System and method for determining directionality of imagery using head tracking
There is provided a system and method for reinstating directionality of onscreen displays of three-dimensional (3D) imagery using sensor data capturing eye location of a user. The method can include: receiving the sensor data capturing the eye location of the user; tracking the location of the eyes of the user relative to a screen using the captured sensor data; determining an updated rendering of the onscreen imagery using off-axis projective geometry based on the tracked location of the eyes of the user to simulate an angled viewpoint of the onscreen imagery from the perspective of the location of the user; and outputting the updated rendering of the onscreen imagery on a display screen.
1 . A computer-implemented method for determining directionality of an onscreen display of three-dimensional (3D) images using sensor data from a sensor that captures eye location of a user, the method comprising:
receiving the sensor data from the sensor that captures the eye location of the user;
tracking the location of the eyes of the user relative to a screen displaying the onscreen display of 3D images using the received sensor data;
determining a rendering of the onscreen displays of 3D images using off-axis projective geometry based on the tracked location of the eyes of the user to simulate a viewpoint of the onscreen displays of 3D images from a perspective of the location of the eyes of the user, the off-axis projective geometry is used to simulate motion parallax by applying a homogenous matrix that depends on the location of the object relative to the location of the eyes of the user and the location of the object relative to a device capturing the object; and
displaying the rendering of the onscreen displays of 3D images on the screen.
2 . The method of claim 1 , wherein the sensor data comprises a series of images captured by the sensor directed at the eyes of the user, the sensor being a camera.
3 . The method of claim 2 , wherein the location of the eyes of the user is determined using a perspective-n-point algorithm.
4 . The method of claim 3 , wherein the location of the eyes of the user is determined using Light Detection and Ranging (Lidar) or RGB-D cameras.
5 . The method of claim 2 , wherein determining the rendering of the onscreen displays of 3D images comprises determining the off-axis projective geometry by projecting the images captured by the sensor onto a plane that is projected to be in a same location relative to a camera-projector as the user is relative to the camera position, and copying the content of the planar canvas onto a screen buffer of the screen.
6 . The method of claim 1 , wherein the onscreen displays of 3D images comprises a three-dimensional object, and wherein determining the rendering of the onscreen displays of 3D images comprises rendering a viewing angle of the three-dimensional object based on the location of the eyes of the user relative to the screen.
7 . The method of claim 6 , wherein the sensor data further comprises facial features to extract a facial expression, and wherein the three-dimensional object comprises a three-dimensional avatar of the user mimicking the user's facial expressions.
8 . The method of claim 1 , wherein the onscreen displays of 3D images comprises a recorded video of a secondary user, the video recorded by an array of cameras to film multiple viewpoints of the secondary user, and wherein the viewpoint of the onscreen displays of 3D images for the user matches at least one of the multiple viewpoints.
9 . The method of claim 8 , wherein the array of cameras comprises four cameras.
10 . A system for determining directionality of an onscreen display of three-dimensional (3D) images using sensor data from a sensor that captures eye location of a user, the system comprising one or more processors in communication with a memory storage, the one or more processors configured to execute:
an input module to receive, from the sensor, the sensor data that captures the eye location of the user;
a tracking module to track the location of the eyes of the user relative to a screen displaying the onscreen display of 3D images using the received sensor data;
a rendering module to determine a rendering of the onscreen displays of 3D images using off-axis projective geometry based on the tracked location of the eyes of the user to simulate a viewpoint of the onscreen displays of 3D images from a perspective of the location of the eyes of the user, the off-axis projective geometry is used to simulate motion parallax by applying a homogenous matrix that depends on the location of the object relative to the location of the eyes of the user and the location of the object relative to a device capturing the object; and
an output module to display the rendering of the onscreen displays of 3D images on the screen.
11 . The system of claim 10 , wherein the sensor comprises a camera and the sensor data comprises a series of images captured by the sensor directed at the eyes of the user, the sensor being a camera.
12 . The system of claim 11 , wherein the location of the eyes of the user is determined using a perspective-n-point algorithm.
13 . The system of claim 12 , wherein the location of the eyes of the user is determined using Light Detection and Ranging (Lidar) or RGB-D cameras.
14 . The system of claim 11 , wherein determining the rendering of the onscreen displays of 3D images comprises determining the off-axis projective geometry by projecting the images captured by the sensor onto a plane that is projected to be in a same location relative to a camera-projector as the user is relative to the camera position, and copying the content of the planar canvas onto a screen buffer of the screen.
15 . The system of claim 10 , wherein the onscreen displays of 3D images comprises a three-dimensional object, and wherein determining the rendering of the onscreen displays of 3D images comprises rendering a viewing angle of the three-dimensional object based on the location of the eyes of the user relative to the screen.
16 . The system of claim 15 , wherein the sensor data further comprises facial features to extract a facial expression, and wherein the three-dimensional object comprises a three-dimensional avatar of the user mimicking the user's facial expressions.
17 . The system of claim 10 , wherein the onscreen displays of 3D images comprises a recorded video of a secondary user, the video recorded by an array of cameras to film multiple viewpoints of the secondary user, and wherein the viewpoint of the onscreen displays of 3D images for the user matches at least one of the multiple viewpoints.
18 . The system of claim 17 , wherein the array of cameras comprises four cameras.