Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems

@article{Xiang2019ImportanceAwareSS,
  title={Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems},
  author={Kaite Xiang and Kaiwei Wang and Kailun Yang},
  journal={2019 IEEE Intelligent Transportation Systems Conference (ITSC)},
  year={2019},
  pages={3412-3418}
}
  • Kaite Xiang, Kaiwei Wang, Kailun Yang
  • Published in
    IEEE Intelligent…
    2019
  • Engineering, Computer Science
  • Semantic Segmentation (SS) is a task to assign semantic label to each pixel of the images, which is of immense significance for autonomous vehicles, robotics and assisted navigation of vulnerable road users. It is obvious that in different application scenarios, different objects possess hierarchical importance and safety-relevance, but conventional loss functions like cross entropy have not taken the different levels of importance of diverse traffic elements into consideration. To address this… 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.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES

    The Cityscapes Dataset for Semantic Urban Scene Understanding

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Importance-Aware Semantic Segmentation for Autonomous Vehicles

    • Bike Chen, Chen Gong, Jian Yang
    • Computer Science, Engineering
    • IEEE Transactions on Intelligent Transportation Systems
    • 2019
    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Attribute-aware Semantic Segmentation of Road Scenes for Understanding Pedestrian Orientations

    VIEW 1 EXCERPT