Bags of Binary Words for Fast Place Recognition in Image Sequences

@article{GlvezLpez2012BagsOB,
  title={Bags of Binary Words for Fast Place Recognition in Image Sequences},
  author={Dorian G{\'a}lvez-L{\'o}pez and Juan D. Tard{\'o}s},
  journal={IEEE Transactions on Robotics},
  year={2012},
  volume={28},
  pages={1188-1197}
}
We propose a novel method for visual place recognition using bag of words obtained from accelerated segment test (FAST)+BRIEF features. For the first time, we build a vocabulary tree that discretizes a binary descriptor space and use the tree to speed up correspondences for geometrical verification. We present competitive results with no false positives in very different datasets, using exactly the same vocabulary and settings. The whole technique, including feature extraction, requires 22 ms… 
View on IEEE
doriangalvez.com
1,026 Citations
Highly Influential Citations
110
Background Citations
253
Methods Citations
511
Results Citations
6

1,026 Citations

Citation Type

Citation Type

Adding Cues to Binary Feature Descriptors for Visual Place Recognition
TLDR
This paper proposes an approach to embed multi-dimensional continuous cues in binary feature descriptors used for visual place recognition by extending each feature descriptor with a binary string that encodes a cue and supports the Hamming distance metric.
Bag of Sampled Words: A Sampling-based Strategy for Fast and Accurate Visual Place Recognition in Changing Environments
TLDR
A sampling-based method which improves the speed and the accuracy of the existing Visual Bag of Words models and a coarse and fine approach-based refinement method is proposed which increases theuracy of the system by iteratively updating the similarity between images.
Encoding the description of image sequences: A two-layered pipeline for loop closure detection
TLDR
A novel technique for detecting loop closures on a trajectory by matching sequences of images instead of single instances is proposed, which reveals that this method outperforms other state of the art algorithms.
Fast loop-closure detection using visual-word-vectors from image sequences
TLDR
Evaluation results prove that the presented method compares favorably with other state-of-the-art techniques, while the algorithm is tested on a tablet device, verifying the computational efficiency of the approach.
Visual localization and loop closing using decision trees and binary features
  • D. Schlegel, G. Grisetti
  • Computer Science
    2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2016
TLDR
This paper presents an approach for efficiently retrieving the most similar image, based on point-to-point correspondences, within a sequence that has been acquired through continuous camera movement by exploiting the temporal form of the input data to dynamically adapt the search structure.
Spatio-Semantic ConvNet-Based Visual Place Recognition
TLDR
A Visual Place Recognition system that follows the two-stage format common to image retrieval pipelines, which outperform by a large margin state-of-the-art visual place recognition methods on five of the most commonly used benchmark datasets.
Effective Visual Place Recognition Using Multi-Sequence Maps
TLDR
This letter proposes a method for visual place recognition that is able to deal with seasonal changes, different weather condition as well as illumination changes, and localizes the robot in a map, which is represented by multiple image sequences collected in the past at different points in time.
Graph-Based Place Recognition in Image Sequences with CNN Features
TLDR
This work proposes a graph-based visual place recognition method that is able to obtain significantly better performance than that of FAB-MAP, a commonly used method for place recognition based on handcrafted features, especially on some challenging datasets.
Localizing Discriminative Visual Landmarks for Place Recognition
TLDR
This work investigates how to localize discriminative visual landmarks that positively contribute to the similarity measurement, such as buildings and vegetations, and designs a Landmark Localization Network (LLN), designed to indicate which regions of an image are used for discrimination.
Place recognition by combining multiple feature types with a modified vocabulary tree
TLDR
A modified vocabulary tree with the ability of merging multiple kinds of features such that it allows users to customize different combination of features for better place recognition performance is proposed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 37 REFERENCES
Real-time loop detection with bags of binary words
TLDR
A method for detecting revisited places in a image sequence in real time by using efficient features and a direct index to take advantage of the bag of words to obtain correspondence points between two images efficiently, avoiding a matching of complexity Θ(n2).
Robust Place Recognition With Stereo Sequences
TLDR
A place recognition algorithm for simultaneous localization and mapping systems using stereo cameras that considers both appearance and geometric information of points of interest in the images and carries out inference on a minimum spanning tree (MST), instead of a densely connected graph.
Scalable Recognition with a Vocabulary Tree
  • D. Nistér, Henrik Stewénius
  • Computer Science
    2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
TLDR
A recognition scheme that scales efficiently to a large number of objects and allows a larger and more discriminatory vocabulary to be used efficiently is presented, which it is shown experimentally leads to a dramatic improvement in retrieval quality.
BRIEF: Binary Robust Independent Elementary Features
We propose to use binary strings as an efficient feature point descriptor, which we call BRIEF. We show that it is highly discriminative even when using relatively few bits and can be computed using…
BRISK: Binary Robust invariant scalable keypoints
TLDR
A comprehensive evaluation on benchmark datasets reveals BRISK's adaptive, high quality performance as in state-of-the-art algorithms, albeit at a dramatically lower computational cost (an order of magnitude faster than SURF in cases).
Video Google: a text retrieval approach to object matching in videos
We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set of viewpoint…
Distinctive Image Features from Scale-Invariant Keypoints
  • D. Lowe
  • Computer Science
    International Journal of Computer Vision
  • 2004
TLDR
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
ORB: An efficient alternative to SIFT or SURF
TLDR
This paper proposes a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise, and demonstrates through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations.
Fast and Incremental Method for Loop-Closure Detection Using Bags of Visual Words
TLDR
This work presents an online method that makes it possible to detect when an image comes from an already perceived scene using local shape and color information, and extends the bag-of-words method used in image classification to incremental conditions and relies on Bayesian filtering to estimate loop-closure probability.
Fast Approximated SIFT
TLDR
A considerably faster approximation of the well known SIFT method by using efficient data structures for both, the detector and the descriptor and an analysis of the computational costs.
...
1
2
3
4
...