IP Library Granted Patent US 12,439,145
Granted Patent B1
US 12,439,145 · App. 17/448,638 · Granted Oct 7, 2025

Determining an intended gesture when hands are occupied

Inventors: Nathaniel R. Finney (San Francisco, CA); Jean-Charles Bernard Marcel Bazin (Sunnyvale, CA); Srimanth Gunturi (Cupertino, CA)
Assignee: Apple Inc.
H04N23/611G06F3/017G06V40/28H04N23/651H04N23/695
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,439,145
App. No.
17/448,638
Granted
Oct 7, 2025
Kind
B1
Abstract

Hand tracking techniques are used to initiate actions at a computer even if a hand is occupied. Image data is received of a scene that includes a hand. A determination is mate whether the hand is occupied by a physical object. If the hand is occupied by a physical object, then the hand is monitored for a modified gesture based on the physical object. Some objects may be pre-registered and associated with object-specific actions for various gestures. When a user is within a predetermined distance of a registered object, a system monitors a user's hands for a gesture, and then triggers an action based on the gesture and the object.

Claims (58)

1. Anon-transitory computer readable medium comprising computer readable code executable by one or more processors to:

detect that a user of a wearable device is within a predetermined distance of a first registered object of a plurality of registered object;

in response to the detection, initiate, at the wearable device, hand tracking to monitor one or more hands of the user for an interaction with the first registered object,

determine a first gesture from the interaction based on the hand tracking,

determine a first object-specific action corresponding to the first gesture and the first registered object, and

trigger, by the wearable device, the first object-specific action,

wherein the wearable device triggers a second object-specific action for the first gesture when the first gesture is determined in association with a second registered object.

2. The non-transitory computer readable medium of claim 1 , wherein the first object-specific action triggered is based on an object recognition database comprising registered actions for a plurality of gestures.

3. The non-transitory computer readable medium of claim 1 further comprising computer readable code to:

in response to the detection, initialize a camera,

wherein the first gesture is determined from image data captured by the camera.

4. The non-transitory computer readable medium of claim 3 , wherein the computer readable code to determine a first gesture from the detected interaction further comprises computer readable code to perform hand pose estimation to identify an orientation of the one or more hands.

5. The non-transitory computer readable medium of claim 4 , wherein the computer readable code to perform hand pose estimation to identify an orientation of the hand further comprises computer readable code to apply, to the image data, a network trained on image data of hands performing a plurality of gestures.

6. The non-transitory computer readable medium of claim 1 , wherein the computer readable code to detect that the user is within a predetermined distance of the first registered object is processed in a first system mode, and where the first gesture is detected in a second system mode.

7. The non-transitory computer readable medium of claim 1 , wherein the computer readable code to detect that a user is within a predetermined distance of a first registered object further comprises computer readable code to track a location of the user in relation to each of the plurality of registered objects.

8. The non-transitory computer readable medium of claim 1 , further comprising computer readable code to:

detect that the user is within a predetermined distance of a second registered object;

in accordance with the detection that the user is within a predetermined distance of the second registered object, monitor the one or more hands of the user for an interaction with the second registered object;

in the interaction with the second registered object, detect a second gesture from the interaction; and

trigger a second action associated with the second registered object and the second gesture, wherein the first action is different than the second action, and wherein the first gesture is equivalent to the second gesture.

9. A system comprising:

one or more processors; and

one or more computer readable media comprising computer readable code executable by the one or more processors to:

detect that a user of a wearable device is within a predetermined distance of a first registered object of a plurality of registered objects;

in response to the detection, initiate hand tracking to monitor one or more hands of the user for an interaction with the first registered object,

determine a first gesture from the interaction based on the hand tracking,

determine a first object-specific action corresponding to the first gesture and the first registered object, and

trigger, by the wearable device, the first object-specific action,

wherein the wearable device triggers a second object-specific action for the first gesture when the first gesture is determined in association with a second registered object.

10. The system of claim 9 , wherein the first object-specific action triggered is based on an object recognition database comprising registered actions for a plurality of gestures.

11. The system of claim 9 , further comprising computer readable code to:

in response to the detection, initialize a camera,

wherein the first gesture is determined from image data captured by the camera.

12. The system of claim 11 , wherein the computer readable code to determine a first gesture from the detected interaction further comprises computer readable code to perform hand pose estimation to identify an orientation of the one or more hands.

13. The system of claim 12 , wherein the computer readable code to perform hand pose estimation to identify an orientation of the hand further comprises computer readable code to apply, to the image data, a network trained on image data of hands performing a plurality of gestures.

14. The system of claim 9 , wherein the computer readable code to detect that the user is within a predetermined distance of the registered object is processed in a first system mode, and where the gesture is detected in a second system mode.

15. The system of claim 9 , wherein the computer readable code to detect that a user is within a predetermined distance of a first registered object further comprises computer readable code to track a location of the user in relation to each of the plurality of registered objects.

16. The system of claim 9 , further comprising computer readable code to:

detect that the user is within a predetermined distance of a second registered object;

in accordance with the detection that the user is within a predetermined distance of the second registered object, monitor the one or more hands of the user for an interaction with the second registered object;

in accordance with the interaction with the second registered object, detect a second gesture from the interaction; and

trigger a second action associated with the second registered object and the second gesture, wherein the first action is different than the second action, and wherein the first gesture is equivalent to the second gesture.

17. A method comprising:

detecting that a user of a wearable device is within a predetermined distance of a first registered object of a plurality of registered object;

in response to the detection, initiating hand tracking to monitor one or more hands of the user for an interaction with the first registered object,

determining a first gesture from the interaction based on the hand tracking,

determine a first object-specific action corresponding to the first gesture and the first registered object, and

triggering, by the wearable device, the first object-specific action,

wherein the wearable device triggers a second object-specific action for the first gesture when the first gesture is determined in association with a second registered object.

18. The method of claim 17 , wherein the first object-specific action triggered is based on an object recognition database comprising registered actions for a plurality of gestures.

19. The method of claim 17 , further comprising:

in response to the detection, initializing a camera,

wherein the first gesture is determined from image data captured by the camera.

20. The method of claim 17 , further comprising:

detecting that the user is within a predetermined distance of a second registered object;

in accordance with the detection that the user is within a predetermined distance of the second registered object, monitoring the one or more hands of the user for an interaction with the second registered object;

in accordance with the interaction with the second registered object, detecting a second gesture from the interaction; and

triggering a second action associated with the second registered object and the second gesture, wherein the first action is different than the second action, and wherein the first gesture is equivalent to the second gesture.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 8, 2025
From: FINNEY, NATHANIEL R.; BAZIN, JEAN-CHARLES BERNARD MARCEL; GUNTURI, SRIMANTH
To: APPLE INC.
Reel/Frame 072185/0314 →
Continuity (1)
Provisional Application 63083341 · Sep 25, 2020
References Cited (46)
US 8760398B2 · Pryor · 2014 [cited by applicant]
US 9727145B2 · Murase · 2017 [cited by applicant]
US 9766709B2 · Holz · 2017 [cited by applicant]
US 10127886B2 · Schwarz · 2018 [cited by applicant]
US 10311638B2 · Da Veiga · 2019 [cited by examiner]
US 10360734B2 · Drouin · 2019 [cited by applicant]
US 10416834B1 · Holz · 2019 [cited by applicant]
US 10712837B1 · Douglas · 2020 [cited by applicant]
US 10809808B2 · Goel · 2020 [cited by applicant]
US 10845885B2 · Bostick · 2020 [cited by applicant]
US 10937240B2 · Anderson · 2021 [cited by applicant]
US 11023036B1 · Atlas · 2021 [cited by applicant]
US 11106327B2 · Mani · 2021 [cited by applicant]
US 20080170776A1 · Albertson · 2008 [cited by applicant]
US 20150140535A1 · Geri · 2015 [cited by applicant]
US 20150331576A1 · Piya · 2015 [cited by applicant]
US 20150346829A1 · Chang · 2015 [cited by applicant]
US 20160027188A1 · Marks · 2016 [cited by applicant]
US 20160071319A1 · Fallon · 2016 [cited by applicant]
US 20160100051A1 · Yliaho · 2016 [cited by examiner]
US 20170097687A1 · Pinault · 2017 [cited by applicant]
US 20170161957A1 · Yajima · 2017 [cited by applicant]
US 20180004780A1 · Walker · 2018 [cited by applicant]
US 20180095542A1 · Mallinson · 2018 [cited by applicant]
US 20180189974A1 · Clark · 2018 [cited by applicant]
US 20180325601A1 · Mak · 2018 [cited by applicant]
US 20190034076A1 · Fnu · 2019 [cited by applicant]
US 20190043260A1 · Anderson · 2019 [cited by applicant]
US 20190324549A1 · Araki · 2019 [cited by applicant]
US 20190346967A1 · Ikeda · 2019 [cited by applicant]
US 20190370984A1 · Tsai et al. · 2019 [cited by applicant]
US 20200110928A1 · Al Jazaery · 2020 [cited by examiner]
US 20200142495A1 · Steinberg · 2020 [cited by applicant]
US 20200341538A1 · Zhu · 2020 [cited by applicant]
US 20210034870A1 · Ha · 2021 [cited by applicant]
US 20210287330A1 · Nagano · 2021 [cited by applicant]
US 20220215677A1 · Kaji · 2022 [cited by applicant]
Angelini, Leonardo, et al. “Move, hold and touch: a framework for tangible gesture interactive systems.” Machines 3.3 (2015): 173-207. (Year: 2015). [cited by examiner]
Kim, Jungsoo, et al. “The gesture watch: A wireless contact-free gesture based wrist interface.” 2007 11th IEEE International Symposium on Wearable Computers. IEEE, 2007. (Year: 2007). [cited by examiner]
“Using Kinect to draw 3D AutoCAD polylines,” Through the Interface(https://www.keanw.com/), Apr. 21, 2011. [cited by applicant]
Cheng, et al., “iCON: Utilizing Everyday Objects as Additional, Auxiliary and Instant Tabletop Controllers,” Proceedings of the 2010 SIGCHI Conference on Human Factors in Computing Systems, Apr. 2010. [cited by applicant]
Choi, et al., “CLAW: A Multifunctional Handheld Haptic Controller for Grasping, Touching, and Triggering in Virtual Reality,” Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, Apr. 2018. [cited by applicant]
Matt, “Draw in 3d with the Kinect,” Kinect Hacks, Feb. 22, 2011. [cited by applicant]
Sharma, et al., “Grasping Microgestures: Eliciting Single-hand Microgestures for Handheld Objects,” Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, May 2019. [cited by applicant]
Zhou, et al., “Gripmarks: Using Hand Grips to Transform In-Hand Objects into Mixed Reality Input,” CHI 2020 Paper, Apr. 2020. [cited by applicant]
Wolf, Katrin, et al. “A taxonomy of microinteractions: Defining microgestures based on ergonomic and scenario-Dependent requirements.”Human-ComputerInteration—INTERACT 2011:13th IFIP TC 13 International Conference, Port… [cited by applicant]