noise, and rotational motion often lead to accumulated drift.
Siyong Fu +5 more
doaj +1 more source
Spacecraft/Rover Hybrids for the Exploration of Small Solar System Bodies [PDF]
This study investigated a mission architecture that allows the systematic and affordable in-situ exploration of small solar system bodies, such as asteroids, comets, and Martian moons (Figure 1). The architecture relies on the novel concept of spacecraft/
Castillo-Rogez, Julie C. +4 more
core +1 more source
Obdelava in prikaz zemljevida značilk, pridobljenega s postopkom ORB-SLAM2
, 2023 Diplomsko delo zajema opis kamere Microsoft Kinect in RealSense d_435, programskega jezika Python in knjižnice Open3d, algoritma ORB-SLAM2 in okolja ROS. Sledi opis postopka kalibracije kamere Kinect in opis programa za shranjevanje zemljevida značilk. Diplomsko delo vsebuje primerjavo globinskega dometa prej omenjenih kamer. Opisan je RANSAC algoritem
openaire +1 more source
ORB-SLAM2 vs ARCore, Comparativa y extensión
, 2018 Este trabajo, como ya se ha comentado, está basado en el estudio de dos librerías concretas, ORB-SLAM2 y ARCore. El motivo por el cual se han elegido dichas librerías es que ambas son bastantes representativas en su dominio de aplicación. ARCore de Google es una librería moderna que se usa sólamente en dispositivos móviles y es multiplataforma.
openaire +1 more source
Research on SLAM Localization Algorithm for Orchard Dynamic Vision Based on YOLOD-SLAM2
AgricultureWith the development of agriculture, the complexity and dynamism of orchard environments pose challenges to the perception and positioning of inter-row environments for agricultural vehicles.
Zhen Ma +3 more
doaj +1 more source
Redes neuronales profundas para mejorar la robustez de ORB-SLAM2
, 2019 Los sistemas de SLAM (Simultaneous Localization And Mapping) permiten la generación de unmapa sobre un entorno desconocido mientras se calcula la localización del agente en ese mismo espacio. El sistema ORB-SLAM2, desarrollado por la Universidad de Zaragoza, permite la generación de estos mapas utilizando cámaras como únicos sensores.
Izquierdo Barranco, Sergio +1 more
openaire +1 more source