convert_x_to_bbox function output

[abewley]

convert_x_to_bbox function output

[abewley]

In the code I use the convention that y increases in the downward image direction. So the [x1, y1, x2, y2] could also read [left,top,right,bottom], that's what I meant when referring to the box's top left corner point (x1,y1) and the bottom right corner point (x2, y2). There was a typo in the comment where I had [x1, y1, x2, x2] but that should now be fixed. Sorry for any confusion.

The linear assignment module tries to minimise the total assignment cost. In our case we pass -iou_matrix as we want to maximise the total IOU between track predictions and the frame detection.

[miketry0313]

Thanks a lot!