FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance

By Mark Joseph Cummins, Paul M. Newman. 2008

1,604 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Variational Inference: A Review for Statisticians (2016, background): “…Wang and Mori 2009), image denoising (Likas and Galatsanos 2004), tracking (Vermaak, Lawrence, and Pérez 2003; Yu and Wu 2005), place recognition and mapping for robotics (Cummins and Newman 2008; Ramos et al. 2012), and image segmentation with Bayesian nonparametrics (Sudderth and Jordan 2009).”
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition (2015, background): “Visual place recognition has received a significant amount of attention in the past years both in computer vision [5, 10, 11, 24, 35, 62, 63, 64, 65, 79, 80] and robotics communities [16, 17, 44, 46, 74] motivated by, e.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “Short-term data association is responsible for associating corresponding features in consecutive sensor measurements; for instance, short-term data association would track the fact that 2 pixel measurements in consecutive frames are picturing the same 3D point.”
Privacy Preserving Image-Based Localization (2019, background): “Localizing a device within a scene by computing the camera pose from an image is a fundamental problem in computer vision, with high relevance in applications such as robotics [16, 19, 65], augmented/mixed reality (AR/MR) [36, 46], and structure from motion (SfM) [25, 61, 63].”
Are We There Yet? Challenging SeqSLAM on a 3000 km Journey Across All Four Seasons (2013, background): “While established state of the art approaches to place recognition like FAB-MAP [1] match single images, recent work of Milford and Wyeth [2] proposes to match sequences of images.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “Some work focus on the loop closure detection in specific (Cummins & Newman (2008); Paul & Newman (2010); Lee et al. (2013b)) which will be discussed in detail in Section 8.4.1.”
The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset (2019, methodology): “The trajectories were generated by optimising robust VO [20], visual loop closures [21], and GPS/INS as constraints.”
Visual Place Recognition: A Survey (2016, methodology): “FAB-MAP [6], [87] is a probabilistic appearance-based localization system that uses a data-driven approach to calculating an observational likelihood.”
Convolutional Neural Network-based Place Recognition (2014, methodology): “State-of-the-art SLAM systems such as FAB-MAP [Cummins and Newman, 2008] further represent appearance data using sets of local features, converting images into “bag-of-words”, which enables efficient retrieval.”
Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition (2021, methodology): “Patch-NetVLAD won the Mapillary Challenge at the ECCV2020 workshops (not yet publicly announced to comply with CVPR’s double-blind policy), with Table 1 showing that Patch-NetVLAD outperformed the baseline method, NetVLAD, by 13.0% (absolute R@1 increase) on the withheld test dataset.”
Geometry-Aware Learning of Maps for Camera Localization (2017, methodology): “Examples include 3D landmarks for general visual SLAM methods [34, 35, 42], 3D lines and patches in semi-dense SLAM methods and indoor scenes [20, 43, 56], object-level context in semantic SLAM methods [10, 45], bag of visual word features on key frames for camera relocalization [12, 46, 47].”
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition (2018, methodology): “A two-step approach is commonly used in image based localization [34, 33, 37, 50] - (1) place recognition [9, 8, 25, 46, 12], followed by (2) pose estimation [14].”
Self-Supervised Visual Descriptor Learning for Dense Correspondence (2017, methodology): “Existing SLAM systems that utilize feature descriptors have traditionally used hand-engineered features, such as ORB-SLAM [16], FabMap [5], and BundleFusion [6].”
LDSO: Direct Sparse Odometry with Loop Closure (2018, methodology): “However, FAB-MAP needs to extract its own features and cannot re-use any information from the VO frontend, and the constraint computation in turn does not re-use the feature matches, but relies on direct image alignment using the semi-dense depth maps of candidate frames in both directions and a sta”
Robust map optimization using dynamic covariance scaling (2013, background): “Generating outlier-free graphs in the front-end, however, is very challenging, especially in environments showing selfsimilar structures [5], [6], [7].”
Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map (2018, methodology): “FAB-MAP [13] increased robustness with the probabilistic approach by learning a generative model for the bag of visual words.”
The three-dimensional normal-distributions transform : an efficient representation for registration, surface analysis, and loop detection (2009, methodology): “The SLAM-style experiment on the same data set is more similar to those of Cummins and Newman [24].”