How to find RGB / HSV color parameters for color tracking?

Question

I would like to track color in a set of images. For this reason, I use the constant threshold algorithm mentioned in Introduction to Autonomous Mobile Robots . This method simply marks all those pixels that are minimum, and the maximum threshold of red, green, blue (or hue, saturation, value in my case).

My problem is that although HSV is less sensitive to changing lighting conditions, I would still like to set thresholds from the program to minimize the number of false positives and false negatives. In other words, the algorithm ensures that at the end only a certain set of pixels will be marked, for example, a rectangle in the calibration image.

I know that the problem is to search in a 6-dimensional space of parameters, and I could find possible solutions, but I am looking for the opinion of other experts and experience on this issue.

If this is important, I am trying to implement it in C ++ with OpenCV .

Answer 1

, 6 (. HSV) , . :

• , ,
• , HSV
• 0,05 0,95

, 0,05 0,95 .

EDIT:

: , ( ) . . .