Real-time loop detection with bags of binary words

  title={Real-time loop detection with bags of binary words},
  author={Dorian G{\'a}lvez-L{\'o}pez and Juan D. Tard{\'o}s},
  journal={2011 IEEE/RSJ International Conference on Intelligent Robots and Systems},
We present a method for detecting revisited places in a image sequence in real time by using efficient features. We introduce three important novelties to the bag-of-words plus geometrical checking approach. We use FAST keypoints and BRIEF descriptors, which are binary and very fast to compute (less that 20µs per point). To perform image comparisons, we make use of a bag of words that discretises the binary descriptor space and an inverse index. We also introduce the use of a direct index to… 

Figures and Tables from this paper

Evaluation of Bags of Binary Words for Place Recognition in Challenging Scenarios
A behavioral evaluation of a conventional BoW scheme based on Oriented FAST and Rotated BRIEF features for image similarity detection in challenging scenarios shows a good balance to deal with such severe conditions at a low computational cost.
On the use of binary feature descriptors for loop closure detection
  • E. Garcia-Fidalgo, A. Ortiz
  • Computer Science
    Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA)
  • 2014
An indexing method for binary features, which, in combination with an inverted index, enable to obtain loop closure candidates in an online manner, is introduced and used in a discrete Bayes filter to select final loop candidates and to ensure temporal coherency between predictions.
Automatic Vocabulary and Graph Verification for Accurate Loop Closure Detection
This work proposes a natural convergence criterion based on the comparison between the radii of nodes and the drifts of feature descriptors, which is then utilized to build the optimal vocabulary automatically and presents a novel topological graph verification method for validating candidate loops.
Bags of Binary Words for Fast Place Recognition in Image Sequences
A vocabulary tree is built that discretizes a binary descriptor space and uses the tree to speed up correspondences for geometrical verification, and presents competitive results with no false positives in very different datasets.
Robust Loop Closure Detection based on Bag of SuperPoints and Graph Verification
The results demonstrate that the proposed graph verification method can significantly improve the accuracy of image matching and the overall LCD approach outperforms existing methods.
Appearance-Based Loop Closure Detection in Real-Time for Large-Scale and Long-Term Operation
In appearance-based localization and mapping, loop closure detection is the process used to determinate if the current observation comes from a previously visited location or a new one. As the size
Real-Time Continuous 6 D Relocalisation for Depth Cameras
This paper presents results of a system performing visual 6-D relocalisation at every single frame and in real time, such as is useful in re-exploration of scenes or for loop-closure in earnest. Our
Visual loop closure detection with a compact image descriptor
  • Yang Liu, Hong Zhang
  • Computer Science
    2012 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2012
This paper uses PCA to transform a high dimensional Gabor-Gist descriptor to a lower dimensional form to improve both the computational efficiency of the method and the discriminative power of the image descriptor.
A Precise and Real-Time Loop-closure Detection for SLAM Using the RSOM Tree
This work presents an online and incremental approach to detect loops when images come from an already visited scene and learn new information from the environment, using the attributed graph model to represent images and measure the similarity between pairs of images in this method.
Mobile robot loop closure detection using endpoint and line feature visual dictionary
This paper proposes to build endpoint and line visual dictionary which can describe endpoint set structure and texture information in environment, then two BoW vectors merged into one which contains relation of endpoint visual words.


Keypoint recognition using randomized trees
  • V. Lepetit, P. Fua
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2006
A keypoint-based approach is developed that is effective in this context by formulating wide-baseline matching of keypoints extracted from the input images to those found in the model images as a classification problem, which shifts much of the computational burden to a training phase, without sacrificing recognition performance.
Fast and Incremental Method for Loop-Closure Detection Using Bags of Visual Words
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.
Machine Learning for High-Speed Corner Detection
It is shown that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time.
FAB-MAP 3D: Topological mapping with spatial and visual appearance
  • Rohan Paul, P. Newman
  • Computer Science
    2010 IEEE International Conference on Robotics and Automation
  • 2010
This paper describes a probabilistic framework for appearance based navigation and mapping using spatial and visual appearance data and explicitly model the spatial distribution of visual words as a random graph in which nodes are visual words and edges are distributions over distances.
Compact signatures for high-speed interest point description and matching
This paper shows that it can exploit the sparseness of these signatures to compact them, speed up the computation, and drastically reduce memory usage, and highlights its effectiveness by incorporating it into two very different SLAM packages and demonstrating substantial performance increases.
Robust place recognition with stereo cameras
This paper presents an alternative system that makes use of stereo vision and combines two complementary techniques: bag-of-words to detect loop closing candidate images, and conditional random fields to discard those which are not geometrically consistent.
A performance evaluation of local descriptors
It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
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
Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration
A system that answers the question, “What is the fastest approximate nearest-neighbor algorithm for my data?” and a new algorithm that applies priority search on hierarchical k-means trees, which is found to provide the best known performance on many datasets.
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