Bounding box normalization about piepredict HOT 8 CLOSED

Hi There,

Thanks for using our dataset. To answer your questions:

1- For the trajectory stream of the code we used the bounding box coordinates which only contain the pedestrians because no visual features were used. We used the context bboxes only for intention stream.

2- Normalization was done by subtracting the first bbox coordinates in sequences from the rest of bboxes in the given sequence.
e.g.
seq = [bbox_0, bbox_1, bbox_2, ...., bbox_n]
bbox_1_norm = bbox_1 - bbox_0
bbox_2_norm = bbox_2 - bbox_0
....
seq_norm = [bbox_1_norm, ...., bbox_n_norm]

You can consider the normalization as converting the coordinates to velocity. Since the first bbox is always zero, it is omitted.

I hope my answer helps,

from piepredict.

Oh, thanks, it is of great help! So, for a sequence of 15 detections, only 14 bboxes are fed to the PIEIntent decoder (omitting the bbox0)? The problem is that model.h5 for PIEIntent expects a decoder_input of shape (15,4)

from piepredict.

Correct

from piepredict.

The problem is that model.h5 for PIEIntent expects a decoder_input of shape (15,4)

from piepredict.

Normalization is only done for trajectory module. O_intent gets the coordinates as is so it is 15,4

from piepredict.

Ok then, then for PIEIntent no normalization is performed?

from piepredict.

correct

from piepredict.

Thank you very much for your responses and your great work!

from piepredict.