aqeelanwar / SocialDistancingAI

Using Python to monitor social distancing
MIT License
105 stars 71 forks source link

d_thresh calculation issue !!! i guess could you please explain reason behind it. ? #16

Open VijayaKumarKamma opened 4 years ago

VijayaKumarKamma commented 4 years ago

May i know the reason "d_thresh" calculation is not scaled with the birds eye view height and width where points and all re scaled with height and width of birds eye view ?

d_thresh = np.sqrt( (warped_pt[0][0] - warped_pt[1][0]) ** 2

warped_pt_scaled = [int(warped_pt[0] scale_w), int(warped_pt[1] scale_h)]

mistersingh179 commented 3 years ago

In plot_lines_between_nodes distance between the points is calculated. This distance is of the original warped points. There is no scaling on the points. This is why no scaling on the d_thresh either.

In general I agree this code could be made more straight forward by refactoring how scaling is applying. I think it is best to apply when building the transformation matrix once and rather than how it is right now where it is applied when building the bird image and when plotting points on it.