Which camera do I use to film?

Hi there,

I am in the early stages of designing my experiment and plan to use Deeplabcuts to analyze the data.

Which camera do you recommend to use for collecting the data? My video will be 20 minutes and it will be of an infant (need color).

Thank you,
Shana

One of the nice things about using Deeplabcut is that because of the way it processes images, its performance can work across many different cameras as long as you label some example data from each camera. For example, some of my sessions were recorded with color, some in black and white, and some with nice cameras vs. some with a relatively cheap webcam, and one single DLC model works well across all of them.

So I think your most important considerations as far as what camera to use should be sharp enough images for what your specific needs are - e.g. maybe you need to track fingers individually, versus just where hands are generally. The tradeoff here is that high-resolution videos take longer to process, and you need to have space to store long videos (adds up very quickly in my experience!)

(P.S. Less of a camera issue and more of a session setup consideration, but one thing to keep in mind is that giving labeled training data from many different angles will help to keep the labeling stable across future datasets!)

2 Likes

Maybe the PS3Eye camera would get at your needs. See: https://optogeneticsandneuralengineeringcore.gitlab.io/ONECoreSite/projects/

Please email us with questions/problems/suggestions and acknowledge the ONE Core (email and suggested wording in the link).

The paper that used the PS3eye first is https://www.sciencedirect.com/science/article/pii/S0165027017302509?via%3Dihub#fig0005https://www.sciencedirect.com/science/article/pii/S0165027017302509?via%3Dihub#fig0005, so I would suggest that is cited if used :wink:

Also check out the details in the UserGuide, from where I’m quoting: “Camera(s): The toolbox is robust to extraction of poses from data collected by many cameras. There are no a priori limitations in terms of lighting; color or greyscale images are acceptable, videos captured under infrared light, and inhomogeneous or natural lighting can be used. Cameras should be placed such that the features the
user wishes to track are visible. For reference, as reported in the original DLC paper, the following cameras have been used for video capture: Point Grey Firefly (FMVU-03MTM-CS), Grasshopper 3 4.1MP Mono USB3 Vision (CMOSIS CMV4000-3E12), infrared-sensitive CMOS camera from Basler. Here, the Cheetahs were filmed with GoPro Hero 5 Session cameras, and DFK-37BUX287 cameras from The Imaging Source, Inc. were used to film mice.”

1 Like