Fast and Incremental Method for Loop-Closure Detection Using Bags of Visual Words

By Adrien Angeli, David Filliat, Stéphane Doncieux, Jean-Arcady Meyer. 2008

564 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

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

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning (2019, background): “In robotics, one often needs to locate or navigate itself by interpreting a map of the world [61, 87, 3].”
Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map (2018, methodology): “Visual methods have been commonly used for place recognition in SLAM literatures [13, 14, 15].”
On-line regression algorithms for learning mechanical models of robots: A survey (2011, methodology): “With respect to standard gmr , the main advantage of ilo - gmr lies in an e ﬃ cient partitioning of the set of samples into regions based on an algorithm similar to kd-trees described in Angeli et al. [2].”
Appearance-only SLAM at large scale with FAB-MAP 2.0 (2011, background): “Appearancebased navigation and loop-closure detection systems operating on trajectories on the order of a few kilometers in length are now commonplace (Angeli et al. 2008; Fraundorfer et al. 2007; Callmer et al. 2008; Zhu et al. 2007; Magnusson et al. 2009).”
Scale Drift-Aware Large Scale Monocular SLAM (2010, background): “It is well known that loop closures can be detected effectively using appearance information only [1, 5].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “The Lip6Indoor and Lip6Outdoor datasets are obtained from Angeli et al. (2008).”
Incremental local online Gaussian Mixture Regression for imitation learning of multiple tasks (2010, methodology): “During training in this approach, data points are stored incrementally in a data structure which allows for very fast approximate nearest neighbors retrieval (e.g. such as in [21]).”
Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection (2020, unknown): “In a SLAM system, the estimation of robot’s state and trajectory often comes with inevitable drift that fails localization easily [1].”
Bags of Binary Words for Fast Place Recognition in Image Sequences (2012, methodology): “We apply an epipolar constraint to the best matching candidate as done in [4], but we take advantage of a direct index to calculate correspondence points faster.”
Highly scalable appearance-only SLAM - FAB-MAP 2.0 (2009, background): “Many systems have now been demonstrated operating at scales around a kilometer [7], [8], [9], [10].”
Real-time monocular SLAM: Why filter? (2010, background): “[5], [1]) which can be formulated independently from metric SLAM systems.”
Visual Place Recognition: A Survey (2016, methodology): “its widespread use in place recognition [76]–[83].”
Convolutional Neural Network-based Place Recognition (2014, methodology): “State-of-the-art visual SLAM algorithms such as FAB-MAP [Cummins and Newman, 2008] match the appearance of the current scene to a past place by converting the image into bag-of-words representations [Angeli, et al., 2008] built on local features such as SIFT or SURF.”
Online global loop closure detection for large-scale multi-session graph-based SLAM (2014, background): “Popular global loop detection approaches are appearance-based [9]– [12], exploiting the distinctiveness of images.”
Appearance-Based Loop Closure Detection for Online Large-Scale and Long-Term Operation (2013, methodology): “The feature response is used to select the most prominent features in the image.”
Persistent Navigation and Mapping using a Biologically Inspired SLAM System (2010, methodology): “As a primarily appearance-based SLAM system, it is one of a number of recent appearance-based systems (Andreasson et al., 2008 Angeli et al., 2008 Cummins and Newman, 2008 Mahon et al., 2008) that have been catching up to large-scale metric mapping systems.”