Landmark detection with surprise saliency using convolutional neural networks

@article{Tang2016LandmarkDW,
  title={Landmark detection with surprise saliency using convolutional neural networks},
  author={F. Tang and D. Lyons and Daniel D. Leeds},
  journal={2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)},
  year={2016},
  pages={204-211}
}
  • F. Tang, D. Lyons, Daniel D. Leeds
  • Published 2016
  • Computer Science
  • 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)
  • Landmarks can be used as a reference to enable people or robots to localize themselves or to navigate in their environment. Automatic definition and extraction of appropriate landmarks from the environment has proven to be a challenging task when pre-defined landmarks are not present. We propose a novel computational model of automatic landmark detection from a single image without any pre-defined landmark database. The hypothesis is that if an object looks abnormal due to its atypical scene… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,456
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,490
    • Highly Influential
    • PDF
    You Only Look Once: Unified, Real-Time Object Detection
    • 8,796
    • PDF
    Learning Deep Features for Scene Recognition using Places Database
    • 2,174
    • Highly Influential
    • PDF
    DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
    • 3,555
    • PDF
    Detection of natural landmarks through multiscale opponent features
    • 29
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,494
    • Highly Influential
    • PDF
    Histograms of oriented gradients for human detection
    • 25,750
    • PDF
    Selective Search for Object Recognition
    • 3,586
    • PDF