Appearance-based place recognition for topological localization

By Iwan Ulrich, Illah Reza Nourbakhsh. Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065), 2000

637 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/3a8c09b65338e4bf3c7c36e85e2c2ee45049a23d

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 Electrical and Electronic Engineering

Citations in the corpus

Appearance-only SLAM at large scale with FAB-MAP 2.0 (2011, background): “While appearance-based navigation has a long history within robotics (Dudek and Jugessur 2000; Ulrich and Nourbakhsh 2000), there has been considerable development in the field in the last five years.”
Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm (2005, neutral): “From these couplings accurate relative solute geometries and information about solute conformational change can be obtained.”
Multiple‐Robot Simultaneous Localization and Mapping: A Review (2016, methodology): “It can also be used in combination with feature-based or view-based SLAM; however, in the literature, appearance-based SLAM is often performed with a camera (Ulrich & Nourbakhsh, 2000).”
Mobile Robot Localisation and Mapping in Extensive Outdoor Environments (2002, methodology): “The second recognition method is based on vision data and involves defining each place node with images obtained from its (arbitrary) location and then matching observed images to the node according to a prescribed similarity measure [51, 1, 137].”
Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization (2005, background): “Ulrich and Nourbakhsh [12] developed a system that uses color histograms for appearance-based localizations.”
FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance (2008, background): “Early examples include representing appearance as a set of image histograms (Ulrich and Nourbakhsh 2000), and as ordered sequences of edge and color features (Lamon et al. 2001).”
Convolutional Neural Network-based Place Recognition (2014, background): “Histograms of image gray values or texture is also a widely used feature in place recognition systems [Ulrich and Nourbakhsh, 2000, Blaer and Allen, 2002] due to its compact representation rotation invariance.”
CENTRIST: A Visual Descriptor for Scene Categorization (2011, background): “Topological place recognition answers the same question as place recognition, but at a coarser granularity [5].”
Fast and Incremental Method for Loop-Closure Detection Using Bags of Visual Words (2008, methodology): “In [18], the authors also use multiple-view geometry to validate each matching hypothesis, while in [19], the accuracy of the likelihood is qualitatively evaluated in order to reject outliers.”
Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications (2012, background): “, [67] and [68]) or local image descriptors (e.”
Context-based vision system for place and object recognition (2003, methodology): “In fact, the model we propose for place recognition is more similar to a topological map of the kind used in the mobile robotics community (e.g., [ 13 , 15]).”
Visual Place Recognition: A Survey (2016, methodology): “Global place descriptors used in early localization systems included color histograms [5] and descriptors based on principal component analysis [104].”
Introduction to Autonomous Mobile Robots (2004, neutral): “Using this whole-image extraction approach, a robot can readily recover the particular hallway or particular room in which it is located [152].”
A Bayesian approach for place recognition (2012, methodology): “Some previous approaches use image histograms and topological maps for classification [21, 14].”