• Corpus ID: 63149974

Real-time 3D visual SLAM with a hand-held camera

  title={Real-time 3D visual SLAM with a hand-held camera},
  author={Nikolas Engelhard and Felix Endres and J{\"u}rgen Hess and J{\"u}rgen Sturm and Wolfram Burgard},
Crowd-sensing Simultaneous Localization and Radio Fingerprint Mapping based on Probabilistic Similarity Models
A novel approach for crowd-sensing simultaneous localization and radio fingerprint mapping (C-SLAM-RF) in large unknown indoor environments and is capable of estimating the tracks of a group of users with an accuracy of 1.74 meters when compared to the ground truth acquired from a point cloud-based SLAM.
Augmenting Visual SLAM with Wi-Fi Sensing For Indoor Applications
This work proposes a generic way to integrate Wi-Fi sensing into visual SLAM algorithms and shows that this approach can improve the accuracy of visualSLAM algorithms by 11% on average and reduce computation time on average by 15% to 25%.
Intelligent Robotics and Applications
A robust backstepping control scheme is designed to solve the rendezvous problem and theoretical analysis and numerical simulation validate the effectiveness of the proposed method.
3D Visual SLAM Based on Multiple Iterative Closest Point
The motion of the RGB-D camera is estimated by a motion capture system after a calibration process, and the MICP algorithm is used to improve the alignment and the 3D map can be generated in real time.
Statistical modelling for enhanced outlier detection
A noniterative scheme for outlier detection that includes in the distance calculation the location uncertainty of the keypoint, specifically modeled by a covariance matrix: the LDR is then evaluated relying on Mahalanobis distance.
Application of Octree Map in Robotic Environment Reconstruction
  • Yi Cheng, Xiaoyu Tong
  • Computer Science
    2018 IEEE 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER)
  • 2018
The binarized data form of the octree map, which can effectively optimize the reconstruction of the unknown environment mapping for a mobile robot, is used in RGB-D SLAM to realize the localization and mapping of the robot in this paper.
Fourier Volume Registration based Dense 3D Mapping
A novel volume registration technique is proposed for solving the simultaneous localization and mapping (SLAM) problem which utilises 3D phase correlation and provides high noise robustness, even in the presence of moving objects within the scene which are problematic for SLAM systems.
Noise in Structured-Light Stereo Depth Cameras: Modeling and its Applications
This paper validate this theoretical model against empirical observations and demonstrate the utility of this noise model in three popular applications: depth map denoising, volumetric scan merging for 3D modeling, and identification of 3D planes in depth maps.
Building a 3 D Map from RGB-D Sensors
This study will see how a 3D map based on a graphical model can be built by tracking visual features like SIFT/SURF, computing geometric transformations with RANSAC, and applying non-linear optimization techniques to estimate the trajectory.
Adaptive RGB-D Localization
  • M. Paton, J. Kosecka
  • Computer Science
    2012 Ninth Conference on Computer and Robot Vision
  • 2012
An adaptive architecture which computes the pose estimate from the most reliable measurements in a given environment is proposed and thorough evaluation of the resulting algorithm is presented against a dataset of RGB-D benchmarks, demonstrating superior or comparable performance in the absence of the global optimization stage.