i am trying to analyze a video of several moving blobs.

The cv.jit.blobs.moments outputs 17 variables for every recognized blob.

The help file defines the 3 last: x & y coordinates and area. What are the other 14? i thing the first 7 are the previous state of the other ones, but what are these variables?

I searched for documentation but found nothing… If anyone could help…

Thanks in advance,

Nikolas ]]>

17-plane single-row float32

Planes 1-7 contain second and third order moments of inertia.

Planes 8-14 contain Hu invariant shape descriptors

Planes 15-16 hold centroid coordinates

Plane 17 holds connected component area

but i cannot understand what the Hu invariants are..

I searched but couldnt find anything that i could understand

Thank you very much anyway! :) ]]>

I’m NOT an expert so the best I can suggest is reading up on it. The Hu’s set of invariants is a set of 7 commonly used calculations used to determine invariant moments. Understanding mathematic invariants is the key here:

http://en.wikipedia.org/wiki/Invariant_(mathematics)

Here’s the Wiki entry on image moments:

http://en.wikipedia.org/wiki/Image_moment

Rotation invariant moments

It is possible to calculate moments which are invariant under translation, changes in scale, and also rotation. Most frequently used are the Hu set of invariant moments [1]:

The first one, I1, is analogous to the moment of inertia around the image’s centroid, where the pixels’ intensities are analogous to physical density. The last one, I7, is skew invariant, which enables it to distinguish mirror images of otherwise identical images.

A general theory on deriving complete and independent sets of rotation invariant moments was proposed by J. Flusser[2] and T. Suk.[3] They showed that the traditional Hu’s invariant set is not independent nor complete. I2 and I3 are not very useful for pattern recognition, as they are dependent. On the original Hu’s set there is a missing third order independent moment invariant:

[...]

^ M. K. Hu, “Visual Pattern Recognition by Moment Invariants”, IRE Trans. Info. Theory, vol. IT-8, pp.179–187, 1962

Hope this helps.

]]>