Fast Loop Closure Detection via Binary Content

@article{Wang2019FastLC,
  title={Fast Loop Closure Detection via Binary Content},
  author={Han Wang and Juncheng Li and Maopeng Ran and Lihua Xie},
  journal={2019 IEEE 15th International Conference on Control and Automation (ICCA)},
  year={2019},
  pages={1563-1568}
}
  • Han Wang, Juncheng Li, Lihua Xie
  • Published 1 July 2019
  • Computer Science
  • 2019 IEEE 15th International Conference on Control and Automation (ICCA)
Loop closure detection plays an important role in reducing localization drift in Simultaneous Localization And Mapping (SLAM). It aims to find repetitive scenes from historical data to reset localization. To tackle the loop closure problem, existing methods often leverage on the matching of visual features, which achieve good accuracy but require high computational resources. However, feature point based methods ignore the patterns of image, i.e., the shape of the objects as well as the… 
1 Citations

Figures and Tables from this paper

References

SHOWING 1-10 OF 25 REFERENCES
VLAD-based loop closure detection for monocular SLAM
  • Yao Huang, F. Sun, Yao Guo
  • Computer Science
    2016 IEEE International Conference on Information and Automation (ICIA)
  • 2016
TLDR
A novel vlad-based loop closure detection approach is proposed and is compared with the state-of-the-art DBoW2 in some open datasets, which performs better in accuracy and memory cost.
Loop closure detection for visual SLAM using PCANet features
TLDR
It is shown that unsupervised features extracted by deep learning models, can improves the accuracy of loop closure detection, and in particular, a cascaded deep network is employed, namely the PCANet, to extract features as image descriptors.
Convolutional neural network-based image representation for visual loop closure detection
TLDR
CNN-based image representations perform comparably to state-of-the-art hand-crafted competitors in environments without significant lighting change, and are also significantly faster to extract than the state of the art hand- crafted features even on a conventional CPU and are two orders of magnitude faster on an entry-level GPU.
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).
A Photometrically Calibrated Benchmark For Monocular Visual Odometry
TLDR
A novel, simple approach to non-parametric vignette calibration, which requires minimal set-up and is easy to reproduce and thoroughly evaluate two existing methods (ORB-SLAM and DSO) on the dataset.
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
TLDR
ORB-SLAM2, a complete simultaneous localization and mapping (SLAM) system for monocular, stereo and RGB-D cameras, including map reuse, loop closing, and relocalization capabilities, is presented, being in most cases the most accurate SLAM solution.
SURF: Speeded Up Robust Features
In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously
Highly scalable appearance-only SLAM - FAB-MAP 2.0
TLDR
A new formulation of appearance-only SLAM suitable for very large scale navigation that naturally incorporates robustness against perceptual aliasing is described and demonstrated performing reliable online appearance mapping and loop closure detection over a 1,000 km trajectory.
Vision meets robotics: The KITTI dataset
TLDR
A novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research, using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras and a high-precision GPS/IMU inertial navigation system.
Return of the Devil in the Details: Delving Deep into Convolutional Nets
TLDR
It is shown that the data augmentation techniques commonly applied to CNN-based methods can also be applied to shallow methods, and result in an analogous performance boost, and it is identified that the dimensionality of the CNN output layer can be reduced significantly without having an adverse effect on performance.
...
...