Haarcascade "KILLED"

edit

A single stage cascaded classifier simply doesn't exist. You can only get a single weak classifier which cannot be a cascaded structure. Knowing this, you should simple select minimum 2 stages for a cascaded classifier.

If you do not understand what i mean, go read the paper of viola&jones, suggesting a cascaded approach for face detection. It will make it more clear for you: http://research.microsoft.com/en-us/um/people/viola/Pubs/Detect/violaJones_CVPR2001.pdf

I had the same issue, and it was because I took to much memory for the -precalcValBufSize and -precalcIdxBufSize I think it's same of the "-mem" parameters.

I put for those 2 arguments : -precalcValBufSize 1024 -precalcIdxBufSize 1024

so I reduce it to 256 and then the issue was fixed.

-precalcValBufSize 256 -precalcIdxBufSize 256

Just an observation, though it might solve the problem. You are using an extremely small nimber of sample images. I am using 2,000+ negatives and 3,000+ positives. Perhaps there are not enough images to start one full stage?