opencv_traincascade -numStages 1 How many stages do I need?

Question

I am tracking one particular dog and nothing else. What is the maximum stage, number of positive and negative samples that makes sense?

With: ./opencv_traincascade -data xml -vec pos.vec -bg neg.txt -numPos 13 -numNeg 30 -numStages 1 -featureType HAAR -w 50 -h 50

I get:

===== TRAINING 0-stage ===== <BEGIN POS count : consumed 13 : 13 NEG count : acceptanceRatio 30 : 1 Precalculation time: 3

+----+---------+---------+
|  N |    HR   |    FA   |
+----+---------+---------+
|   1|        1|        1|
+----+---------+---------+
|   2|        1|        0|
+----+---------+---------+

END> Training until now has taken 0 days 0 hours 0 minutes 6 seconds.

With: ./opencv_traincascade -data xml -vec pos.vec -bg neg.txt -numPos 13 -numNeg 30 -numStages 2 -featureType HAAR -w 50 -h 50

I get:

===== TRAINING 1-stage ===== <BEGIN POS count : consumed 13 : 13 NEG count : acceptanceRatio 0 : 0 Required leaf false alarm rate achieved. Branch training terminated.

To reach numStages 2, do I need more images? To track one animal in particular, how many positive and negative images are needed? How high should me numStages be to track one specific dog? I am happy to do more. I am just trying to figure out what my expectations should be. Thank you!