- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I have been looking into calibrating an external projector and depth camera as seen in this video (https://www.youtube.com/watch?v=JMcmPX8oy94)
Ideally I want to use multiple depth camera's and multiple projectors to increase FOV and decrease occlusion. Does anyone know of any calibration tools that can get the matrix so that I can apply this to a camera inside Unity3d?
I have seen this that can be used with Kinects: https://github.com/microsoft/RoomAliveToolkit/tree/master/ProCamCalibration
But nothing for Realsense Cameras
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
With the 400 Series cameras, you can just drop external projectors into a room without aligning them to the camera. Intel's excellent illustrated camera tuning guide has a section on this.
https://realsense.intel.com/wp-content/uploads/sites/63/BKM-For-Tuning-D435-and-D415-Cameras-Webinar_Rev3.pdf
An extract of the projector section of the guide is provided below. Please left-click on the image to view it in full size.
If you want to get the calibration details of the camera though, you can use the RealSense SDK's enumerate-devices tool.
https://github.com/IntelRealSense/librealsense/tree/master/tools/enumerate-devices
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thanks for the reply but this is to do with improving tracking with external projectors. I want to align a projector to the depth camera.
Imagine only showing content on top of a person or hand. So the depth camera tracks the person/hand and creates a mask. This is then used on the projector to project video content over the specified mask. I need to convert the mask from the depth camera into external projector space
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
My apologies, I see your intended use of cameras and *image* projectors now to create a multi-camera "volumetric scan" of the room. A member of Intel did an interesting presentation on capturing real world data with multiple cameras and translating it into a virtual representation. This may give you some useful research leads.

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page