Real Time Localization and 3D Reconstruction

By E. Mouragnon, Maxime Lhuillier, Michel Dhome, Fabien Dekeyser, Patrick Sayd. Computer Vision and Pattern Recognition, 2006

464 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/72678af7458e4b46a3254d26158f1bd275c2afc6

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

FrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping (2008, methodology): “To construct the skeleton, we start with the sliding bundle adjustment window, which can be computed very efficiently using the marginalization technique of Section III-E [11], [31].”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, unknown): “As such, sensor data extraction, primitive search [9], data association [10] or map storage and updates [11] are part of the topics which concern SLAM as well.”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, unknown): “This was certainly due to [84] and PTAM [57] which demonstrated that a real-time implementation of BA was possible.”
Real-time monocular SLAM: Why filter? (2010, background): “[6], [8]) which fuse measurements from all images sequentially by updating probability distributions over features and camera pose parameters; and bundle adjustment style optimisation over selected images from the live stream, such as a sliding window [18], [20], or in particular spatially distribut”
Visual SLAM: Why filter? (2012, unknown): “Both approaches were used for stereo vision [40,44,31] as well as for monocular vision [9,40,37,27,17,6,49].”
Visual-inertial navigation, mapping and localization: A scalable real-time causal approach (2011, background): “…focuses on augmented reality and therefore does not address large spaces, long-term drift, scale and gravity issues, Konolige and Agrawal (2008) and Mouragnon et al. (2006) that similarly address monocular vision, and Nebot and Durrant-Whyte (1999) that integrates inertial and bearing sensors for…”
Double window optimisation for constant time visual SLAM (2011, background): “In general, keyframes are fixed at the boundary of the active window, and all those keyframes with co-visible points are typically included [13].”
Parallel Tracking and Mapping for Small AR Workspaces (2007, methodology): “When the system is first started, we employ the five-point stereo algorithm of [27] to initialise the map in a manner similar to [20, 18, 9].”
Large-Scale Visual Odometry for Rough Terrain (2007, methodology): “The precision of the estimate can be increase d by keeping some small number of recent frames in a bundle adjustment[9], [16], [23].”
Robust monocular SLAM in dynamic environments (2013, background): “In recent years, lots of optimization methods [11, 40] have been proposed to accelerate BA, where local bundle adjustment involving tens of keyframes and hundreds of 3D points has been proved to be solved at interactive rate [22].”
ORB-SLAM: A Versatile and Accurate Monocular SLAM System (2015, methodology): “On the other hand, keyframe-based approaches [3], [4] estimate the map using only selected frames (keyframes) allowing to perform more costly but accurate BA optimizations, as mapping is not tied to frame rate.”
Vehicle localization using mono-camera and geo-referenced traffic signs (2015, background): “{firstname.lastname}@ign.fr However, the size of equation system increases with the growing number of images and matched points and becomes computationally expensive for large set of images.”
Visual SLAM and Structure from Motion in Dynamic Environments (2018, background): “However, the work of [109, 110, 117] and PTAM [75] brought the two communities together by introducing incremental SfM that can operate in real time.”