Method for developing augmented reality experiences in low computer power systems and devices
AssigneeShoppar, Ltd.
InventorSina Viseh
Life of this patent
Estimating the term…
Abstract
A method and system for generating an augmented reality experience without a physical marker. At least two frames from a video stream are collected and one of the frames is designated as a first frame. The graphical processor of a device prepares two collected frames for analysis and features from the two collected frames are selected for comparison. The central processor of the device isolates points on a same plane as a tracked point in the first frame and calculates a position of a virtual object in a second frame in 2D. The next frame from the video stream is collected and the process is repeated until the user navigates away from the URL, webpage or when the camera is turned off. The central processor renders the virtual object on a display of the device.
Claims20
A method for generating an augmented reality experience without a physical marker, comprising the steps of:
- a) collecting at least two frames from a video stream and designating one of the frames as a first frame;
- b) preparing said at least two collected frames for analysis by a graphical processor of a device
- c) selecting features from said at least two collected frames for comparison;
- d) isolating points on a same plane as a tracked point in the first frame by a central processor of the device;
- e) calculating a position of a virtual object in a second frame of the said at least two collected frames in 2D by the central processor;
- f) collecting a next frame from the video stream, designating the second frame as the first frame and designating the next frame as the second frame;
- g) rendering the virtual object on a display of the device to provide the augmented reality experiences on a web browser by the graphical processor;
- and
- h) repeating the steps b)-g) continuously until terminated by a user;
- and
- wherein the step of isolating points on the same plane as the track point in the first frame by the central processor comprises steps of removing outlier data using random sample consensus, removing outlier data again using random sample consensus, and calculating homographic transformation using at least four points.
A non-transitory storage medium comprising a program for generating an augmented reality experience without a physical marker when executed by a processor-based device to cause the device to:
- a) collect at least two frames from a video stream and designate one of the frames as a first frame;
- b) prepare said at least two collected frames for analysis by a graphical processor of the device
- c) select features from said at least two collected frames for comparison;
- d) isolate points on a same plane as a tracked point in the first frame by a central processor of the device to provide the augmented reality experiences with 6 degrees of freedom views by removing outlier data using random sample consensus, identifying points on the same plane as the track point, removing outlier data again using random sample consensus, and calculating homographic transformation using at least four points;
- e) calculate a position of a virtual object in a second frame of the said at least two collected frames in 2D by the central processor;
- f) collect a next frame from the video stream, designate the second frame as the first frame and designate the next frame as the second frame;
- g) render the virtual object on a display of the device to provide the augmented reality experiences on a web browser by the graphical processor;
- h) repeat b)-g) continuously until terminated by a user.
A method for generating an augmented reality experience without a physical marker, comprising the steps of:
- a) collecting at least two frames from a video stream and designating one of the frames as a first frame;
- b) preparing said at least two collected frames for analysis by a graphical processor of a device
- c) selecting features from said at least two collected frames for comparison;
- d) isolating points on a same plane as a tracked point in the first frame by a central processor of the device;
- e) calculating a position of a virtual object in a second frame of the said at least two collected frames in 2D by the central processor;
- f) collecting a next frame from the video stream, designating the second frame as the first frame and designating the next frame as the second frame;
- g) rendering the virtual object on a display of the device to provide the augmented reality experiences on a web browser by the graphical processor;
- and
- h) repeating the steps b)-g) continuously until terminated by a user;
- and
- wherein the step of preparing the collected frames comprises steps of reducing a resolution of the collected frames by down-sampling, converting the collected frames to grayscale, applying an equalizer and blur to the collected frames, and generates a pyramid representation of the collected frames.
A method for generating an augmented reality experience without a physical marker, comprising the steps of:
- a) collecting at least two frames from a video stream and designating one of the frames as a first frame;
- b) preparing said at least two collected frames for analysis by a graphical processor of a device
- c) selecting features from said at least two collected frames for comparison;
- d) isolating points on a same plane as a tracked point in the first frame by a central processor of the device;
- e) calculating a position of a virtual object in a second frame of the said at least two collected frames in 2D by the central processor;
- f) collecting a next frame from the video stream, designating the second frame as the first frame and designating the next frame as the second frame;
- g) rendering the virtual object on a display of the device to provide the augmented reality experiences on a web browser by the graphical processor;
- and
- h) repeating the steps b)-g) continuously until terminated by a user;
- and
- wherein the step of selecting features comprises steps of limiting an analysis to a smaller target area less than at least 30% of an original target area, extracting features, sorting best features for comparison, and matching features on adjacent frames, thereby reducing an area of the display that is processed and reducing a required processing per cycle.
Dependencies are inferred from the claim text.