[visionlist] About help on eye-tracking of head free non-human primates

Gabriel Diaz Gabriel.Diaz at rit.edu
Tue Jul 17 06:45:06 -05 2018


Harish, I've spent some time thinking about this problem in the past, and
it seems that we have some common ideas, and some differences in opinion.
Here are a few thoughts...

*1. Is there a good eye tracking system that already has macaque
face appearance templates bulit in?*

Not that I know of!  ...but, yours is a good comment, because it suggests
that you're thinking of using face tracking to estimate head pose, which
must be combined with eye-in-head angles to recover the gaze vector within
a world based reference frame.  That's the right way to approach the
problem. If you you aren't familiar with the technique, there are plenty of
good tutorials for head pose estimation online . For example, here is one.
<https://www.learnopencv.com/head-pose-estimation-using-opencv-and-dlib/>
I worry a bit that the hairy macaque face may not provide enough stable
features for tracking, but I'm not very experienced with the algorithms, so
don't let my hesitations hold you back.


*2. Are there any novel ways of placing  the screen and tracker that result
in better eye-tracking? We have tried various ways of placing **trackers
below the screen and at various distances from the animal.*

You're going through the trouble of facilitating recording from free moving
macaques, and *you still want to use a screen!?!  *Doesn't that defeat the
purpose of facilitating natural behavior?  In any case, to answer this
question requires a lot more knowledge about what kind of eye tracker you
are trying to use. My guess is that you're using a remote tracker placed
near to the screen, and the degradation is due to the small size of the
pupil in the remote eye camera when the head is further away.  That's pure
speculation.


*3. Are there multi-camera eye-tracker systems that we can set-up
from  different view points so that one or more can always have a clear
view  of the animal?*

Not that I've seen. I have discussed building something like this before
with colleagues.  That would be a feat of engineering and software
development that requires a very firm grasp of multiview geometry.  That is
a multi-year project.


*4. Do these systems have hardware input for behavioral event markers
and analog/digital outputs of eye-gaze data so that we can sync it with
our neural data acquisition?*

N/A, because these systems don't yet exist.

Hope that was somewhat informative.  Sorry if it is disappointing!






----------------------

Gabriel J. Diaz, Ph.D.
Assistant Professor
Rochester Institute of Technology
Chester F. Carlson Center for Imaging Science

*Founder of PerForM Labs*
*Click for demos.* <https://www.cis.rit.edu/performlab/>

Office 2108, Building #76
Rochester, NY 14623
Office: (585) 475-6215
gabriel.diaz at rit.edu

On Mon, Jul 16, 2018 at 1:27 PM, Stefan Dowiasch <
stefan.dowiasch at physik.uni-marburg.de> wrote:

> Dear all,
>
> I am Stefan, a visiting assistant professor at the Department of
> Neurophysics at the University of Marburg and Chief Scientific Officer at
> Thomas RECORDING GmbH, Germany.
> We faced the same problems in the past and are currently working on a
> solution, which allows freely moving primates to perform behavioral tasks
> in their home cages or special arenas in combination with eye tracking and
> single cell recordings.
> Recently we finished the first step, i.e. a training and experimental unit
> for freely moving primates, which is commercially available at Thomas
> RECORDING (please see: https://www.thomasrecording.co
> m/products/neuroscience-products/primate-training-systems/
> incage-training-system-icts.html). You can find a demo video of the
> system on Youtube: https://youtu.be/yDOZauNSwqs
> In short: The system consists of a ruggedized tablet computer, a flexible
> cage-mountable holding device and an integrated reward unit. Currently the
> build-in front-facing camera can be used to monitor the animal and its
> overall behavior. However, we are currently working on a software update to
> implement basic eye tracking features (fixation control,
> saccade-antisaccade-tasks, etc.) to the system.
> Furthermore, a trigger interface for synchronization with chronic
> recording devices (e.g. the wireless version of the AMEP system
> https://www.physiology.org/doi/abs/10.1152/jn.00504.2017
> <https://www.thomasrecording.com/products/neuroscience-products/chronic-recording-devices/small-animal/thomas-wireless-system-tws.html>),
> is in development.
>
> Taken together, I think this system should meet most of your requirements
> regarding eye tracking and single unit recordings in freely moving
> primates. At the moment, you can start training your animals with the
> system and getting them used to the new environment. In the near future,
> you can upgrade your existing device with a new software package, giving
> you the possibility to track the eyes of the primate and synchronize your
> behavioral and eye tracking data with your physiological recordings.
>
> If you have further questions or suggestions, please feel free to contact
> me anytime.
>
> Best regards,
>
> Dr. Stefan Dowiasch
>
> Am 14.07.2018 um 21:09 schrieb visionlist-request at visionscience.com:
>
> Date: Sat, 14 Jul 2018 12:00:45 +0530
> From: Harish Katti <harish2006 at gmail.com> <harish2006 at gmail.com>
> To: visionlist at visionscience.com
> Subject: [visionlist] About help on eye-tracking of head free
> 	non-human primates
> Message-ID:
> 	<CAOei6hAoRnc=aApwyws4R2WiZ6EXd9K4q-JPSj+u+TwWHi9ALA at mail.gmail.com> <CAOei6hAoRnc=aApwyws4R2WiZ6EXd9K4q-JPSj+u+TwWHi9ALA at mail.gmail.com>
> Content-Type: text/plain; charset="utf-8"
>
>  Dear all
>       I am Harish, a post-doctoral fellow in Dr SP Arun's experimental
> vision group at the Centre for Neuroscience, Indian Institute of Science.
> I'm posting this to get feedback from researchers who have tried automated
> eye-gaze/head-pose/body-pose tracking of freely moving non-human primates.
>
> In our lab we are trying to setup eye tracking in monkeys without any
> head restraints. Our plan is to have a behavioural arena where the
> animal is not head-fixed and can come up to a touch screen and perform
> simple tasks in return for juice rewards. Since the animals are not
> head-fixed, the eye-tracking needs to be done in a manner that can
> handle change in body and head pose. We have been evaluating a few
> commercial eye-tracking systems but find that the trackers have
> difficulty in finding the face/eyes. It will be nice to have your inputs
> on the following issues,
>
> 1. Is there a good eye tracking system that already has macaque face
> appearance templates bulit in?
>
> 2. Are there any novel ways of placing  the screen and tracker that
> result in better eye-tracking? We have tried various ways of placing
> trackers below the screen and at various distances from the animal.
>
> 3. Are there multi-camera eye-tracker systems that we can set-up from
> different view points so that one or more can always have a clear view
> of the animal?
>
> 4. Do these systems have hardware input for behavioral event markers and
> analog/digital outputs of eye-gaze data so that we can sync it with our
> neural data acquisition.
>
> best,
> Harish
>
>
>
> _______________________________________________
> visionlist mailing list
> visionlist at visionscience.com
> http://visionscience.com/mailman/listinfo/visionlist_visionscience.com
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180717/ebe91390/attachment.html>


More information about the visionlist mailing list