Skip to main content
Share Your Experience: Take the 2024 Developer Survey
3 votes

What's the role of bounding boxes in object detection?

A bounding box is a rectangle superimposed over an image within which all important features of a particular object is expected to reside. It's purpose is to reduce the range of search for those ...
Douglas Daseeco's user avatar
2 votes

How are IOUs for ground truth boxes in YOLO calculated?

My assumption was correct: the ground truth bounding box is aligned with an anchor box such that they share the same center In other words, only the widths and heights are used to calculate the ...
nivter's user avatar
  • 73
2 votes

YOLO - are the anchor boxes used only in training?

Object detection models behave the same during both, training and test phase, i.e. they just return thousands and thousands of bounding boxes as predictions, plus a confidence score for each box (...
Edoardo Guerriero's user avatar
2 votes

How does a bounding box detection network "know" about absolute position?

It of course depends on the detection model that is used. But in your case I think you relate to a Faster-RCNN type architecture for bounding box detection. In this case only the relative position to ...
Marcel_marcel1991's user avatar
1 vote

Can the output of non-max suppression have more bounding boxes than the number of objects the picture actually has?

Usually bounding-boxes are associated to a score or confidence. So, you loop over them considering the highest scoring first. You then set a threshold on the IoU (intersection over union) that is used ...
Luca Anzalone's user avatar
1 vote

Why is it called "area of union" when calculating the Intersection over Union?

Consider these two sets $A = \{1, 2, 3, 4 \}$ and $B = \{0, 2, 3, 5, 6 \}$. Their union $A \cup B = \{0, 1, 2, 3, 4, 5, 6\}$. So, $|A \cup B| = 7$. The order of these numbers in $A \cup B$ does not ...
nbro's user avatar
  • 40.8k
1 vote

How to architect a network to find bounding boxes in simple images?

There are some special architectures of CNNs which are designed exactly for the task you mention. The Detector library includes a collection of these architectures, this paper describes the Mask R-CNN ...
50k4's user avatar
  • 225
1 vote

Why do the object detection networks produce multiple anchor boxes per location?

Yes, theoretically it is possible to learn the offsets to get any possible bounding box from only one anchor box. However, it is hard to learn such dramatic shifts and changes. Learning only small ...
a crazy Minion's user avatar
1 vote

Can bounding boxes further improve the performance of a CNN classifier?

Information outside of the bounding box could still be useful as context. So not to lose it you can but bounding box as pixel mask into additional "pseudo-color" layer. That way you can also have ...
mirror2image's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible