Pulling a JPEG from V5 vision sensor

Sorry if this is incorrectly formatted at all, this is my first time posting on this forum and I am very new to vex in general.

Anyways, I want to be able to pull an image from the Vision sensor. I’m trying to do something along the lines of face tracking, but the 'signatures" are very restrictive and I want to be able to plug an image into OpenCV. I could just use the USB out to a raspberry pi, and then process it on there but I have no idea how I would get that data back into the brain. Is it possible to do either of those things?

Welcome to the VEX Forum!

I do not know if there is a way to get an image directly from the Vision Sensor camera the way you want. The vision sensor does not send image data to the V5 brain, it only sends data about what color signatures and color codes it has identified when it takes a snapshot. It does all of that processing on the vision sensor itself. It will generate a preview image when connected to the configuration utility, but I don’t know if there is a way to directly capture that image.

One thing you might try is connecting to the live stream via the WIFI on the vision sensor and getting screen captures off of that.

Also understand that the vision sensor only has a resolution of 640x400, so you might be better off using a different camera entirely, such as a USB webcam.

4 Likes