Back to results
US 2011/0216089 A1Published application
Alignment of objects in augmented reality
AssigneeEmpire Technology Development LLC
InventorHenry Leung
Life of this patent
Estimating the term…
Abstract
Technologies are generally described for aligning objects in augmented reality. In some examples, a processor may be adapted to receive detected image data and virtual object data. In some examples, the processor may further be adapted to generate and apply weights to log-likelihood functions at intensity and feature levels based on the virtual object data and detected image data. In some examples, the processor may further be adapted to add the weighted log-likelihood function at intensity level to the weighted log-likelihood function at feature level to produce a cost function. In some examples, the processor may further be adapted to determine transformation parameters based on the cost function that may be used to align the detected image data with virtual object data.
Claims29
A method for aligning data regarding a real object and a virtual object in an augmented reality system, the method comprising:
- receiving detected image data at a processor, wherein the detected image data relates to the real object;
- receiving virtual object data at the processor, wherein the virtual object data is representative of the virtual object in the augmented reality system;
- generating, by the processor, a log-likelihood function at intensity level based on the virtual object data and the detected image data;
- generating, by the processor, a log-likelihood function at feature level based on the virtual object data and the detected image data;
- applying, by the processor, a first weight to the log-likelihood function at intensity level to produce a weighted log-likelihood function at intensity level;
- applying, by the processor, a second weight to the log-likelihood function at feature level to produce a weighted log-likelihood function at feature level;
- adding, by the processor, the weighted log-likelihood function at intensity level to the weighted log-likelihood function at feature level to produce a cost function;
- and
- determining, by the processor, transformation parameters for the detected image data based on the cost function;
- wherein the transformation parameters are effective to align the detected image data with the virtual object data.
7 more elements
A device for aligning data regarding a real object and a virtual object in augmented reality, the device comprising:
- a processor;
- and
- a memory arranged in communication with the processor;
- the processor effective to
- receive detected image data, wherein the detected image data relates to the real object;
- receive virtual object data, wherein the virtual object data is associated with the virtual object in the augmented reality;
- generate a log-likelihood function at intensity level based on the virtual object data and the detected image data;
- generate a log-likelihood function at feature level based on the virtual object data and the detected image data;
- apply a first weight to the log-likelihood function at intensity level to produce a weighted log-likelihood function at intensity level;
- apply a second weight to the log-likelihood function at feature level to produce a weighted log-likelihood function at feature level;
- add the weighted log-likelihood function at intensity level data to the weighted log-likelihood function at feature level to produce a cost function;
- determine transformation parameters for the detected image data based on the cost function;
- wherein the transformation parameters are effective to align the detected image data with the virtual object data;
- and
- store the transformation parameters in the memory.
12 more elements
A system for aligning data regarding a real object and a virtual object in augmented reality, the system comprising:
- a processor;
- a sensor arranged in communication with the processor, the sensor effective to detect detected image data, and send the detected image data from the sensor to the processor, wherein the detected image data relates to the real object;
- a memory arranged in communication with the processor;
- a display arranged in communication with the processor;
- the processor effective to
- receive the detected image data;
- receive virtual object data, wherein the virtual object data is associated with the virtual object in the augmented reality;
- generate a log-likelihood function at intensity level based on the virtual object data and the detected image data;
- generate a log-likelihood function at feature level based on the virtual object data and the detected image data;
- apply a first weight to the log-likelihood function at intensity level to produce a weighted log-likelihood function at intensity level;
- apply a second weight to the log-likelihood function at feature level to produce a weighted log-likelihood function at feature level;
- add the weighted log-likelihood function at intensity level data to the weighted log-likelihood function at feature level to produce a cost function;
- determine transformation parameters for the detected image data based on the cost function;
- wherein the transformation parameters are effective to align the detected image data with the virtual object data;
- store the transformation parameters in the memory;
- and
- align the detected image data with the virtual object data using the transformation parameters to produce enhanced image data;
- and
- wherein the display is effective to display the enhanced image data.
16 more elements
A method for aligning data regarding a real object and a virtual object in an augmented reality system, the method comprising:
- detecting detected image data by a sensor, wherein the detected image data relates to the real object;
- sending the detected image data from the sensor to a processor;
- receiving the detected image data by the processor;
- receiving virtual object data at the processor, wherein the virtual object data is representative of the virtual object in the augmented reality system;
- generating, by the processor, a log-likelihood function at intensity level based on the virtual object data and the detected image data;
- generating, by the processor, a log-likelihood function at feature level based on the virtual object data and the detected image data;
- applying, by the processor, a first weight to the log-likelihood function at intensity level to produce a weighted log-likelihood function at intensity level;
- applying, by the processor, a second weight to the log-likelihood function at feature level to produce a weighted log-likelihood function at feature level;
- adding, by the processor, the weighted log-likelihood function at intensity level to the weighted log-likelihood function at feature level to produce a cost function;
- determining, by the processor, transformation parameters for the detected image data based on the cost function, where the transformation parameters are effective to align the detected image data with the virtual object data;
- aligning the detected image data with the virtual object data using the transformation parameters by the processor to produce enhanced image data;
- and
- displaying the enhanced image data on a display, wherein the enhanced image data is representative of the virtual object in the augmented reality system.
10 more elements
A computer storage medium having computer-executable instructions stored thereon which, when executed by a computing device, adapt the computing device to perform a method for aligning data regarding a real object and a virtual object in an augmented reality system, the method comprising:
- receiving detected image data at a processor, wherein the detected image data relates to the real object;
- receiving virtual object data at the processor, wherein the virtual object data is representative of the virtual object in the augmented reality system;
- generating, by the processor, a log-likelihood function at intensity level based on the virtual object data and the detected image data;
- generating, by the processor, a log-likelihood function at feature level based on the virtual object data and the detected image data;
- applying, by the processor, a first weight to the log-likelihood function at intensity level to produce a weighted log-likelihood function at intensity level;
- applying, by the processor, a second weight to the log-likelihood function at feature level to produce a weighted log-likelihood function at feature level;
- adding, by the processor, the weighted log-likelihood function at intensity level to the weighted log-likelihood function at feature level to produce a cost function;
- and
- determining, by the processor transformation parameters for the detected image data based on the cost function;
- wherein the transformation parameters are effective to align the detected image data with the virtual object data.
7 more elements
Dependencies are inferred from the claim text.