I'd like to ask some help about a project that me and my collegues are implementing for a university course.
We are asked to extract some features position (in our case two coloured dots) placed on the surface of a pulsing human heart.
We saw some of the tutorials on how to use vision sensors like the blob detection but we are not able to retrieve the wanted information, in particular we need to extract the "features" information in order to reconstruct the periodical motion of the heart via FFT and Klaman filtering and then use this information for a visual servoing task during a minimal invasive surgery.
We finded a built-in filter in the vision sensor to retrieve particular colors but we dont know how to extract information from the filter.
Can someone help us to obtain the position of the points during the heart motion?
Thanks in advance
If someone need a little overview on what we are asking here is the introduction to what we need to do
Abstract— In this paper , we present a novel approach for
mapping periodically moving visual features with a monocular
camera. Our target application is the estimation of moving
surfaces during minimally invasive surgery for the purpose of
aiding in the guidance of surgical tools. Our approach uses
a bank of Kalman filters to estimate FFT parameters that
encode the periodic motion of visually detected features. T o
ensure convergent estimation for this highly nonlinear problem,
we have developed an iterative update procedure that treats
the Kalman filter measurement update step as an optimization
problem. Unlike existing solutions that rely on stereo vision,
our approach estimates periodic motion with a single moving
camera. With an experiment involving a beating heart phantom,
we have shown that our approach is able to successfully estimate
the periodic motion of visual features.