Rotational Rectification Network: Enabling Pedestrian Detection for Mobile Vision

@article{Weng2018RotationalRN,
  title={Rotational Rectification Network: Enabling Pedestrian Detection for Mobile Vision},
  author={Xinshuo Weng and Shangxuan Wu and Fares N. Beainy and Kris M. Kitani},
  journal={2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2018},
  pages={1084-1092}
}
  • Xinshuo Weng, Shangxuan Wu, +1 author Kris M. Kitani
  • Published 2018
  • Computer Science
  • 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • Across most pedestrian detection datasets, it is typically assumed that pedestrians will be standing upright with respect to the image coordinate system. This assumption is not always valid for many vision-equipped mobile platforms, such as mobile phones, UAVs, or construction vehicles on rugged terrain. In these situations, the motion of the camera can cause images of pedestrians to be captured at extreme angles. This can lead to inferior pedestrian detection performance when using standard… CONTINUE READING
    GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
    • 6
    • PDF
    GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency
    • 6
    • PDF
    GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning
    • 3
    • PDF
    Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challenges
    • 6
    • PDF
    Joint Detection and Multi-Object Tracking with Graph Neural Networks
    • 3
    • PDF
    A Baseline for 3D Multi-Object Tracking
    • 36
    3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
    • 5
    • PDF
    Orientation-Aware Regression for Oriented Bounding Box Estimation
    • 2

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES
    Deep Learning Strong Parts for Pedestrian Detection
    • 307
    • PDF
    Are we ready for autonomous driving? The KITTI vision benchmark suite
    • 4,713
    • PDF
    A mobile vision system for robust multi-person tracking
    • 555
    • PDF
    Pedestrian Detection: An Evaluation of the State of the Art
    • 2,340
    • Highly Influential
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,467
    • PDF
    Warped Convolutions: Efficient Invariance to Spatial Transformations
    • 63
    • PDF
    SSD: Single Shot MultiBox Detector
    • 8,278
    • PDF
    Harmonic Networks: Deep Translation and Rotation Equivariance
    • 280
    • PDF