computer-vision
Bounding boxes, IoU, and non-max suppression
taught
Scoring how well a predicted box matches a ground-truth box with intersection-over-union, and using non-max suppression to collapse a detector's many overlapping candidate boxes for the same object down to one -- never removing a genuinely separate true positive.
Taught in
-
Bounding boxes, IoU, and confidence
Computer Vision
-
Non-max suppression
Computer Vision
Requires
Nothing — this is foundational.
Required by
Local knowledge map
Local knowledge map
Click to expand
Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.