Point-Cloud-Based Place Recognition Using CNN Feature Extraction

@article{Sun2019PointCloudBasedPR,
  title={Point-Cloud-Based Place Recognition Using CNN Feature Extraction},
  author={Ting Sun and Ming Liu and Haoyang Ye and Dit-Yan Yeung},
  journal={IEEE Sensors Journal},
  year={2019},
  volume={19},
  pages={12175-12186}
}
  • Ting Sun, Ming Liu, +1 author Dit-Yan Yeung
  • Published in IEEE Sensors Journal 2019
  • Engineering, Computer Science
  • This paper proposes a novel point-cloud-based place recognition system that adopts a deep learning approach for feature extraction. By using a convolutional neural network pre-trained on color images to extract features from a range image without fine-tuning on extra range images, significant improvement has been observed when compared to using hand-crafted features. The resulting system is illumination invariant, rotation invariant and robust against moving objects that are unrelated to the… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    Deep Fusion of Multi-Layers Salient CNN Features and Similarity Network for Robust Visual Place Recognition*

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 62 REFERENCES

    Caffe: Convolutional Architecture for Fast Feature Embedding

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Place recognition using keypoint voting in large 3D lidar datasets

    • Michael Bosse, Robert Zlot
    • Engineering, Computer Science
    • 2013 IEEE International Conference on Robotics and Automation
    • 2013
    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Are we ready for autonomous driving? The KITTI vision benchmark suite

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    3D is here: Point Cloud Library (PCL)

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Handwritten Digit Recognition with a Back-Propagation Network

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL