A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.
Apache License 2.0
671
stars
232
forks
source link
why is the (x,y) joints cordinates divided by 1280 and 720 to normalize it? #70
record_joints_norm += [round(center_x/1280, 2), round(center_y/720, 2)]
I saw this line of code in pose_visualizer.py, Isn't we suppose to divide it with height and width of image instead of hardcoded values 1280 and 720. Could you please explain why these values (1280,720) were choose?
record_joints_norm += [round(center_x/1280, 2), round(center_y/720, 2)]
I saw this line of code in pose_visualizer.py, Isn't we suppose to divide it with height and width of image instead of hardcoded values 1280 and 720. Could you please explain why these values (1280,720) were choose?