Active Planning, Sensing, and Recognition Using a Resource-Constrained Discriminant POMDP

@article{Wang2014ActivePS,
  title={Active Planning, Sensing, and Recognition Using a Resource-Constrained Discriminant POMDP},
  author={Zhaowen Wang and Zhangyang Wang and Mark Moll and Po-Sen Huang and Devin K. Grady and Nasser M. Nasrabadi and Thomas S. Huang and Lydia E. Kavraki and Mark Hasegawa-Johnson},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  year={2014},
  pages={754-761}
}
  • Zhaowen Wang, Zhangyang Wang, +6 authors Mark Hasegawa-Johnson
  • Published in
    IEEE Conference on Computer…
    2014
  • Computer Science
  • In this paper, we address the problem of object class recognition via observations from actively selected views/modalities/features under limited resource budgets. A Partially Observable Markov Decision Process (POMDP) is employed to find optimal sensing and recognition actions with the goal of long-term classification accuracy. Heterogeneous resource constraints -- such as motion, number of measurements and bandwidth -- are explicitly modeled in the state variable, and a prohibitively high… 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

    Multi-Modal Generative Models for Learning Epistemic Active Sensing

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Provably-Correct Task Planning for Autonomous Outdoor Robots

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 17 REFERENCES

    Civilian vehicle radar data domes

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Standard SAR ATR evaluation experiments using the MSTAR public release data set

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Information Theoretic Sensor Data Selection for Active Object Recognition and State Estimation

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Timely Object Recognition

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Multi-PIE

    VIEW 1 EXCERPT