0

I'm working with OpenCV which has some tracking algorithms (BOOSTING, MIL, KCF, MEDIANFLOW, TLD, ...).

I've read many papers where they use the Bhattacharya Coefficient to measure the efficiency of each tracker. I know the formula is:

formula

But I don't know how/where to start to calculate it.

I know that an OpenCV tracker will give me the coordinates for drawing a bounding box. On the other hand, I have the validation dataset where I have the coordinates for the perfect and right located bounding box, but I don't know how to continue from this point.

Any help please?

user371859
  • 1
  • what are $\Sigma,a_i,b_i$ ? – utobi Nov 02 '22 at 11:34
  • My understanding is that equation for the Bhattacharya Coefficient (BC) is $BC=\sum_{i=1}^n \sqrt {a_i b_i} $. So not sure about the summations under the square root as given in the question. Maybe worth while to check. Also see the answer for this question https://stats.stackexchange.com/questions/534846/bhattacharya-distance-for-sets-of-vectors – Mari153 Dec 29 '22 at 01:02

0 Answers0