Search code examples
conv-neural-networkobject-detection

is Faster RCNN rotation invariant?

I want to generate a dataset of vehicles to train in networks such as RCNN, Fast RCNN, Faster RCNN, etc. My question is:

Does the angle of vehicles in the original image matter for the detector? I mean if the dataset only contains vehicle images which are all directed from left to right, can the trained network detect any vehicle with any angle?

Solution

  • Detectron2 added Rotated Faster RCNN network recently. To create such model, you should create annotations for vehicles with rotated bounding box, which is:

    rbbox = [center_x, center_x, width, height, angle]

    Visit this link for more information.