Resource-responsive motion capture
View Patent ↗The technology disclosed relates to operating a motion-capture system responsive to available computational resources. In particular, it relates to assessing a level of image acquisition and image-analysis resources available using benchmarking of system components. In response, one or more image acquisition parameters and/or image-analysis parameters are adjusted. Acquisition and/or analysis of image data are then made compliant with the adjusted image acquisition parameters and/or image-analysis parameters. In some implementations, image acquisition parameters include frame resolution and frame capture rate and image-analysis parameters include analysis algorithm and analysis density.
1. A method of operating a motion-capture system, comprising at least a camera, responsive to available image acquisition resources and image-analysis resources, the method including:
assessing a level of the image acquisition resources available using benchmarking of acquisition components of the motion-capture system, the benchmarking of the acquisition components including evaluating processing capabilities of the acquisition components;
adjusting, in response to the level of the image acquisition resources, one or more image acquisition parameters, wherein the one or more image acquisition parameters include a frame size and a frame capture rate;
capturing, by a camera of the motion-capture system, a sequence of digital image frames to acquire image data for an object of interest, the sequence of digital image frames being captured in compliance with the adjusted one or more image acquisition parameters; and
analyzing the image data to detect the object of interest and to approximate a contour of the object of interest.
2. The method of claim 1 , further including:
assessing a level of the image-analysis resources available using benchmarking of analysis components of the motion-capture system; and
adjusting, in response to the level of the image-analysis resources, one or more image-analysis parameters that include an analysis algorithm and an analysis density,
wherein the analyzing of the image data is compliant with the adjusted one or more image-analysis parameters.
3. The method of claim 2 , wherein the adjusting of the image-analysis parameters further includes reducing the frame size by resampling to a lower resolution.
4. The method claim 2 , further including identifying a position and a shape of the object of interest based on the analyzing of the image data.
5. The method of claim 2 , wherein the analyzing of the image data further includes approximating a plurality of closed curves across the detected object of interest that collectively defines the approximated contour of the object of interest.
6. The method of claim 5 , wherein an image-analysis parameter of the one or more image-analysis parameters is a density of the plurality of closed curves.
7. The method of claim 2 ,
wherein each digital image frame of the sequence of digital image frames includes a sequence of data lines, and
wherein at least one image-analysis parameter of the one or more image-analysis parameters specifies a number of data lines analyzed per digital image frame in approximating the contour of the object of interest.
8. The method of claim 2 , wherein the adjusting of the one or more image-analysis parameters includes at least analyzing a reduced amount of image data per digital image frame.
9. The method of claim 1 , wherein the processing capabilities of the acquisition components include at least one capacity parameter of the acquisition components.
10. The method of claim 1 , wherein the benchmarking of the acquisition components includes evaluating a USB bus capacity of a channel that couples an acquisition component to a system board of the motion-capture system.
11. The method of claim 1 , wherein the processing capabilities of the acquisition components include at least a processor speed and a number of processor cores.
12. The method of claim 1 , wherein the processing capabilities of the acquisition components include at least one of a memory throughput and a bus speed.
13. The method of claim 1 , wherein the processing capabilities of the acquisition components include at least one of a graphics pipeline architecture, graphics memory availability, and an amount of cache memory.
14. The method of claim 1 , further including identifying, via a performance database, adjusted values of image acquisition parameters for evaluated values of capacity parameters.
15. The method of claim 1 , wherein the benchmarking is performed repeatedly during a motion capture operation of the motion-capture system, so as to periodically assess the level of the image acquisition resources available and adjust the one or more image acquisition parameters.
16. A method of operating a motion-capture system, which includes at least a camera, responsive to available image acquisition resources and image-analysis resources, the method including:
assessing a level of the image-analysis resources available using benchmarking of analysis components of the motion-capture system, the benchmarking of the analysis components including evaluating processing capabilities of the analysis components;
adjusting, in response to the level of the image-analysis resources, one or more image-analysis parameters, wherein the one or more image-analysis parameters include an analysis algorithm and an analysis density;
capturing, by a camera of the motion-capture system, a sequence of digital image frames to acquire image data for an object of interest; and
analyzing the digital image frames in compliance with the adjusted one or more image-analysis parameters, the image data being analyzed to detect the object of interest and to approximate a contour of the object of interest.
17. The method of claim 16 , wherein the adjusting of the one or more image-analysis parameters further includes reducing a frame size by resampling to a lower resolution.
18. The method claim 16 , further including identifying a position and a shape of the object of interest based on the analyzing of the digital image frames.
19. The method of claim 16 , wherein the analyzing of the digital image frames further includes approximating a plurality of closed curves across the object of interest that collectively defines the approximated contour of the object of interest.
20. The method of claim 19 , wherein an image-analysis parameter of the one or more image-analysis parameters is a density of the plurality of closed curves.
21. The method of claim 16 ,
wherein each digital image frame of the sequence of digital image frames includes a sequence of data lines, and
wherein at least one image-analysis parameter of the one or more image-analysis parameters specifies a number of data lines analyzed per digital image frame in approximating the contour of the object of interest.