Results 171 to 180 of about 13,782 (194)

An Improved ORB-SLAM2 With Refined Depth Estimation

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR), 2019
We present a novel VSLAM system based on ORB-SLAM2. Firstly, the uncertainties of the position estimate of the 3D feature points by triangulation are computed through the propagation of covariance matrix. Then, the value of the triangulated depth and the variance of depth are updated by an information refining method from multiple triangulations.
Kaitao Tang, Jing Yuan, Qinxuan Sun, Xuebo Zhang, Haiming Gao   +4 more
openaire   +1 more source

Dense point cloud map construction based on ORB-SLAM2 and cross-attention network

IET Conference Proceedings
Yizheng Liu, Qinghua Su, Yue Song, Pengbo Zhang, Zhihao Xie, Liyong Wang   +5 more
openaire   +2 more sources

Comparison of Visual SLAM Algorithms ORB-SLAM2, RTAB-Map and SPTAM in Internal and External Environments with ROS

Latin American Robotics Symposium, 2021
This work compares three visual Simultaneous Localization and Mapping (vSLAM) algorithms: RTAB-Map, ORB-SLAM2 and SPTAM. Simulations were carried out in an indoor and an outdoor environment on gazebo using ROS (Robot Operating System).
Kesse Jonatas de Jesus, Henry Julio Kobs, A. Cukla, M. A. Cuadros, D. Gamarra   +4 more
semanticscholar   +1 more source

An Acceleration Method Using CUDA based on ORB-SLAM2

2019 IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 2019
In order to solve the problem of poor real-time performance and low position accuracy when mobile robots apply the technology of simultaneous localization and mapping, this paper proposed an improved algorithm using CUDA parallel computing to do the ORB feature extraction and matching portion to reduce the running time of the algorithm based on open ...
Zhenzhen Li, Lei Zhang, Chenglong Xu, Fengshan Zou, Jilai Song, Daji Tian   +5 more
openaire   +1 more source

A Pose Estimation Method in Dynamic Scene with Yolov5, Mask R-CNN and ORB-SLAM2

IEEE International Conference on Signal and Image Processing, 2022
Most visual SLAM systems exhibit strong robustness in static scenes. When there are dynamic objects in the scene, these systems tend to treat dynamic objects as static backgrounds for pose estimation, which reduces the accuracy of pose estimation.
Junchao Zhu, Yongxing Jia, Weixiang Shen, Xiaojian Qian   +3 more
semanticscholar   +1 more source

Autonomous Navigation Using Monocular ORB SLAM2

2019
Simultaneous Localisation and Mapping (SLAM) is the mapping of an unknown environment and at the same time localising the ego body in that environment. ORB SLAM2 (IEEE Trans Robot 33:1255–1262 2017 [1]) is a state of the art visual SLAM algorithm which can calculate camera trajectory using Monocular camera.
Shubham Vithalani, Sneh Soni, Param Rajpura   +2 more
openaire   +1 more source

SFD-SLAM: an improved sparse semi-direct method based on ORB-SLAM2

International Conference on Signal Processing and Computer Science
The trend toward larger ships in the maritime industry has resulted in significant challenges for robots' self-localization capabilities due to occlusion and metal interference in the extensive bottom areas.
Jiaqi Mao, Lifei Song, Jilong Hu
semanticscholar   +1 more source

An Improved ORB-SLAM2 in Dynamic Scene with Instance Segmentation

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS), 2019
In order to improve the accuracy of ORB-SLAM2 poses estimation in dynamic environment, an Instance Segmentation method is proposed to remove the moving feature points distributed on the human body and improve the pose accuracy in view of the deception of motion.
Huaming Qian, Peng Ding
openaire   +1 more source

A Graph-Attention Frontend for ORB-SLAM2 under Large Viewpoint Changes

Advances in Artificial Intelligence and Machine Learning
This paper presents a visual SLAM system that augments the ORB-SLAM2 frontend with learned detection and matching while preserving the standard backend.
Giuseppe Macario
semanticscholar   +1 more source

An Improved ORB-SLAM2 Algorithm Based on Extended Kalman Filtering and Particle Swarm Optimization

Image and Vision Computing New Zealand
To address the challenges of pose estimation jitter and cumulative errors in visual SLAM systems operating in complex dynamic environments, this paper proposes an enhanced ORB-SLAM2 algorithm that integrates an Extended Kalman Filter (EKF)-based frontend
Hongyan Chen, W. Yan, Qinjun Zhao, Yueyang Li   +3 more
semanticscholar   +1 more source