search

abewley / sort

Simple, online, and realtime tracking of multiple objects in a video sequence.
GNU General Public License v3.0
3.82k stars 1.07k forks source link

Clarify Detection Bounding Box Coordinate Definitions #97

Open GOBish opened 4 years ago

GOBish commented 4 years ago

Hi, Could you please clarify the coordinate system for the bounding box of the detections? In sort.py, the notes say

Params: dets - a numpy array of detections in the format [[x1,y1,x2,y2,score],[x1,y1,x2,y2,score],...] Requires: this method must be called once for each frame even with empty detections (use np.empty((0, 5)) for frames without detections). Returns the a similar array, where the last column is the object ID.

Just want to check, does this mean (x1,y1)-->upper left corner (x2,y2)-->lower right corner? (absolute) Or is it (x1,y1)-->upper left corner, (x2,y2)-->width and height? (relative)

Thanks!

aia39 commented 3 years ago

As I have implemented successfully it, I saw that you have to pass (x1,y1) as absolute upper left corner and (x2,y2) as absolute lower right corner.