System and method of enabling object auto-framing on webcam through an indicator
Described are methods and systems for auto framing an object of interest. A webcam of an information handling system captures a full field of view image that has a region of interest (ROI) that includes a pointing element, such as an active pen, user finger, or other such object. The ROI also includes the object of interest. An auto-framing AI/ML model detects the ROI and the pointing element and auto-frames the object of interest to which the pointing element is directed to.
1. A computer-implementable method for auto-framing an object of interest comprising:
capturing a full field of view image by a webcam of an information handling system (IHS);
activating an auto-framing artificial intelligence/machine learning (AI/ML) model integrated into the webcam by a peripheral manager of the IHS, to perform object auto-framing to focus on the object of interest, wherein the AI/ML model performs:
detecting a region of interest (ROI);
detecting a pointing element in the ROI;
auto-framing the object of interest to which the pointing element is directed to; and
deactivating the auto-framing AI/ML model by the peripheral manager of the IHS.
2. The computer-implementable method of claim 1 , wherein the pointing element is an active pen, and activating is performed by depressing a control on the active pen.
3. The computer-implementable method of claim 1 , wherein the pointing element is user finger, writing pen, or pencil, and activating is through a peripherals manager of an information handling system connected to the webcam.
4. The computer-implementable method of claim 1 , wherein the deactivating is through an active pen, wherein depressing a control on the active ends the auto-framing AI/ML model.
5. The computer-implementable method of claim 1 , wherein the deactivating is performed after a time the pointing element is held steady.
6. The computer-implementable method of claim 1 further comprising providing a picture in picture view of the ROI and the full field of view image.
7. An information handling system (IHS) comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations for auto-framing an object of interest comprising instructions executable by the processor and configured for:
capturing a full field of view image by a webcam of the information handling system (IHS);
activating an auto-framing artificial intelligence/machine learning (AI/ML) model integrated into the webcam by a peripheral manager of the IHS, to perform object auto-framing to focus on the object of interest, wherein the AI/ML model performs:
detecting a region of interest (ROI);
detecting a pointing element in the ROI;
auto-framing the object of interest to which the pointing element is directed to; and
deactivating the auto-framing AI/ML model by the peripheral manager of the IHS.
8. The information handling system (IHS) of claim 7 , wherein the pointing element is an active pen, and activating is performed by depressing a control on the active pen.
9. The information handling system (IHS) of claim 7 , wherein the pointing element is user finger, writing pen, or pencil, and activating is through a peripherals manager of the information handling system connected to the webcam.
10. The information handling system (IHS) of claim 7 , wherein the deactivating is through an active pen, wherein depressing a control on the active ends the auto-framing AI/ML model.
11. The information handling system (IHS) of claim 7 , wherein the deactivating is performed after a time the pointing element is held steady.
12. The information handling system (IHS) of claim 7 further comprising providing a picture in picture view of the ROI and the full field of view image.
13. A non-transitory, computer-readable storage medium embodying computer program code for auto-framing an object of interest, the computer program code comprising computer executable instructions configured for:
capturing a full field of view image by a webcam of an information handling system (IHS);
activating an auto-framing artificial intelligence/machine learning (AI/ML) model integrated into the webcam by a peripheral manager of the IHS, to perform object auto-framing to focus on the object of interest, wherein the AI/ML model performs:
detecting a region of interest (ROI);
detecting a pointing element in the ROI;
auto-framing the object of interest to which the pointing element is directed to; and
deactivating the auto-framing AI/ML model by the peripheral manager of the IHS.
14. The non-transitory, computer-readable storage medium of claim 13 , wherein the pointing element is an active pen, and activating is performed by depressing a control on the active pen.
15. The non-transitory, computer-readable storage medium of claim 13 , wherein the pointing element is user finger, writing pen, or pencil, and activating is through a peripherals manager of an information handling system connected to the webcam.
16. The non-transitory, computer-readable storage medium of claim 13 , wherein the deactivating is through an active pen, wherein depressing a control on the active ends the auto-framing AI/ML model.
17. The non-transitory, computer-readable storage medium of claim 13 , wherein the deactivating is performed after a time the pointing element is held steady.