1 / 20

Rotational Rectification Network (R2N): Enabling Pedestrian Detection for Mobile Vision

Rotational Rectification Network (R2N): Enabling Pedestrian Detection for Mobile Vision. Xinshuo Weng 1 , Shangxuan Wu 1 , Fares Beainy 2 , Kris M. Kitani 1 1 Carnegie Mellon University, 2 Volvo Construction Equipment WACV 2018, Lake Tahoe. Pedestrian Detection. Pedestrian Detection.

sbrandt
Download Presentation

Rotational Rectification Network (R2N): Enabling Pedestrian Detection for Mobile Vision

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Rotational Rectification Network (R2N): Enabling Pedestrian Detection for Mobile Vision Xinshuo Weng1, Shangxuan Wu1, Fares Beainy2, Kris M. Kitani1 1Carnegie Mellon University, 2Volvo Construction Equipment WACV 2018, Lake Tahoe

  2. Pedestrian Detection

  3. Pedestrian Detection • Results on Caltech dataset Zhang et al. Is Faster R-CNN Doing Well for Pedestrian Detection? ECCV, 2016.

  4. Arbitrary-Oriented Pedestrian Detection

  5. Arbitrary-Oriented Pedestrian Detection

  6. Arbitrary-Oriented Pedestrian Detection • Random failure cases on Caltech dataset.

  7. Why is it interesting? Imagine the cases: • Mobile phones

  8. Why is it interesting? Imagine the cases: • Mobile phones • UAVs/drones

  9. Why is it interesting? Imagine the cases: • Mobile phones • UAVs/drones • Construction vehicles on a rugged terrain

  10. Why is it interesting? Imagine the cases: • Mobile phones • UAVs/drones • Construction vehicles on a rugged terrain • Wearable cameras • ….

  11. Why is it interesting? Imagine the cases: • Mobile phones • UAVs/drones • Construction vehicles on a rugged terrain • Wearable cameras • …. Camera orientation can be very flexible with respect to the ground in the real world.

  12. Modeling Rotation Invariance or Equivariance

  13. Modelling Rotation Invariance/Equivariance Rotating the inputs • Data augmentation • TI-Pooling [Laptev et al CVPR’ 16] • …. • Cons: • Low efficiency • More parameters Rotating the filters Changing sampling grids

  14. Modelling Rotation Invariance/Equivariance Rotating the inputs • Data augmentation • TI-Pooling [Laptev et al, CVPR’ 16] • …. • Cons: • Low efficiency • More parameters Rotating the filters • RotEqNet [Marcos et al, ICCV’ 17] • ORNs [Zhou et al, CVPR’ 17] • …. • Cons: • Approximated rotations • Memory issues Changing sampling grids

  15. Modelling Rotation Invariance/Equivariance Rotating the inputs • Data augmentation • TI-Pooling [Laptev et al, CVPR’ 16] • …. • Cons: • Low efficiency • More parameters Rotating the filters • RotEqNet [Marcos et al, ICCV’ 17] • ORNs [Zhou et al, CVPR’ 17] • …. • Cons: • Approximated rotations • Memory issues Changing sampling grids • Spatial Transformer [Jaderberg et al, NIPS’ 15] • Deformable ConvNets [Dai et al, ICCV’ 17] • GPPooling (Ours) • ….

  16. Global Polar Pooling (GPPooling) Inputs Activations

  17. GPPooling vs Pooling GPPooling Pooling Noh et al. Learning Deconvolution Network for Semantic Segmentation? ICCV, 2015.

  18. What is Rotational Rectification Network (R2N)? R2N = Rotation Estimation Module (including GPPooling) + Spatial Transformer

  19. Results

  20. Take Home Messages • GPPooling can be used to model global rotation equivariance/invariance in general CNNs. • R2N is easy to plug in and improves the performance on oriented detection without bells and whistles.

More Related