3

When studying bounding box-based detectors, it's not clear to me if data augmentation includes adding random rotations.

If random rotations are added, how is the new bounding box calculated?

nbro
  • 39,006
  • 12
  • 98
  • 176
FourierFlux
  • 783
  • 1
  • 4
  • 14
  • 1
    I don't have much practical experience with them, but, I guess, if you rotate the images, you just need to rotate the boxes (i.e. labels) too. Check [this](https://github.com/anhtuan85/Data-Augmentation-for-Object-Detection/blob/master/augmentation.ipynb) (which may not be a reliable implementation: I don't know!). – nbro Nov 15 '20 at 22:43
  • The problem is the predicted boxes are not rotated - so would you just create a new box from the rotated images bounding box corners? This works but might make the predicted box a little larger,. – FourierFlux Nov 15 '20 at 22:47

0 Answers0