(prerequisite-R-CNN) Bounding Box Regression

• Bounding Box Regression

It is a metric for measuring how well predicted bounding boxes captures objects. This is done by calculating the mean-squared error (MSE) between the coordinates of predicted bounding boxes and the ground truth bounding boxes.

 

• Calculation

 

The MSE between two bounding boxes, P and Q is given by:

 

---

Where 4 comes from the fact that we want the mean of 4 coordinates (x1, y1, x2, y2). For the two predictions we get the following MSE values:

 

https://ambolt.io/en/how-object-detectors-learn/#:~:text=Bounding%20Box%20regression%20is%20a,the%20ground%20truth%20bounding%20boxes.