Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual Landmarks

By Stephen Se, David G. Lowe, James J. Little. Int. J. Robotics Res., 2002

932 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ec7230b7bc28df22d7045b5b1b70a44ebd950112

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

1. Cordelia Schmid
2. Andrew Zisserman
3. Jiri Matas
4. Krystian Mikolajczyk
5. Luc Van Gool
6. David G. Lowe
7. Pascal Fua
8. Tinne Tuytelaars

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Andrew Zisserman
3. Cordelia Schmid
4. Andrea Vedaldi
5. Li Fei-Fei
6. Jitendra Malik
7. Trevor Darrell
8. Dacheng Tao

Citations in the corpus

• Visual Place Recognition: A Survey (2016, methodology): “SIFT features as in [76], CenSurE features as in FrameSLAM [2], or ORB features [137] as in ORB-SLAM [136].”
• Cooperative Localization in Wireless Networks (2009, background): “A state usually includes the two- or three-dimensional posit ion, and possibly other properties such as the velocity and the orientation of the node [16]–[18].”
• Monocular Vision for Mobile Robot Localization and Autonomous Navigation (2007, methodology): “Real-time SLAM using only monocular vision has been achieved by Davison [5], but only for a small environment with less than 100 landmarks.”
• 50 Years of object recognition: Directions forward (2013, background): “Local image-based features are also used for vision based localization and mapping with some success [165], [166], [167] and are currently quite popular in content-based image retrieval [168].”
• Incremental smoothing and mapping (2008, methodology): “[120, 121] that uses SIFT features in combination with a trinocular sensor.”
• Real-time Localization in Outdoor Environments using Stereo Vision and Inexpensive GPS (2006, methodology): “SLAM can be performed using different types of sensors such as sonar [20], laser range finders [22] and vision [18, 4, 19].”
• Two years of Visual Odometry on the Mars Exploration Rovers (2007, background): “Lowe’s work on scale invariant features is one possible approach (Se et al., 2002).”
• The SLAM problem: a survey (2008, methodology): “Feature tracking is the problem of estimating the locations of features in an image sequence (for instance, Harris corner detector and Random Sample Consensus (RANSAC), Scale Invariant Feature Transform (SIFT) [ 15 ] or Speeded-up Robust Features (SURF) [31]).”
• Vision-Based SLAM: Stereo and Monocular Approaches (2007, methodology): “In Se et al. (2002), an approach that uses scale invariant features (SIFT) is depicted, with results obtained by a robot evolving in 2D in a 10 × 10 m 2 laboratory environment, in which about 3500 landmarks are mapped in 3D.”
• Visual Navigation for Mobile Robots: A Survey (2008, background): “During the robot navigation process, detected invariant features are observed from different points of view, angles, distances and under different illumination conditions and thus become highly appropriate landmarks to be tracked for navigation, global localization [117] and robust vision-based SLAM”
• Visual simultaneous localization and mapping: a survey (2012, background): “The first works on visual navigation were based on a binocular stereo configuration (Se et al. 2002; Olson et al. 2003).”
• A Comparison of Affine Region Detectors (2005, background): “The requirement for these regions is that they should correspond to the same pre-image for different viewpoints, i.e., their shape is not fixed but automatically adapts, based on the underlying image intensities, so that they are the projection of the same 3D surface patch.”
• Evaluation of Features Detectors and Descriptors based on 3D Objects (2005, methodology): “To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically.”
• Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking (2011, methodology): “Se et al. (2002) SLAM/trinocular camera DoG [scale, orientation] LSE, Kalman filter Skrypnyk and Lowe (2004) tracking/known scene DoG SIFT RANSAC, non-lin.”
• Vision-based global localization and mapping for mobile robots (2005, methodology): “SIMULTANEOUS LOCALIZATION AND MAPPING Our vision-based mobile robot localization and mapping system uses SIFT visual landmarks in unmodified environments [25].”