- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
In addition:
PXCMFaceData.HeadPosition.headCenter = DetectionData.QueryBoundingRect().centerPos?
Thanks.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The QueryHeadPosition instruction, which is part of the HeadPosition instruction set, may be what you need. The documentation says that "the QueryHeadPosition function returns the face center point position."
https://software.intel.com/sites/landingpage/realsense/camera-sdk/v1.1/documentation/html/queryheadposition_posedata_pxcfacedata.html QueryHeadPosition
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
QueryHeadPosition returns is the depthCamere space, not the screen space...
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
So if you want the screen space (image) coordinates, I think you are looking to project to Color coordinates?
The best match I could find to what you wanted was using the Image component of the LandmarkPoint instruction to get the color image coordinates of a landmark point on the face
https://software.intel.com/sites/landingpage/realsense/camera-sdk/v1.1/documentation/html/landmarkpoint_pxcfacedata.html LandmarkPoint (+JS,+UWP)
An alternative to looking for a specific face landmark would be to get the color coordinates using the more general ProjectCameraToColor instruction.
https://software.intel.com/sites/landingpage/realsense/camera-sdk/v1.1/documentation/html/projectcameratocolor_pxcprojection.html ProjectCameraToColor
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page