Parallel Tracking and Mapping for Small AR Workspaces

By Georg S. W. Klein, David William Murray. 2007

4,755 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

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

In Geology

Citations in the corpus

(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image (2016, background): “Monocular cameras, on the other hand, require 3D estimation from motion, which remains a challenging open problem despite considerable recent progress [13, 20].”
Learning to fly by crashing (2017, methodology): “For this purpose, we use PTAM [27] module that localizes the robot and helps it backtrack.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “Some methods approximately decouple localization and mapping in two threads that run in parallel like Klein and Murray [135].”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, positive): “[84] and [92] proposed to perform the BA only on a sliding window (which may lead to a camera drift) while Parallel Tracking and Mapping (PTAM) [57] considers in parallel a local BA with a tracking method that involves only a localization process as in 3.1.2 with points that have been already recons”
DTAM: Dense tracking and mapping in real-time (2011, methodology): “In comparison to the nearly 300× 10(3) points estimated in our keyframe, we show the ≈ 1000 point features used in the same frame for localisation in PTAM ([6]).”
Visual-Inertial Sensor Fusion: Localization, Mapping and Sensor-to-Sensor Self-calibration (2011, methodology): “Klein and Murray (2007) propose parallel tracking and mapping, where localization and mapping are run as separate, asynchronous processes to improve performance.”
Unifying Map and Landmark Based Representations for Visual Navigation (2017, background): “Extending this to the setting of unknown environments, simultaneous localization and mapping (SLAM) algorithms [7,9,10,13,19] aim to both construct a map and localize the robot.”
A robust RGB-D SLAM algorithm (2012, background): “Klein and Murray [12] addressed the problem of rapid camera motion by separating the tracking and mapping problem.”
Dense visual SLAM for RGB-D cameras (2013, methodology): “The second group uses batch optimization to refine feature locations and camera poses [27], [28].”
iMAP: Implicit Mapping and Positioning in Real-Time (2021, methodology): “Our iMAP system is designed with a keyframe structure and multi-processing computation flow reminiscent of PTAM [11].”
Maplab: An Open Framework for Research in Visual-Inertial Mapping and Localization (2017, background): “One of the earliest examples is PTAM [21], a lightweight approach for mapping and tracking a local map in parallel.”
Vision-based state estimation for autonomous rotorcraft MAVs in complex environments (2013, methodology): “To our knowledge, the only functional monocular visionbased autonomous rotorcraft MAV is proposed in [7] and uses a modified version of the Parallel Tracking and Mapping (PTAM) software [8] for pose estimation using a downwardfacing camera.”
Vision based MAV navigation in unknown and unstructured environments (2010, background): “[25] in order to localize the MAV from a single camera (see Fig.”
Made to measure: Bespoke landmarks for 24-hour, all-weather localisation with a camera (2016, methodology): “Numerous SLAM approaches using combinations of these feature detectors and descriptors have been demonstrated [16][17][18].”
Large-scale direct SLAM with stereo cameras (2015, background): “Another example of sparse monocular SLAM is Parallel Tracking and Mapping (PTAM [4]) which separates and parallelizes optimization for tracking and mapping in a bundle adjustment framework.”
A Comprehensive Survey of Visual SLAM Algorithms (2022, methodology): “Another pioneer algorithm is the Parallel Tracking and Mapping (PTAM) [36] algo-rithm.”
Comprehensive Simulation of Quadrotor UAVs Using ROS and Gazebo (2012, methodology): “Visual SLAM To demonstrate simulated image based state estimation, we deploy a modified version [22] of the original PTAM system [13] for visual SLAM.”
Towards a benchmark for RGB-D SLAM evaluation (2011, neutral): “Simultaneous localization and mapping (SLAM) has a long history in robotics and computer-vision research [11], [6], [1], [15], [7], [4].”