Abstract: An example system includes a pose engine to determine a pose of a camera based on an environmental measurement. The system also includes a transform engine to determine a transform to apply to frames captured by the camera based on the pose of the camera. The system includes a correction engine to apply the transform to the frames captured by the camera in substantially real-time with capturing of the frames.

Abstract: An example calibration device includes a projector projecting a first light region including a first area onto and extending over a border of a non-patterned touch mat. A camera captures a first image of the first light region. A processor establishes a first set of four corner coordinates of the touch mat. The projector projects a second light region including a second area onto the touch mat. The second area is smaller than the first area. The camera captures a second image of the second light region. The processor performs a perspective transformation of the second image using the first set of corner coordinates and a resolution of the second light region to get a second set of four corner coordinates of the touch mat in a coordinate plane of the projector. The processor aligns the first and second set of four corner coordinates.

Abstract: An example method includes receiving by a processor of an image capturing device, an image of a quadrilateral object captured by a camera of the image capturing device. A homography matrix is calculated by the processor based on the image of the quadrilateral object and a known dimension of the quadrilateral object. The processor performs a keystone correction based on the homography matrix to convert a subsequent image captured by the camera into a corrected image.

Abstract: An example system includes a pose engine to determine a pose of a camera based on an environmental measurement. The system also includes a transform engine to determine a transform to apply to frames captured by the camera based on the pose of the camera. The system includes a correction engine to apply the transform to the frames captured by the camera in substantially real-time with capturing of the frames.

Abstract: An example method includes receiving by a processor of an image capturing device, an image of a quadrilateral object captured by a camera of the image capturing device. A homography matrix is calculated by the processor based on the image of the quadrilateral object and a known dimension of the quadrilateral object. The processor performs a keystone correction based on the homography matrix to convert a subsequent image captured by the camera into a corrected image.

Abstract: An example calibration device includes a projector projecting a first light region including a first area onto and extending over a border of a non-patterned touch mat. A camera captures a first image of the first light region. A processor establishes a first set of four corner coordinates of the touch mat. The projector projects a second light region including a second area onto the touch mat. The second area is smaller than the first area. The camera captures a second image of the second light region. The processor performs a perspective transformation of the second image using the first set of corner coordinates and a resolution of the second light region to get a second set of four corner coordinates of the touch mat in a coordinate plane of the projector. The processor aligns the first and second set of four corner coordinates.