Real-time simultaneous localisation and mapping with a single camera

By Andrew J. Davison. Proceedings Ninth IEEE International Conference on Computer Vision, 2003

2,034 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/102e50c2c9a8e3d00de64a26759916c926fa3db6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM (2018, background): “The validation of the two-frame reconstruction performance is of high importance as it is directly connected to the initialisation procedure of the full SLAM system.”
An Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics (2015, background): “Indeed, variety of solutions using different visual sensors including monocular [28], stereo [78], omni-directional [70], time of ﬂight (TOF) [103] and combined color and depth (RGB-D) cameras [56] have been proposed.”
REMODE: Probabilistic, monocular dense reconstruction in real time (2014, neutral): “The problem of reconstructing the scene from images collected by a moving camera has been studied for more than two decades and is known as Structure from Motion in computer vision [1] and Monocular SLAM in robotics [2].”
Particle Filter SLAM with High Dimensional Vehicle Model (2009, background): “, [9–11, 17], and the second way is to fuse measurements from several sensors.”
Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications (2012, background): “The motion can be given by an additional sensor like IMU, wheel odometry [25], laser, and GPS, or can be inferred from the previous position assuming a constant velocity model, as proposed in [26].”
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM (2020, methodology): “Monocular SLAM was ﬁrst solved in MonoSLAM [13], [14], [53] using an Extended Kalman Filter (EKF) and Shi-Tomasi points that were tracked in subsequent images doing a guided search by correlation.”
Scale Drift-Aware Large Scale Monocular SLAM (2010, background): “Special attention was given to feature initialisation schemes which permitted sequential probabilistic filtering of the joint camera and map state [7] [28] [20].”
Visual SLAM: Why filter? (2012, positive): “Note that in both systems, as opposed to MonoSLAM [9, 11] and derived work, no motion prior is enforced.”
KinectFusion: Real-time dense surface mapping and tracking (2011, background): “Such ‘monocular SLAM’ systems such as MonoSLAM [8] and the more accurate Parallel Tracking and Mapping (PTAM) system [17] allow researchers to investigate ﬂexible infrastructure-and marker-free AR applications.”
Robust reconstruction of indoor scenes (2015, methodology): “The influential KinectFusion system demonstrated realtime dense reconstruction with a consumer depth camera [46], building on earlier work on range image integration [14], visual odometry [15, 48, 38], and real-time 3D reconstruction [51, 49, 45].”
Visual simultaneous localization and mapping: a survey (2012, methodology): “Clemente et al. (2007) propose an alternative to use the MonoSLAM in large outdoor environments.”
Real-time Localization in Outdoor Environments using Stereo Vision and Inexpensive GPS (2006, background): “[4] and [14] uses these corner tracks for monocular cameras.”
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects (2013, methodology): “Sparse feature ﬁltering methods like [5] were improved on by ‘keyframe SLAM’ systems like PTAM [8] which used bundle adjustment in parallel with tracking to enable high feature counts and more accurate tracking.”
Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback (2017, methodology): “Along the lines of other landmark-based visual odometry approaches (Davison (2003)) we model landmarks as distinguished stationary 3D locations in the environment.”
A survey on vision-based UAV navigation (2018, background): “Davison (2003) presented a top-down Bayesian framework for single camera localization with real-time performance via mapping a sparse set of natural features.”
Real-Time Monocular SLAM with Straight Lines (2006, methodology): “The statistics of measuring this depth are non-Gaussian, so Davison [5] represents the uncertainty in new points using a one-dimensional particle filter along the world ray that corresponds to the detected feature and updates this until it has converged enough to be represented by a single Gaussian.”
Keyframe-based visual–inertial odometry using nonlinear optimization (2015, methodology): “Due to computational constraints, for a long time, vision-based real-time odometry or SLAM algorithms such as those presented by Davison (2003) were only possible using a filtering approach.”