Tracking an apparatus for human-machine interactions
The combination of computer-vision and ultrasonic tracking with inertial data in a tightly-coupled fusion algorithm addresses the limitations of existing techniques, improving precision and robustness for handheld controller tracking in extended reality systems.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- QUALCOMM INC
- Filing Date
- 2024-12-18
- Publication Date
- 2026-06-25
AI Technical Summary
Existing controller-tracking techniques for handheld devices in extended reality systems face challenges such as sensitivity to light interference, limited field of view, and susceptibility to environmental noise, which affect precision and robustness, especially in bright environments.
A tightly-coupled fusion algorithm combining computer-vision-based and ultrasonic tracking techniques, utilizing light sources and transducers, along with inertial data from an IMU, to enhance tracking precision and robustness by fusing image-based, audio-based, and motion-based data.
The fusion algorithm improves tracking precision and robustness, especially in bright environments, providing wider tracking field of view and quicker recovery from occlusions, enhancing user experience.
Smart Images

Figure CN2024140204_25062026_PF_FP_ABST
Abstract
Description
TRACKING AN APPARATUS FOR HUMAN-MACHINE INTERACTIONSTECHNICAL FIELD
[0001] The present disclosure generally relates to a human-machine interactions. For example, aspects of the present disclosure relate to systems and techniques for tracking a human-machine-interface (HMI) device.BACKGROUND
[0002] A handheld controller is an example of an HMI device. Such a handheld controller may allow a user to interact with a machine by pressing or activating buttons on the handheld controller and / or through a position and / or motion of the handheld controller. Handheld controllers can be used with extended-reality (XR) systems.SUMMARY
[0003] The following presents a simplified summary relating to one or more aspects disclosed herein. Thus, the following summary should not be considered an extensive overview relating to all contemplated aspects, nor should the following summary be considered to identify key or critical elements relating to all contemplated aspects or to delineate the scope associated with any particular aspect. Accordingly, the following summary presents certain concepts relating to one or more aspects relating to the mechanisms disclosed herein in a simplified form to precede the detailed description presented below.
[0004] Systems and techniques are described for tracking a human-machine-interface device. According to at least one example, a method is provided for tracking a human-machine-interface device. The method includes: determining image-based data comprising a position associated with a controller in an image; determining audio-based data based on an audio signal output by the controller and captured at one or more microphones; and determining a pose of the controller based on the image-based data and the audio-based data.
[0005] In another example, an apparatus for tracking a human-machine-interface device is provided that includes at least one memory and at least one processor (e.g., configured in circuitry) coupled to the at least one memory. The at least one processor configured to: determine image-based data comprising a position associated with a controller in an image; determine audio-based data based on an audio signal output by the controller and captured at one or more microphones; and determine a pose of the controller based on the image-based data and the audio-based data.
[0006] In another example, a non-transitory computer-readable medium is provided that has stored thereon instructions that, when executed by one or more processors, cause the one or more processors to: determine image-based data comprising a position associated with a controller in an image; determine audio-based data based on an audio signal output by the controller and captured at one or more microphones; and determine a pose of the controller based on the image-based data and the audio-based data.
[0007] In another example, an apparatus for tracking a human-machine-interface device is provided. The apparatus includes: means for determining image-based data comprising a position associated with a controller in an image; means for determining audio-based data based on an audio signal output by the controller and captured at one or more microphones; and means for determining a pose of the controller based on the image-based data and the audio-based data.
[0008] In some aspects, one or more of the apparatuses described herein is, can be part of, or can include an extended reality device (e.g., a virtual reality (VR) device, an augmented reality (AR) device, or a mixed reality (MR) device) , a vehicle (or a computing device, system, or component of a vehicle) , a mobile device (e.g., a mobile telephone or so-called “smart phone” , a tablet computer, or other type of mobile device) , a smart or connected device (e.g., an Internet-of-Things (IoT) device) , a wearable device, a personal computer, a laptop computer, a video server, a television (e.g., a network-connected television) , a robotics device or system, or other device. In some aspects, each apparatus can include an image sensor (e.g., a camera) or multiple image sensors (e.g., multiple cameras) for capturing one or more images. In some aspects, each apparatus can include one or more displays for displaying one or more images, notifications, and / or other displayable data. In some aspects, each apparatus can include one or more speakers, one or more light-emitting devices, and / or one or more microphones. In some aspects, each apparatus can include one or more sensors. In some cases, the one or more sensors can be used for determining a location of the apparatuses, a state of the apparatuses (e.g., a tracking state, an operating state, a temperature, a humidity level, and / or other state) , and / or for other purposes.
[0009] This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used in isolation to determine the scope of the claimed subject matter. The subject matter should be understood by reference to appropriate portions of the entire specification of this patent, any or all drawings, and each claim.
[0010] The foregoing, together with other features and aspects, will become more apparent upon referring to the following specification, claims, and accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Illustrative examples of the present application are described in detail below with reference to the following figures:
[0012] FIG. 1A is a diagram illustrating an example handheld controller including a number of light sources (e.g., light-emitting diodes) arranged on a tracking ring protruding from a handle of the handheld controller;
[0013] FIG. 1B is a diagram illustrating an example handheld controller including a number of light sources (e.g., LEDs) arranged on a body of the handheld controller;
[0014] FIG. 2 is a diagram illustrating an example handheld controller including a number of transducers arranged on a tracking ring protruding from a handle of the handheld controller;
[0015] FIG. 3 is a diagram illustrating an example handheld controller including a number of transducers and a number of light sources arranged on a tracking ring protruding from a handle of the handheld controller;
[0016] FIG. 4A is a diagram illustrating an example system including a tracking system for tracking a handheld controller, according to various aspects of the present disclosure;
[0017] FIG. 4B is a block diagram illustrating example elements of the handheld controller and the tracking system of system 400 of FIG. 4A, according to various aspects of the present disclosure;
[0018] FIG. 5 is a block diagram illustrating an example system for tracking a handheld controller, according to various aspects of the present disclosure;
[0019] FIG. 6 is a hybrid block-diagram-flow-diagram illustrating an example implementation of the computer-vision pipeline of the system of FIG. 5, according to various aspects of the present disclosure;
[0020] FIG. 7 is a block diagram illustrating an example implementation of the audio pipeline of the system of FIG. 5, according to various aspects of the present disclosure;
[0021] FIG. 8 is a hybrid block-diagram-flow-diagram illustrating an example implementation of the fusor of the system of FIG. 5, according to various aspects of the present disclosure;
[0022] FIG. 9 is a diagram illustrating a system including microphones of a tracking system for tracking a controller including transducers, according to various aspects of the present disclosure;
[0023] FIG. 10 is a flow diagram illustrating an example process for tracking a human-machine-interface device, in accordance with aspects of the present disclosure;
[0024] FIG. 11 is a block diagram illustrating an example of a deep learning neural network that can be used to perform various tasks, according to some aspects of the disclosed technology;
[0025] FIG. 12 is a block diagram illustrating an example of a convolutional neural network (CNN) , according to various aspects of the present disclosure; and
[0026] FIG. 13 is a block diagram illustrating an example computing-device architecture of an example computing device which can implement the various techniques described herein.DETAILED DESCRIPTION
[0027] Certain aspects of this disclosure are provided below. Some of these aspects may be applied independently and some of them may be applied in combination as would be apparent to those of skill in the art. In the following description, for the purposes of explanation, specific details are set forth in order to provide a thorough understanding of aspects of the application. However, it will be apparent that various aspects may be practiced without these specific details. The figures and description are not intended to be restrictive.
[0028] The ensuing description provides example aspects only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary aspects will provide those skilled in the art with an enabling description for implementing an exemplary aspect. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the application as set forth in the appended claims.
[0029] The terms “exemplary” and / or “example” are used herein to mean “serving as an example, instance, or illustration. ” Any aspect described herein as “exemplary” and / or “example” is not necessarily to be construed as preferred or advantageous over other aspects. Likewise, the term “aspects of the disclosure” does not require that all aspects of the disclosure include the discussed feature, advantage, or mode of operation.
[0030] A handheld controller can be used as a human-machine-interface (HMI) device. In some aspects, a handheld controller can be tracked such that a user can interface with a computing system by moving and / or rotating the handheld controller. For example, a system (e.g., a computing system such as a gaming system) may receive inputs (e.g., images, audio signals, and / or inertial data) that may indicate how the user moves and / or rotates the handheld controller. The system may track the controller based on the inputs. Additionally, the controller may include one or more buttons that the user may press or activate. The controller may transmit indications of the buttons being pressed or activated to the system.
[0031] One example of a system that may be interacted with by a handheld controller is an extended reality (XR) system including an XR device (e.g., a virtual reality (VR) device, an augmented reality (AR) device, or a mixed reality (MR) device) . Some XR devices may be, or may include, head-mounted displays (HMD) (e.g., in the form of a headset, glasses, etc. ) that can be worn by the user. The XR device may include one or more cameras that may capture images of a handheld controller. The user may move and / or rotate the handheld controller. The XR device may include a tracking system that can, using the images from the cameras, track the handheld controller and interpret inputs based on how the user moves and / or rotates the handheld controller. Another example of a system that may be interacted with by a handheld controller is a gaming system that can receive images from one or more cameras in an environment in which the handheld controller is used.
[0032] Hand-held controllers may provide inputs based on fast movements with high precision, high robustness, and low latency. Such characteristics may be important for games (including XR games) .
[0033] There are different techniques for tracking handheld controllers. Such techniques include computer-vision-based controller-tracking techniques and ultrasonic controller-tracking techniques. Computer-vision-based controller-tracking techniques provide high-precision tracking with high robustness. Ultrasonic controller-tracking techniques can overcome some disadvantages of computer-vision-based controller-tracking techniques.
[0034] Computer-vision-based controller-tracking techniques may track controllers based on images of the controllers. For example, object-detection and / or object-tracking algorithms can be used to identify a controller and track the controller over time. For example, an image including a controller can be obtained and an object detector can detect the controller in the image. Further, a bounding box can be generated to identify a position of the controller in the image. Various types of systems can be used for object detection, including neural network-based object detectors. The position of the controller in images can be tracked through a series of images. In some cases, tracking the object can include determining a pose of the object relative to a camera which captured the image of the object and / or relative to prior positions of the object. In the present disclosure, the term “pose” may refer to a position and orientation. Poses may be determined according to six degrees of freedom including three translational degrees of freedom (e.g., x, y, and z dimensions) and three rotational degrees of freedom (e.g., roll, pitch, and yaw) .
[0035] According to an ultrasonic controller-tracking technique an ultrasonic controller may output one or more audio signals from one or more transducers. A system may receive the audio signals at two or more microphones and use a time-difference-of-arrival (TDOA) technique to determine a position of the controller based on differences between when the one or more audio signals arrive at the one or more microphones. In the present disclosure, the term “ultrasonic” may refer to sound that is outside the normal hearing range of a person. For example, ultrasonic may refer to sound with a frequency greater than 20 Kilohertz (kHz) . Although the present disclosure refers to ultrasonic controller-tracking techniques, the same concepts apply to techniques using audible audio signals (e.g., with a frequency less than 20 kHz) . Accordingly, the systems and techniques of the present disclosure may use ultrasonic audio signals or audible audio signals.
[0036] In some aspects, computer-vision-based controller-tracking techniques and ultrasonic controller-tracking techniques may be improved using inertial data measured by an inertial measurement unit (IMU) of a controller. For example, the controller may include an IMU that may measure inertial data as the controller moves and reorients and transmit the inertial data to a tracking system. The tracking system may use the inertial data to improve computer-vision-based controller-tracking techniques or ultrasonic controller-tracking techniques.
[0037] Systems, apparatuses, methods (also referred to as processes) , and computer-readable media (collectively referred to herein as “systems and techniques” ) are described herein for tracking a human-machine-interface (HMI) device. For example, the systems and techniques described herein may combine a computer-vision-based controller-tracking technique and an ultrasonic controller-tracking technique.
[0038] Computer-vision-based controller-tracking techniques and ultrasonic controller-tracking techniques each have their own advantages and disadvantages. The advantages and disadvantages of computer-vision-based controller-tracking techniques and ultrasonic controller-tracking techniques complement each other. To combine all their advantages and overcome the disadvantages, the systems and techniques of the present disclosure include a tightly-coupled fusion algorithm for a visual-ultrasonic controller and visual-ultrasonic tracking. The fusion algorithm improves tracking precision and robustness, including in bright environments, which may improve user experience.
[0039] Various aspects of the application will be described with respect to the figures below.
[0040] FIG. 1A is a diagram illustrating an example handheld controller 100 including a number of light sources 106 (e.g., light-emitting diodes) arranged on a tracking ring 104 protruding from a handle 102 of handheld controller 100. Handheld controller 100 includes a button 108 as an example of buttons that may be present on handle 102 of handheld controller 100.
[0041] FIG. 1B is a diagram illustrating an example handheld controller 110 including a number of light sources 116 (e.g., LEDs) arranged on a body 112 of handheld controller 110. In contrast to handheld controller 100 of FIG. 1A, light sources 116 are not arranged on a tracking ring 104 protruding from a handle 102. Rather, light sources 116 are arranged on body 112 (e.g., not radially protruding from handle 114 of body 112) . Handheld controller 110 includes a button 118 as an example of buttons that may be present on body 112 of handheld controller 110.
[0042] Computer-vision-based controller-tracking techniques may use light sources 106, as light sources 106 appear in images including handheld controller 100, to detect and track handheld controller 100. Similarly, computer-vision-based controller-tracking techniques may use light sources 116, as light sources 116 appear in images including handheld controller 110, to detect and track handheld controller 110. For example, a computer-vision-based controller-tracking technique may optimize a controller pose (e.g., a pose of handheld controller 100) with PnP (Perspective-n-Point) solver based on light sources 106 as light sources 106 appear in images of handheld controller 100.
[0043] Light sources 106 and / or light sources 116 may emit visible light (of any color) , near infrared light, and / or infrared light. Light sources 106 and light sources 116 may be arranged in a pattern to cause an orientation of handheld controller 100 or handheld controller 110 to be recognizable based on how the pattern appears in images of handheld controller 100 or handheld controller 110. According to various aspects of the present disclosure, controllers may include any number of light sources in any pattern on a ring and / or on a body of the controller.
[0044] Computer-vision-based controller-tracking techniques are highly precise and robust. However, computer-vision-based controller-tracking techniques may be sensitive to light interference (e.g., in outdoor environments) . Additionally the tracking range of computer-vision-based controller-tracking techniques is limited by the field of view (FoV) of the cameras that capture images of the controller. Further, computer-vision-based controller-tracking techniques may require multiple LEDs to be visible in images of the controller to recover from losing track of the controller, for example, based on occlusion or the controller moving out of view.
[0045] FIG. 2 is a diagram illustrating an example handheld controller 200 including a number of transducers 206 arranged on a tracking ring 204 protruding from a handle 202 of handheld controller 200. Handheld controller 200 includes a button 208 as an example of buttons that may be present on handle 202 of handheld controller 200.
[0046] According to various aspects of the present disclosure, controllers may include any number of transducers arranged anywhere on a controller or ring of a controller. Although handheld controller 200 is illustrated including tracking ring 204, other handheld controllers according to various aspects of the present disclosure may not include a tracking ring and may include transducers on a body of such controllers.
[0047] Each of transducers 206 may output an audio signal. The audio signal of each of transducers 206 may be different from the audio signals of the others of transducers 206. For example, each of the audio signals may have a different frequency (or carrier frequency) . Additionally, each of the audio signals may be modulated differently (e.g., by a different signal) . Transducers 206 may output ultrasonic audio signals (e.g., inaudible audio signals with frequencies above 20 kHz) or audible audio signals (e.g., audio signals including frequencies below 20 kHz) .
[0048] According to an ultrasonic controller-tracking technique, a system may receive the audio signals at two or more microphones and use a time-difference-of-arrival (TDOA) technique to determine a position and orientation of handheld controller 200 based on differences between when the audio signals of transducers 206 arrive at the two or more microphones. Additionally or alternatively, the timing of the audio signals of transducers 206 may be synchronized with the system (e.g., through wireless electronic signaling between the system and handheld controller 200) such that the system may be able to the determine position and orientation of handheld controller 200 based on a time of arrival (TOA) technique.
[0049] Ultrasonic controller-tracking techniques may provide high-precision pose data. Additionally, ultrasonic controller-tracking techniques may not be affected by light interference. Further, ultrasonic controller-tracking techniques are not limited by a FoV of a camera. Further still, ultrasonic controller-tracking techniques may more quickly recover tracks, for example, after occlusions.
[0050] However, ultrasonic controller-tracking techniques may be susceptible to (e.g., suffer degradations in performance based on) fast controller motion (e.g., because of the doppler effect) . Further, ultrasonic controller-tracking techniques may be susceptible to environmental noise, such as occupancy sensor which transmits ultrasound with similar frequencies. Further still, ultrasonic controller-tracking techniques may be susceptible to audio-signal reflections when controllers are close to object surfaces which may cause multipath effect. Further still, ultrasonic controller-tracking techniques may be sensitive to temperature changes since speed of sound varies with temperature.
[0051] Table 1 includes advantages and disadvantages of computer-vision-based controller-tracking techniques and ultrasonic controller-tracking techniques. Table 1
[0052] To achieve the advantages computer-vision-based controller-tracking techniques and the advantages of ultrasonic controller-tracking techniques, and to and overcome the disadvantages of computer-vision-based controller-tracking techniques and the disadvantages of ultrasonic controller-tracking techniques, the systems and techniques include a visual-ultrasonic controller that uses both light sources (e.g., IR LEDs) and transducers. Additionally, to track such a visual-ultrasonic controller, the systems and techniques include a tightly-coupled visual-ultrasonic fusion algorithm.
[0053] FIG. 3 is a diagram illustrating an example handheld controller 300 including a number of transducers 306 and a number of light sources 310 arranged on a tracking ring 304 protruding from a handle 302 of handheld controller 300. Handheld controller 300 includes a button 208 as an example of buttons that may be present on handle 302 of handheld controller 300.
[0054] According to various aspects of the present disclosure, controllers may include any number of transducers and light sources arranged anywhere on a controller or ring of a controller. Although handheld controller 300 is illustrated including tracking ring 304, other handheld controllers according to various aspects of the present disclosure may not include a tracking ring and may include transducers and light sources on a body of such controllers.
[0055] Compared to the computer-vision-based controller-tracking techniques, the visual-ultrasonic fusion algorithm (e.g., for tracking a visual-ultrasonic controller) has following improvements: higher precision and robustness (especially in very bright environments like outdoors) , wider tracking FoV, and more quick recovery after the controller is occluded or goes out of view.
[0056] The visual-ultrasonic fusion algorithm fuse image-based data and audio-based data. For example, the visual-ultrasonic fusion algorithm may fuse positions of LEDs in images of the visual-ultrasonic controller and delays measured by microphones that capture audio signals output by transducers of the visual-ultrasonic controller to track the visual-ultrasonic controller. Additionally, in some aspects, the visual-ultrasonic fusion algorithm may fuse motion-based data with the image-based data and the audio-based data to track the visual-ultrasonic controller.
[0057] Additionally or alternatively, the systems and techniques may perform ultrasonic-inertial-aided LED tracking and relocalization to improve the LED tracking and relocalization robustness, especially when very few LEDs can be seen. For example, the systems and techniques may use audio-based data and / or motion-based data to improve the implementation of computer-vision-based controller-tracking techniques.
[0058] Additionally or alternatively, the systems and techniques may perform visual-inertial-aided ultrasonic signal tracking to improve the ultrasonic signal processing robustness against fast motion, multipath effect and so on. For example, the systems and techniques may use image-based data and / or motion-based data to improve the implementation of ultrasonic controller-tracking techniques.
[0059] FIG. 4A is a diagram illustrating an example system 400 including a tracking system 422 for tracking a handheld controller 402, according to various aspects of the present disclosure. FIG. 4B is a block diagram illustrating example elements of handheld controller 402 and tracking system 422 of system 400, according to various aspects of the present disclosure.
[0060] Handheld controller 402 includes light sources 406 (e.g., LEDs, such as IR LEDs) and transducers 408 on body 404 of handheld controller 402. Handheld controller 402 is an example of a ringless controller. Handheld controller 402 may include any number of light sources 406 arranged in any positions on body 404 and any number of transducers 408 arranged in any positions on body 404.
[0061] Light sources 406 may emit visible light (of any color) , near infrared light, and / or infrared light. In some aspects, light sources (406) may include groups of LEDs (e.g., each group including a red LED, a green LED, a blue LED, and / or IR LEDs configured to emit different IR wavelengths, such that each group of LEDs may vary wavelengths of light emitted) . Light sources 406 may be included on handheld controller 402 to enable tracking system 422 to track handheld controller 402.
[0062] Transducers 408 may output audio signals 438, which may be audible or ultrasonic. Audio signals 438 may be tones or may encode information (e.g., modulated tones) . Transducers 408 may output audio signals 438 to enable tracking system 422 to track handheld controller 402.
[0063] Handheld controller 402 includes an IMU 412, which may be, or may include, one or more accelerometers, one or more gyroscopes, and / or one or more magnetometers. IMU 412 may measure movement (including translation and orientation) of handheld controller 402 and generate inertial data based on the measured movements.
[0064] Additionally, handheld controller 402 includes at least one processor (e.g., processor (s) 416) and a communication unit 410. Processor (s) 416 may control light sources 406, for example, to turn various ones of light sources 406 on or off and / or to control a frequency of light emitted by light sources 406. Additionally, processor (s) 416 may control transducers 408, for example, processor (s) 416 may provide an electrical signal that transducers 408 may convert into audio signals 438.
[0065] In some aspects, processor (s) 416 may generate motion-based data (e.g., IMU preintegration) based on inertial data from IMU 412. In some aspects, processor (s) 416 may cause communication unit 410 to transmit motion-based data to tracking system 422. Additionally or alternatively, communication unit 410 of handheld controller 402 and communication unit 430 of tracking system 422 may exchange status and / or control messages.
[0066] Alternatively, processor (s) 416 may cause communication unit 410 to transmit inertial data from IMU 412 to tracking system 422. Processor (s) 432 of tracking system 422 may determine motion-based data (e.g., IMU preintegration) based on the inertial data received from handheld controller 402.
[0067] In some cases, the tracking system 422 can be part of, included in, or include an XR device (e.g., an HMD) . In such cases, tracking system 422 may have camera (s) 426 and / or microphone (s) 428 directly connected to or included in the XR device. In other cases, tracking system 422 may be, or may include, a gaming system with one or more camera (s) 426 and microphone (s) 428 communicatively coupled thereto. For example, camera (s) 426 and microphone (s) 428 may be positioned within an environment (e.g., room) in which handheld controller 402 is to be used. Camera (s) 426 and / or microphone (s) 428 may be communicatively connected (e.g., through a wired or wireless connection) to a computing system of tracking system 422.
[0068] Tracking system 422 includes one or more camera (s) 426 which may capture images 436 including handheld controller 402 (including of light sources 406 of handheld controller 402 and images of hands and / or arms of a user of handheld controller 402) . Images 436 may represent an environment of handheld controller 402 generally. Images 436 may include handheld controller 402 (e.g., when handheld controller 402 is in a FoV of camera (s) 426. In some aspects, camera (s) 426 may be positioned to images 436 of handheld controller 402 from different perspectives (e.g., to reduce occlusions and / or to improve the ability of tracking system 422 to track handheld controller 402 through computational geometry techniques) . In the present disclosure, an image of a scene that includes a controller may be described as an image “including the controller” or an image “of the controller. ” For example, camera (s) 426 of tracking system 422 may capture images 436 of an environment (e.g., room) of tracking system 422. Handheld controller 402 may be in the environment. Images 436 may represent at least a portion of the environment. Images 436 may represent handheld controller 402 in the environment. As such, images 436 may be images “of handheld controller 402” or images “including handheld controller 402. ”
[0069] Tracking system 422 may include one or more microphone (s) 428 which may capture audio signals 438 output by transducers 408. Microphone (s) 428 may include two or more microphones positioned known distances apart such that an audio signal from one of microphone (s) 428 may arrive at the two or more microphones at different times.
[0070] Tracking system 422 includes at least one processor (e.g., processor (s) 432) . Tracking system 422, using the processor (s) 432, may track handheld controller 402 based on the images of light sources 406 captured by camera (s) 426 and audio signals 438 captured by microphone (s) 428. Tracking system 422 may further include a communication unit 430, with which tracking system 422 may communicate with handheld controller 402 (via a communication unit 410 of handheld controller 402) . For example, handheld controller 402 may communicate status message and / or motion-based data (e.g., based on measurements from IMU 412) to tracking system 422. In some aspects, tracking system 422 may use the motion-based data in tracking handheld controller 402. Tracking system 422 may communicate control messages (e.g., instructing handheld controller 402 to illuminate light sources 406 or to output audio signals 438 at transducers 408) .
[0071] FIG. 5 is a block diagram illustrating an example system 500 for tracking a handheld controller, according to various aspects of the present disclosure. One or more elements and / or operations described with regard to system 500 may be included in and / or performed by tracking system 422 of FIG. 4A and FIG. 4B.
[0072] System 500 is illustrated and described with regard to three separate pipelines, for example, a computer-vision pipeline 502, an audio pipeline 522, and an IMU pipeline 542. In some aspects, computer-vision pipeline 502 may operate independently to produce image-based data 510, audio pipeline 522 may operate independently to produce audio-based data 530, and IMU pipeline 542 may operate independently to produce motion-based data 550. For example, computer-vision pipeline 502 may perform operations of a computer-vision-based controller-tracking technique to determine image-based data 510. Audio pipeline 522 may perform operations of ultrasonic controller-tracking technique to determine audio-based data 530. IMU pipeline 542 may perform operations of an inertial-navigation to determine motion-based data 550.
[0073] In other aspects, computer-vision pipeline 502 may perform ultrasonic-inertial-aided LED tracking to determine image-based data 510. For example, computer-vision pipeline 502 may use predicted pose 532 (determined by audio pipeline 522) and / or predicted pose 552 (determined by IMU pipeline 542) in determining image-based data 510. Similarly, audio pipeline 522 may perform visual-inertial-aided ultrasonic signal tracking to determine audio-based data 530. For example, audio pipeline 522 may use predicted pose 512 (determined by computer-vision pipeline 502) and / or predicted pose 552 (determined by IMU pipeline 542) in determining audio-based data 530.
[0074] Fusor 562 may fuse image-based data 510 and audio-based data 530 to determine controller pose 566. In some aspects, fusor 562 may fuse image-based data 510, audio-based data 530, and motion-based data 550 to determine controller pose 566.
[0075] Turning to a description of computer-vision pipeline 502, system 500 may obtain images 504. Images 504 may be images including a controller (e.g., handheld controller 402) . Images 504 may be the same as, or may be substantially similar to, images 436 of FIG. 4B. Images 504 may include images from multiple (e.g., 2 to 4) cameras. In some aspects, the cameras may be part of, or on, an HMD. Additionally or alternatively, the cameras may be positioned in an environment of the controller.
[0076] Point extractor 506 may extract features from (e.g., identify visually distinct points of) images 504. In some aspects, point extractor 506 may identify positions, in images 504, of light sources (e.g., light sources 406) the controller in images 504. As an example, point extractor 506 may extract blobs (e.g., LED blobs) using computer-vision methods and / or deep-learning techniques. LEDs in the image are usually round or oval bright blobs.
[0077] Point tracker 508 may track points across a series of images (e.g., several instances of images 504) . For example, point tracker 508 may determine a correlation between a point identified in a first image and the point as identified in a second image. The point may be at a different position in the second image than in the first image. Further, in some aspects, point tracker 508 may correlate points in images 504 with points of the controller. As an example, point tracker 508 may match the blobs (e.g., as identified by point extractor 506) with LED patterns of the controller to determine matched LEDs information.
[0078] Point tracker 508 may generate image-based data 510. Image-based data 510 may be, or may include, positions of points in corresponding images and correlations between the points and points (e.g., LEDs) of the controller.
[0079] In some aspects, point tracker 508 may generate image-based data 510 using predicted pose 532 and / or predicted pose 552. For example, point tracker 508 may limit a search space within images 504 for matching points based on predicted pose 532 and / or predicted pose 552.
[0080] It may be difficult to track and / or relocalize a controller when relatively few LED blobs can be seen in images 504. Point tracker 508 may use predicted pose 552 to predict current controller pose, but the error of predicted pose 552 accumulates with time. Point tracker 508 may aid the LED tracking and relocalization with predicted pose 532. By aiding point tracker 508 with predicted pose 532, tracking robustness when tracking a controller based on images including relatively few LEDs can be significantly improved.
[0081] Additionally or alternatively, in some aspects, point tracker 508 may determine predicted pose 512 and / or predicted velocity 514. Predicted pose 512 may be, or may include, a pose of the controller as predicted by point tracker 508 based on images 504. Predicted velocity 514 may be, or may include, a velocity of the controller as precited by point tracker 508 based on images 504.
[0082] Turning to a description of audio pipeline 522, system 500 may obtain audio data 524. Audio data 524 may be audio signals captured by one or more microphones (e.g., microphone (s) 428) . Audio data 524 may include an audio signal as output by a transducer of the controller as captured by the one or more microphones. Audio data 524 may be the same as, or may be substantially similar to, audio signals 438 of FIG. 4B. In some aspects, the microphones may be part of, or on, an HMD. Additionally or alternatively, the microphones may be positioned in an environment of the controller.
[0083] Signal processor 526 may process audio data 524. For example, signal processor 526 may perform a Fourier transform (e.g., a fast Fourier transform (FFT) ) to convert audio data 524 from time domain to frequency domain. Further, signal processor 526 may isolate audio signals output by transducers of a controller, for example, by filtering audio data 524.
[0084] In some aspects, signal processor 526 may generate doppler-shift information and / or velocity information based on audio data 524. In some aspects, signal processor 526 may use predicted velocity 514 and / or predicted velocity 554 as a prior in generating such information.
[0085] Range / velocity predictor 528 may determine a range (e.g., a distance between the controller and the one or more microphones) and / or a velocity of the controller. For example, range / velocity predictor 528 may correlate audio data 524 with an ultrasonic template of each transducer to estimated delays and doppler shifts and determine the ranges and velocities based on the delays and doppler shifts.
[0086] Range / velocity predictor 528 may generate audio-based data 530. Audio-based data 530 may be, or may include, ranges between transducers of the controller and microphones, delays between when audio signals are output by the transducers and when the audio signals are recorded by the microphones, delays between when a first microphone of the one or more microphones records the audio signal and when the others of the one or more microphones record the audio signal, and / or doppler-shift information.
[0087] In some aspects, range / velocity predictor 528 may generate audio-based data 530 using predicted pose 512 and / or predicted pose 552. For example, range / velocity predictor 528 may use predicted pose 512 and / or predicted pose 552 as a prior in determining audio-based data 530.
[0088] As mentioned above, the ultrasonic signal tracking may be susceptible to environmental noise, doppler effect and multipath effect. Audio pipeline 522 may use predicted pose 512, predicted pose 552, predicted velocity 514, and / or predicted velocity 554 as priors. Because audio pipeline 522 uses predicted pose 512, predicted pose 552, predicted velocity 514, and / or predicted velocity 554 as priors, the ultrasonic signal tracking of audio pipeline 522 may be more reliable than if audio pipeline 522 did not use predicted pose 512, predicted pose 552, predicted velocity 514, and / or predicted velocity 554 as priors.
[0089] Additionally or alternatively, in some aspects, range / velocity predictor 528 may determine predicted pose 532. Predicted pose 532 may be, or may include, a controller pose of the controller as predicted by range / velocity predictor 528 based on audio data 524.
[0090] Turning to a description of IMU pipeline 542, system 500 may obtain IMU data 544. IMU data 544 may be, or may include, measurements of one or more IMUs (e.g., IMU 412) of the controller. System 500 may receive a message (e.g., messages 440) transmitted by the controller including IMU data 544.
[0091] Predictor 548 may predict a predicted pose 552 of the controller based on IMU data 544. For example, predictor 548 may implement an inertial-navigation technique to predict predicted pose 552. Additionally, predictor 548 may generate motion-based data 550. Motion-based data 550 may be, or may include, inertial preintegration data.
[0092] System 500 may obtain camera and microphone poses 564. Camera and microphone poses 564 may be, or may include, controller pose information indicative of positions of the cameras that capture images 504 and positions of the microphones that capture audio data 524. In some cases, camera and microphone poses 564 may be, or may include, a controller pose of an HMD including the cameras and microphones.
[0093] Camera and microphone poses 564 may be denoted R represents a rotation matrix, and p represents a position vector. C represents a camera (and / or microphone) coordinate system and w represents a reference coordinate system.
[0094] System 500 may receive images 504, audio data 524, IMU data 544, and camera and microphone poses 564 as inputs. The timestamps of images 504, audio data 524, IMU data 544, and / or camera and microphone poses 564 may be software or hardware synchronized.
[0095] Fusor 562 may fuse image-based data 510, audio-based data 530, motion-based data 550, and camera and microphone poses 564 to generate controller pose 566. Controller pose 566 may be, or may include, a controller pose (e.g., including a position and orientation) of the controller.
[0096] Controller pose 566 may be denoted I represents a coordinate system of the controller.
[0097] For example, after tracking LEDs (e.g., in computer-vision pipeline 502) and processing ultrasonic signals (e.g., in audio pipeline 522) , the LED tracking measurements (e.g., image-based data 510) , ultrasonic measurements (e.g., audio-based data 530) , IMU preintegration (e.g., motion-based data 550) and camera controller poses (e.g., camera and microphone poses 564) may be passed to the tightly-coupled fusion module (e.g., fusor 562) . Fusor 562 may generate the controller pose 566 at the current image timestamp.
[0098] FIG. 6 is a hybrid block-diagram-flow-diagram illustrating an example implementation of computer-vision pipeline 502 of system 500 of FIG. 5, according to various aspects of the present disclosure. Point extractor 506 may extract points (e.g., LED blobs) of images 504 using computer vision methods or deep learning.
[0099] At decision block 602, point tracker 508 may check the LED tracking state. For example, at decision block 602, point tracker 508 may determine whether point tracker 508 is tracking (e.g., has image positions for the points and / or controller) .
[0100] It may be difficult to track and / or relocalize a controller when relatively few LED blobs can be seen in images 504. Point tracker 508 may use predicted pose 552 to predict current controller pose, but the error of predicted pose 552 accumulates with time. Point tracker 508 may aid the LED tracking and relocalization with predicted pose 532. By aiding point tracker 508 with predicted pose 532, tracking robustness when tracking a controller based on images including relatively few LEDs can be significantly improved.
[0101] If point tracker 508 is not in the tracking mode (e.g., as determined at decision block 602) , that is to say not initialized or in the lost mode, relocalizer 604 may perform a global search, perform initialization when not initialized, and / or perform relocalization operations when in the lost mode to recovery the controller pose.
[0102] In some aspects, relocalizer 604 may use predicted pose 532 and / or predicted pose 552 to track the LEDs. When relocalizer 604 use predicted pose 532 and / or predicted pose 552, relocalizer 604 may search and match LED patterns within a small area of images 504 based on predicted LED positions of predicted pose 532 and / or predicted pose 552. In other words, relocalizer 604 may limit a search space for matching LEDs based on predicted pose 532 and / or predicted pose 552. Searching based on predicted pose 532 and / or predicted pose 552 may significantly improve the robustness and probability of successful relocalization. After initialization or relocalization, fusor 562 may be initialized or reset.
[0103] If point tracker 508 is in the LED tracking mode (e.g., as determined at decision block 602) , that is to say the previous controller pose is known, tracker 606 may predict the current controller pose based on previous controller pose (e.g., controller pose 566) (and / or based on predicted pose 552) , and then predict the positions of LEDs in the current images. As a result, tracker 606 may search and match corresponding LED blobs near the predicted positions in the current images. Additionally, tracker 606 may use predicted pose 532 in substantially the same way that relocalizer 604 uses predicted pose 532 (e.g., to limit a search space for matching) . Using predicted pose 532 may improve robustness of operations of tracker 606.
[0104] FIG. 7 is a block diagram illustrating an example implementation of audio pipeline 522 of system 500 of FIG. 5, according to various aspects of the present disclosure. FFT 702 may perform a fast Fourier transform (FFT) on audio data 524 to transform audio data 524 from the time domain into the frequency domain. Audio data 704 represents audio data 524 in the frequency-domain.
[0105] Doppler estimator 706 may estimate a doppler shift of audio data 524. Doppler estimator 706 may use predicted velocity 514 and / or predicted velocity 554 as priors, to compensate the doppler shift of audio data 524. Compensating for the doppler shift can significantly improve the tracking robustness against fast motion. Audio data 708 represents audio data 704 after doppler compensation.
[0106] Interference canceller 710 may detect and remove some interference from the environment. For example, interference canceller 710 may filter audio data 708 to generate audio data 712, which represents audio data 708 filtered.
[0107] Correlator 714 may correlate audio data 712 with a template 716 of each transducer to find peaks. For example, after performing the correlation in the frequency domain between audio data 712 and template 716, correlator 714 with have a curve with some peaks. If the signal (e.g., of audio data 712) is clean (e.g., not noisy) , the location of the highest peak represents the delay when transformed back to time domain. Due to the multipath effect and / or noise interference, sometimes there will be multiple peaks. In some aspects, correlator 714 may use predicted pose 512 and / or predicted pose 552 as priors. Correlator 714 can find the peaks near the predicted locations, which can significantly reduce the multipath effect and influence by environmental noises.
[0108] Delay estimator 718 may estimate the transmission delays, for example, the delays between when the audio signal was output by transducers of the controller and when audio data 524 was captured by microphones. In some aspects, the delays may be, or may include, delays between when an audio signal was output and when the audio signal was captured (e.g., based on a synchronization between the controller and the tracking system) . In some aspects, the delays may be, or may include, delays between when a first audio signal (output by a first transducer) was captured at a first microphone and when the first audio signal was captured by a second microphone.
[0109] FIG. 8 is a hybrid block-diagram-flow-diagram illustrating an example implementation of fusor 562 of system 500 of FIG. 5, according to various aspects of the present disclosure. Fusor 562 may implement a visual-ultrasonic-inertial tightly-coupled fusion algorithm.
[0110] According to the degree of information fusion, fusion techniques can be divided into loosely-coupled techniques and tightly-coupled techniques. Loosely-coupled techniques fuse estimated poses from visual / ultrasonic information and IMU information. Pose solved from LED or ultrasonic information are used as measurements. In general, to solve the pose of controller, at least three LED / ultrasonic points are needed. If fewer than three points are available, the controller pose cannot be solved based on visual / ultrasonic information. Loosely-coupled methods cannot fuse visual information when fewer than 3 LED / ultrasonic points are available.
[0111] Tightly-coupled techniques, according to various aspects of the present disclosure, directly uses the successfully matched LED blobs on the image, or the ultrasonic ranges / doppler shifts, as the observation measurements. Thus, the degree of information coupling is tighter. In contrast to loosely-coupled techniques, tightly-coupled techniques can also fuse visual / ultrasonic information with fewer than three LED / ultrasonic points. For example, Tightly-coupled techniques may fuse one point in cases in which only one point is available. Therefore, tightly-coupled techniques allows for fusion when fewer LED / ultrasonic points are available. Additionally, the tracking robustness of tightly-coupled techniques is higher than the tracking robustness of loosely-coupled techniques, especially in the case of occlusion or near the boundary of FOV.
[0112] In general, fusor 562 may operate by, at decision block 802 fusor 562 may determine if a filter (e.g., an extended Kalman filter (EKF) ) is not initialized. If the filter is not initialized, initializer 812 may initialize filter states and a covariance matrix. Once the filter is initialized, state propagator 804 may propagate a system state vector and the covariance matrix based on motion-based data 550 (e.g., based on IMU preintegration of motion-based data 550) . Model builder 806 may build an EKF measurement model based on image-based data 510 and motion-based data 550. Model builder 808 may build an EKF measurement model based on audio-based data 530 and motion-based data 550. Filter updater 810 may update the EKF filter, correcting the states, and finally outputting the pose of the controller.
[0113] Before describing each module of fusion algorithm in detail, some coordination system and mathematical symbol definitions are introduced. Coordinate definitions: W represents the world coordinate system (e.g., a reference coordinate system) . C represents the camera coordinate system. I represents the controller coordinate system.
[0114] Symbol definitions: represents the rotation matrix from coordinate system A to coordinate system B. represents the position of A coordinate system in B coordinate system.
[0115] Error definitions: Where x is the ground truth, is the estimated value of x, and δx is the error of x. Where is the measurement of x, nx is the measurement noise.
[0116] Next, each module of fusion algorithm is described in detail, starting with the system state. At each time step k, the fusion system (e.g., fusor 562) maintains the following error state vector: Where is the error state vector of rotation from IMU coordinate system {Ik} to World coordinate system {W} ; is the error state of the position of {Ik} in {W} ; δvk is velocity error at time step k; and and are the bias errors of the gyroscope and accelerometer respectively.
[0117] State propagator 804 may propagate a sate according to an IMU preintegration recursion formula: Where ΔRk, k-1, Δvk, k-1, Δpk, k-1 are IMU preintegration results; ΔRk, k-1 is the rotation increment from k-1 time step to k time step; Δvk, k-1 is the velocity increment from k-1 time step to k time step; and Δpk, k-1 is the position increment from k-1 time step to k time step.
[0118] The propagation step of the system state vector xk can be expressed as: Where nk= [σg σa σbg σba] T is the system noise; the Covariance matrix of nk, Qk, depends on the IMU noise characteristics and is calculated during sensor calibration; G is the noise covariance Jacobian matrix; and F is the system state transition matrix, which can be expressed as: Where is the Jacobian matrix of rotation increment to gyro bias; is the Jacobian matrix of velocity increment to gyro bias; is the Jacobian matrix of velocity increment to accelerometer bias; is the Jacobian matrix of position increment to gyro bias; and is the Jacobian matrix of position increment to accelerometer bias.
[0119] The general linearized form of EKF measurement model is: rk=Hxk+noise Where rk is the measurement residuals; H is the measurement Jacobian matrix; and the noise term is zero-mean, Gaussian, and uncorrelated to the error state xk.
[0120] For the visual-ultrasonic-inertial fusion (e.g., of fusor 562) , the measurements include LED measurements (e.g., or image-based data 510) and ultrasonic measurements (e.g., of audio-based data 530) .
[0121] Model builder 806 may build a measurement model for points (e.g., LEDs) capture in images 504. For example, for a j-th LED measurement the residual may be: Where is the j-th LED blob measurement; is the estimated j-th LED blob measurement; and is the j-th LED blob measurement Jacobian matrix of controller pose state xk at time step k.
[0122] Model builder 808 may build a measurement model for residuals between each microphone and each transducer. For example, the ultrasonic measurement residual between each microphone and transducer includes range measurements and velocity measurements. The j-th range measurement residual: Where ρj represents a range measurement between microphone and transducer j; lj represents a line of sight from transducer uj to microphone (e.g., as illustrated by FIG. 9); represents a position of microphone in world; represents a position of transducer uj in world; represent a controller pose in world, to be estimated; represents a position of transducer uj relative to controller; nρ represents a range measurement noise; represents the range measurement Jacobian matrix of controller pose state xk at time step k.
[0123] According to doppler effect:
[0124] Velocity measurements can be determined according to:
[0125] So the j-th velocity measurement residual is: Where f represents a transmit carrier frequency from uj; fj represents a received carrier frequency by microphone from transducer uj; c represents the speed of audio signal in the air; represents a microphone velocity component along lj; represents a transducer uj velocity component along lj; vm represents a microphone velocity in world; vuj represents a transducer uj velocity in world; represents a controller velocity in world, to be estimated; ωI represents gyroscope data from Controller IMU; nv represents range measurement noise; and represents the range measurement Jacobian matrix of controller pose state xk at time step k.
[0126] Fusor 562 may stack all the LED measurements (e.g., of image-based data 510) and ultrasonic measurement residuals (e.g., of audio-based data 530) together, to obtain:
[0127] At this stage, all the states are propagated, and all the measurements are ready. Next image-based data 510 may perform EKF update. The Kalman gain may be: Where Rk is the measurement noise covariance matrix.
[0128] The estimated error state is:
[0129] Finally, the state covariance matrix is updated according to:
[0130] After the EKF is updated, the estimated error state is determined. The error is used to correct states. To correct the pose:
[0131] To correct the extra states:
[0132] Returning to FIG. 8, the inputs of fusor 562 include a prior error state estimate a prior covariance matrix IMU preintegration increments ΔRk, k-1, Δvk, k-1, Δpk, k-1, camera pose: (e.g., of camera and microphone poses 564) , microphone position and velocity: vm (e.g., of camera and microphone poses 564) , point measurements (e.g., LED measurements) : (e.g., of image-based data 510) , and ultrasonic range and velocity measurements: (e.g., of audio-based data 530) .
[0133] In general, fusor 562 may propagate states, build an image-based measurement model (e.g., an LED measurement model) , build an audio-based measurement model, perform an EKF update, and correct states.
[0134] FIG. 9 is a diagram illustrating a system 900 including microphones 906 of a tracking system for tracking a controller 904 including transducers 908, according to various aspects of the present disclosure. In some aspects, the tracking system may be, or may include, an HMD with microphones 906 positioned thereon. Additionally or alternatively, the tracking system may include microphones 906 positioned within an environment of controller 904.
[0135] FIG. 10 is a flow diagram illustrating an example process 1000 for tracking a human-machine-interface device, in accordance with aspects of the present disclosure. One or more operations of process 1000 may be performed by a computing device (or apparatus) or a component (e.g., a chipset, codec, etc. ) of the computing device. The computing device may be a mobile device (e.g., a mobile phone) , a network-connected wearable such as a watch, an extended reality (XR) device such as a virtual reality (VR) device or augmented reality (AR) device, a vehicle or component or system of a vehicle, a desktop computing device, a tablet computing device, a server computer, a robotic device, and / or any other computing device with the resource capabilities to perform the one or more operations of process 1000. The one or more operations of process 1000 may be implemented as software components that are executed and run on one or more processors.
[0136] At block 1002, a computing device (or one or more components thereof) may determine image-based data comprising a position associated with a controller in an image. For example, point extractor 506 and point tracker 508 may determine image-based data 510 based on images 504. For example, point extractor 506 may extract features related to points (e.g., LEDs) of a controller as the points appear in images 504. Point tracker 508 may track the features and generate image-based data 510 based on the tracked features.
[0137] In some aspects, the position associated with the controller in the image is determined is based on a light source on the controller. For example, point extractor 506 may extract features related to light sources (e.g., light sources 310) .
[0138] In some aspects, the image-based data comprises a plurality of positions of a respective plurality of points of the controller in the image of the controller. For example, point extractor 506 may extract features related to light sources (e.g., light sources 310) and point tracker 508 may track the features across multiple instances of images 504.
[0139] In some aspects, to determine the image-based data, the computing device (or one or more components thereof) may track the position associated with the controller across multiple images. For example, point tracker 508 may track features across multiple instances of images 504.
[0140] In some aspects, the computing device (or one or more components thereof) may limit a search space for the position associated with the controller in the image based on an estimated pose of the controller, wherein the estimated pose of the controller is estimated based on at least one of the audio-based data or inertial data measured by an inertial measurement unit (IMU) of the controller. For example, point tracker 508 may limit a search space in images 504 for which to search for features based on predicted pose 552 and / or predicted pose 532.
[0141] At block 1004, the computing device (or one or more components thereof) may determine audio-based data based on an audio signal output by the controller and captured at one or more microphones. For example, range / velocity predictor 528 may generate audio-based data 530 based on audio data 524.
[0142] In some aspects, the audio-based data may be, or may include, a plurality of delays based on a corresponding plurality of audio signals output by a corresponding plurality of speakers of the controller. The plurality of audio signals are different one from another (each audio signal of the plurality of audio signals is different from the other audio signal (s) of the plurality of audio signals) . For example, audio-based data 530 may be, or may include, a plurality of delays based on audio data 524. In some aspects, audio-based data 530 may include delays between when a plurality of microphones received an audio signal from a speaker of a controller. Additionally or alternatively, audio-based data 530 may be, or may include, delays between when a microphone receive a plurality of audio signals form a corresponding plurality of speakers of the controller.
[0143] In some aspects, the computing device (or one or more components thereof) may determine the audio-based data based on an estimated pose of the controller, wherein the estimated pose of the controller is estimated based on at least one of the image-based data or inertial data measured by an inertial measurement unit (IMU) of the controller. For example, range / velocity predictor 528 may determine audio-based data 530 based on predicted pose 552 and / or predicted pose 512.
[0144] In some aspects, the computing device (or one or more components thereof) may determine the audio-based data based on an estimated velocity of the controller, wherein the estimated velocity of the controller is estimated based on at least one of the image-based data or inertial data measured by an inertial measurement unit (IMU) of the controller. For example, range / velocity predictor 528 may determine audio-based data 530 based on predicted pose 552 and / or predicted pose 512.
[0145] At block 1006, the computing device (or one or more components thereof) may determine a pose of the controller based on the image-based data and the audio-based data. For example, fusor 562 may determine controller pose 566 based on image-based data 510 and audio-based data 530.
[0146] In some aspects, the computing device (or one or more components thereof) may determine motion-based data based on inertia measurements from an inertial measurement unit (IMU) of the controller, wherein the pose of the controller is determined further based on the motion-based data. For example, fusor 562 may determine controller pose based on image-based data 510, audio-based data 530, and motion-based data 550.
[0147] In some aspects, to determine the pose of the controller, the computing device (or one or more components thereof) may track the pose of the controller using a recursive filter algorithm. For example, fusor 562 may track the pose of the controller using a recursive filter algorithm.
[0148] In some aspects, the recursive filter algorithm may be, or may include, at least one of an extended Kalman filter (EKF) algorithm, an unscented Kalman filter (UKF) algorithm, or a particle filter algorithm. For example, fusor 562 may track the pose of the controller using an EKF, UKF, and / or a particle filter.
[0149] In some aspects, to determine the pose of the controller, the computing device (or one or more components thereof) may propagate a state vector; determine an image-based measurement model based on the image-based data; determine an audio-based measurement model based on the audio-based data; and update the state vector based on the image-based measurement model and the audio-based measurement model. For example, fusor 562 may track the pose of the controller by propagating a state vector; determining an image-based measurement model based on the image-based data; determining an audio-based measurement model based on the audio-based data; and updating the state vector based on the image-based measurement model and the audio-based measurement model.
[0150] In some aspects, the state vector is based on motion-based data based on inertia measurements from an inertial measurement unit (IMU) of the controller; the image-based measurement model is determined further based on the motion-based data; and the audio-based measurement model is determined further based on the motion-based data.
[0151] In some examples, as noted previously, the methods described herein (e.g., process 1000 of FIG. 10, and / or other methods described herein) can be performed, in whole or in part, by a computing device or apparatus. In one example, one or more of the methods can be performed by system 500 of FIG. 5, or by another system or device. In another example, one or more of the methods (e.g., process 1000, and / or other methods described herein) can be performed, in whole or in part, by the computing-device architecture 1300 shown in FIG. 13. For instance, a computing device with the computing-device architecture 1300 shown in FIG. 13 can include, or be included in, the components of the system 500 and can implement the operations of process 1000, and / or other process described herein. In some cases, the computing device or apparatus can include various components, such as one or more input devices, one or more output devices, one or more processors, one or more microprocessors, one or more microcomputers, one or more cameras, one or more sensors, and / or other component (s) that are configured to carry out the steps of processes described herein. In some examples, the computing device can include a display, a network interface configured to communicate and / or receive the data, any combination thereof, and / or other component (s) . The network interface can be configured to communicate and / or receive Internet Protocol (IP) based data or other type of data.
[0152] The components of the computing device can be implemented in circuitry. For example, the components can include and / or can be implemented using electronic circuits or other electronic hardware, which can include one or more programmable electronic circuits (e.g., microprocessors, graphics processing units (GPUs) , digital signal processors (DSPs) , central processing units (CPUs) , and / or other suitable electronic circuits) , and / or can include and / or be implemented using computer software, firmware, or any combination thereof, to perform the various operations described herein.
[0153] Process 1000, and / or other process described herein are illustrated as logical flow diagrams, the operation of which represents a sequence of operations that can be implemented in hardware, computer instructions, or a combination thereof. In the context of computer instructions, the operations represent computer-executable instructions stored on one or more computer-readable storage media that, when executed by one or more processors, perform the recited operations. Generally, computer-executable instructions include routines, programs, objects, components, data structures, and the like that perform particular functions or implement particular data types. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described operations can be combined in any order and / or in parallel to implement the processes.
[0154] Additionally, process 1000, and / or other process described herein can be performed under the control of one or more computer systems configured with executable instructions and can be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) executing collectively on one or more processors, by hardware, or combinations thereof. As noted above, the code can be stored on a computer-readable or machine-readable storage medium, for example, in the form of a computer program comprising a plurality of instructions executable by one or more processors. The computer-readable or machine-readable storage medium can be non-transitory.
[0155] As noted above, various aspects of the present disclosure can use machine-learning models or systems.
[0156] FIG. 11 is an illustrative example of a neural network 1100 (e.g., a deep-learning neural network) that can be used to implement machine-learning based feature extraction, object detection, object tracking, implicit-neural-representation generation, rendering, classification, image recognition (e.g., face recognition, object recognition, scene recognition, etc. ) , feature extraction, authentication, gaze detection, gaze prediction, and / or automation. For example, neural network 1100 may be an example of, or can implement, point extractor 506 and / or point tracker 508.
[0157] An input layer 1102 includes input data. In one illustrative example, input layer 1102 can include data representing images 504. Neural network 1100 includes multiple hidden layers, for example, hidden layers 1106a, 1106b, through 1106n. The hidden layers 1106a, 1106b, through hidden layer 1106n include “n” number of hidden layers, where “n” is an integer greater than or equal to one. The number of hidden layers can be made to include as many layers as needed for the given application. Neural network 1100 further includes an output layer 1104 that provides an output resulting from the processing performed by the hidden layers 1106a, 1106b, through 1106n. In one illustrative example, output layer 1104 can provide image-based data 510 and / or predicted pose 512.
[0158] Neural network 1100 may be, or may include, a multi-layer neural network of interconnected nodes. Each node can represent a piece of information. Information associated with the nodes is shared among the different layers and each layer retains information as information is processed. In some cases, neural network 1100 can include a feed-forward network, in which case there are no feedback connections where outputs of the network are fed back into itself. In some cases, neural network 1100 can include a recurrent neural network, which can have loops that allow information to be carried across nodes while reading in input.
[0159] Information can be exchanged between nodes through node-to-node interconnections between the various layers. Nodes of input layer 1102 can activate a set of nodes in the first hidden layer 1106a. For example, as shown, each of the input nodes of input layer 1102 is connected to each of the nodes of the first hidden layer 1106a. The nodes of first hidden layer 1106a can transform the information of each input node by applying activation functions to the input node information. The information derived from the transformation can then be passed to and can activate the nodes of the next hidden layer 1106b, which can perform their own designated functions. Example functions include convolutional, up-sampling, data transformation, and / or any other suitable functions. The output of the hidden layer 1106b can then activate nodes of the next hidden layer, and so on. The output of the last hidden layer 1106n can activate one or more nodes of the output layer 1104, at which an output is provided. In some cases, while nodes (e.g., node 1108) in neural network 1100 are shown as having multiple output lines, a node has a single output and all lines shown as being output from a node represent the same output value.
[0160] In some cases, each node or interconnection between nodes can have a weight that is a set of parameters derived from the training of neural network 1100. Once neural network 1100 is trained, it can be referred to as a trained neural network, which can be used to perform one or more operations. For example, an interconnection between nodes can represent a piece of information learned about the interconnected nodes. The interconnection can have a tunable numeric weight that can be tuned (e.g., based on a training dataset) , allowing neural network 1100 to be adaptive to inputs and able to learn as more and more data is processed.
[0161] Neural network 1100 may be pre-trained to process the features from the data in the input layer 1102 using the different hidden layers 1106a, 1106b, through 1106n in order to provide the output through the output layer 1104. In an example in which neural network 1100 is used to identify features in images, neural network 1100 can be trained using training data that includes both images and labels, as described above. For instance, training images can be input into the network, with each training image having a label indicating the features in the images (for the feature-segmentation machine-learning system) or a label indicating classes of an activity in each image. In one example using object classification for illustrative purposes, a training image can include an image of a number 2, in which case the label for the image can be [0 0 1 0 0 0 0 0 0 0] .
[0162] In some cases, neural network 1100 can adjust the weights of the nodes using a training process called backpropagation. As noted above, a backpropagation process can include a forward pass, a loss function, a backward pass, and a weight update. The forward pass, loss function, backward pass, and parameter update are performed for one training iteration. The process can be repeated for a certain number of iterations for each set of training images until neural network 1100 is trained well enough so that the weights of the layers are accurately tuned.
[0163] For the example of identifying objects in images, the forward pass can include passing a training image through neural network 1100. The weights are initially randomized before neural network 1100 is trained. As an illustrative example, an image can include an array of numbers representing the pixels of the image. Each number in the array can include a value from 0 to 255 describing the pixel intensity at that position in the array. In one example, the array can include a 28 x 28 x 3 array of numbers with 28 rows and 28 columns of pixels and 3 color components (such as red, green, and blue, or luma and two chroma components, or the like) .
[0164] As noted above, for a first training iteration for neural network 1100, the output will likely include values that do not give preference to any particular class due to the weights being randomly selected at initialization. For example, if the output is a vector with probabilities that the object includes different classes, the probability value for each of the different classes can be equal or at least very similar (e.g., for ten possible classes, each class can have a probability value of 0.1) . With the initial weights, neural network 1100 is unable to determine low-level features and thus cannot make an accurate determination of what the classification of the object might be. A loss function can be used to analyze error in the output. Any suitable loss function definition can be used, such as a cross-entropy loss. Another example of a loss function includes the mean squared error (MSE) , defined as Etotal = Σ 1 / 2 (target -output) 2. The loss can be set to be equal to the value of Etotal.
[0165] The loss (or error) will be high for the first training images since the actual values will be much different than the predicted output. The goal of training is to minimize the amount of loss so that the predicted output is the same as the training label. Neural network 1100 can perform a backward pass by determining which inputs (weights) most contributed to the loss of the network and can adjust the weights so that the loss decreases and is eventually minimized. A derivative of the loss with respect to the weights (denoted as dL / dW, where W are the weights at a particular layer) can be computed to determine the weights that contributed most to the loss of the network. After the derivative is computed, a weight update can be performed by updating all the weights of the filters. For example, the weights can be updated so that they change in the opposite direction of the gradient. The weight update can be denoted as w = wi -η dL / dW, where w denotes a weight, wi denotes the initial weight, and η denotes a learning rate. The learning rate can be set to any suitable value, with a high learning rate including larger weight updates and a lower value indicating smaller weight updates.
[0166] Neural network 1100 can include any suitable deep network. One example includes a convolutional neural network (CNN) , which includes an input layer and an output layer, with multiple hidden layers between the input and out layers. The hidden layers of a CNN include a series of convolutional, nonlinear, pooling (for downsampling) , and fully connected layers. Neural network 1100 can include any other deep network other than a CNN, such as an autoencoder, a deep belief nets (DBNs) , a Recurrent Neural Networks (RNNs) , among others.
[0167] FIG. 12 is an illustrative example of a convolutional neural network (CNN) 1200. The input layer 1202 of the CNN 1200 includes data representing an image or frame. For example, the data can include an array of numbers representing the pixels of the image, with each number in the array including a value from 0 to 255 describing the pixel intensity at that position in the array. Using the previous example from above, the array can include a 28 x 28 x 3 array of numbers with 28 rows and 28 columns of pixels and 3 color components (e.g., red, green, and blue, or luma and two chroma components, or the like) . The image can be passed through a convolutional hidden layer 1204, an optional non-linear activation layer, a pooling hidden layer 1206, and fully connected layer 1208 (which fully connected layer 1208 can be hidden) to get an output at the output layer 1210. While only one of each hidden layer is shown in FIG. 12, one of ordinary skill will appreciate that multiple convolutional hidden layers, non-linear layers, pooling hidden layers, and / or fully connected layers can be included in the CNN 1200. As previously described, the output can indicate a single class of an object or can include a probability of classes that best describe the object in the image.
[0168] The first layer of the CNN 1200 can be the convolutional hidden layer 1204. The convolutional hidden layer 1204 can analyze image data of the input layer 1202. Each node of the convolutional hidden layer 1204 is connected to a region of nodes (pixels) of the input image called a receptive field. The convolutional hidden layer 1204 can be considered as one or more filters (each filter corresponding to a different activation or feature map) , with each convolutional iteration of a filter being a node or neuron of the convolutional hidden layer 1204. For example, the region of the input image that a filter covers at each convolutional iteration would be the receptive field for the filter. In one illustrative example, if the input image includes a 28×28 array, and each filter (and corresponding receptive field) is a 5×5 array, then there will be 24×24 nodes in the convolutional hidden layer 1204. Each connection between a node and a receptive field for that node learns a weight and, in some cases, an overall bias such that each node learns to analyze its particular local receptive field in the input image. Each node of the convolutional hidden layer 1204 will have the same weights and bias (called a shared weight and a shared bias) . For example, the filter has an array of weights (numbers) and the same depth as the input. A filter will have a depth of 3 for an image frame example (according to three color components of the input image) . An illustrative example size of the filter array is 5 x 5 x 3, corresponding to a size of the receptive field of a node.
[0169] The convolutional nature of the convolutional hidden layer 1204 is due to each node of the convolutional layer being applied to its corresponding receptive field. For example, a filter of the convolutional hidden layer 1204 can begin in the top-left corner of the input image array and can convolve around the input image. As noted above, each convolutional iteration of the filter can be considered a node or neuron of the convolutional hidden layer 1204. At each convolutional iteration, the values of the filter are multiplied with a corresponding number of the original pixel values of the image (e.g., the 5x5 filter array is multiplied by a 5x5 array of input pixel values at the top-left corner of the input image array) . The multiplications from each convolutional iteration can be summed together to obtain a total sum for that iteration or node. The process is next continued at a next location in the input image according to the receptive field of a next node in the convolutional hidden layer 1204. For example, a filter can be moved by a step amount (referred to as a stride) to the next receptive field. The stride can be set to 1 or any other suitable amount. For example, if the stride is set to 1, the filter will be moved to the right by 1 pixel at each convolutional iteration. Processing the filter at each unique location of the input volume produces a number representing the filter results for that location, resulting in a total sum value being determined for each node of the convolutional hidden layer 1204.
[0170] The mapping from the input layer to the convolutional hidden layer 1204 is referred to as an activation map (or feature map) . The activation map includes a value for each node representing the filter results at each location of the input volume. The activation map can include an array that includes the various total sum values resulting from each iteration of the filter on the input volume. For example, the activation map will include a 24 x 24 array if a 5 x 5 filter is applied to each pixel (astride of 1) of a 28 x 28 input image. The convolutional hidden layer 1204 can include several activation maps in order to identify multiple features in an image. The example shown in FIG. 12 includes three activation maps. Using three activation maps, the convolutional hidden layer 1204 can detect three different kinds of features, with each feature being detectable across the entire image.
[0171] In some examples, a non-linear hidden layer can be applied after the convolutional hidden layer 1204. The non-linear layer can be used to introduce non-linearity to a system that has been computing linear operations. One illustrative example of a non-linear layer is a rectified linear unit (ReLU) layer. A ReLU layer can apply the function f (x) = max (0, x) to all of the values in the input volume, which changes all the negative activations to 0. The ReLU can thus increase the non-linear properties of the CNN 1200 without affecting the receptive fields of the convolutional hidden layer 1204.
[0172] The pooling hidden layer 1206 can be applied after the convolutional hidden layer 1204 (and after the non-linear hidden layer when used) . The pooling hidden layer 1206 is used to simplify the information in the output from the convolutional hidden layer 1204. For example, the pooling hidden layer 1206 can take each activation map output from the convolutional hidden layer 1204 and generates a condensed activation map (or feature map) using a pooling function. Max-pooling is one example of a function performed by a pooling hidden layer. Other forms of pooling functions be used by the pooling hidden layer 1206, such as average pooling, L2-norm pooling, or other suitable pooling functions. A pooling function (e.g., a max-pooling filter, an L2-norm filter, or other suitable pooling filter) is applied to each activation map included in the convolutional hidden layer 1204. In the example shown in FIG. 12, three pooling filters are used for the three activation maps in the convolutional hidden layer 1204.
[0173] In some examples, max-pooling can be used by applying a max-pooling filter (e.g., having a size of 2x2) with a stride (e.g., equal to a dimension of the filter, such as a stride of 2) to an activation map output from the convolutional hidden layer 1204. The output from a max-pooling filter includes the maximum number in every sub-region that the filter convolves around. Using a 2x2 filter as an example, each unit in the pooling layer can summarize a region of 2×2 nodes in the previous layer (with each node being a value in the activation map) . For example, four values (nodes) in an activation map will be analyzed by a 2x2 max-pooling filter at each iteration of the filter, with the maximum value from the four values being output as the “max” value. If such a max-pooling filter is applied to an activation filter from the convolutional hidden layer 1204 having a dimension of 24x24 nodes, the output from the pooling hidden layer 1206 will be an array of 12x12 nodes.
[0174] In some examples, an L2-norm pooling filter could also be used. The L2-norm pooling filter includes computing the square root of the sum of the squares of the values in the 2×2 region (or other suitable region) of an activation map (instead of computing the maximum values as is done in max-pooling) and using the computed values as an output.
[0175] The pooling function (e.g., max-pooling, L2-norm pooling, or other pooling function) determines whether a given feature is found anywhere in a region of the image and discards the exact positional information. This can be done without affecting results of the feature detection because, once a feature has been found, the exact location of the feature is not as important as its approximate location relative to other features. Max-pooling (as well as other pooling methods) offer the benefit that there are many fewer pooled features, thus reducing the number of parameters needed in later layers of the CNN 1200.
[0176] The final layer of connections in the network is a fully-connected layer that connects every node from the pooling hidden layer 1206 to every one of the output nodes in the output layer 1210. Using the example above, the input layer includes 28 x 28 nodes encoding the pixel intensities of the input image, the convolutional hidden layer 1204 includes 3×24×24 hidden feature nodes based on application of a 5×5 local receptive field (for the filters) to three activation maps, and the pooling hidden layer 1206 includes a layer of 3×12×12 hidden feature nodes based on application of max-pooling filter to 2×2 regions across each of the three feature maps. Extending this example, the output layer 1210 can include ten output nodes. In such an example, every node of the 3x12x12 pooling hidden layer 1206 is connected to every node of the output layer 1210.
[0177] The fully connected layer 1208 can obtain the output of the previous pooling hidden layer 1206 (which should represent the activation maps of high-level features) and determines the features that most correlate to a particular class. For example, the fully connected layer 1208 can determine the high-level features that most strongly correlate to a particular class and can include weights (nodes) for the high-level features. A product can be computed between the weights of the fully connected layer 1208 and the pooling hidden layer 1206 to obtain probabilities for the different classes. For example, if the CNN 1200 is being used to predict that an object in an image is a person, high values will be present in the activation maps that represent high-level features of people (e.g., two legs are present, a face is present at the top of the object, two eyes are present at the top left and top right of the face, a nose is present in the middle of the face, a mouth is present at the bottom of the face, and / or other features common for a person) .
[0178] In some examples, the output from the output layer 1210 can include an M-dimensional vector (in the prior example, M=10) . M indicates the number of classes that the CNN 1200 has to choose from when classifying the object in the image. Other example outputs can also be provided. Each number in the M-dimensional vector can represent the probability the object is of a certain class. In one illustrative example, if a 10-dimensional output vector represents ten different classes of objects is [0 0 0.05 0.8 0 0.15 0 0 0 0] , the vector indicates that there is a 5%probability that the image is the third class of object (e.g., a dog) , an 80%probability that the image is the fourth class of object (e.g., a human) , and a 15%probability that the image is the sixth class of object (e.g., a kangaroo) . The probability for a class can be considered a confidence level that the object is part of that class.
[0179] FIG. 13 illustrates an example computing-device architecture 1300 of an example computing device which can implement the various techniques described herein. In some examples, the computing device can include a mobile device, a wearable device, an extended reality device (e.g., a virtual reality (VR) device, an augmented reality (AR) device, or a mixed reality (MR) device) , a personal computer, a laptop computer, a video server, a vehicle (or computing device of a vehicle) , or other device. For example, the computing-device architecture 1300 may include, implement, or be included in any or all of ___and / or other devices, modules, or systems described herein. Additionally or alternatively, computing-device architecture 1300 may be configured to perform process 1000, and / or other process described herein.
[0180] The components of computing-device architecture 1300 are shown in electrical communication with each other using connection 1312, such as a bus. The example computing-device architecture 1300 includes a processing unit (CPU or processor) 1302 and computing device connection 1312 that couples various computing device components including computing device memory 1310, such as read only memory (ROM) 1308 and random-access memory (RAM) 1306, to processor 1302.
[0181] Computing-device architecture 1300 can include a cache of high-speed memory connected directly with, in close proximity to, or integrated as part of processor 1302. Computing-device architecture 1300 can copy data from memory 1310 and / or the storage device 1314 to cache 1304 for quick access by processor 1302. In this way, the cache can provide a performance boost that avoids processor 1302 delays while waiting for data. These and other modules can control or be configured to control processor 1302 to perform various actions. Other computing device memory 1310 may be available for use as well. Memory 1310 can include multiple different types of memory with different performance characteristics. Processor 1302 can include any general-purpose processor and a hardware or software service, such as service 1 1316, service 2 1318, and service 3 1320 stored in storage device 1314, configured to control processor 1302 as well as a special-purpose processor where software instructions are incorporated into the processor design. Processor 1302 may be a self-contained system, containing multiple cores or processors, a bus, memory controller, cache, etc. A multi-core processor may be symmetric or asymmetric.
[0182] To enable user interaction with the computing-device architecture 1300, input device 1322 can represent any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphical input, keyboard, mouse, motion input, speech and so forth. Output device 1324 can also be one or more of a number of output mechanisms known to those of skill in the art, such as a display, projector, television, speaker device, etc. In some instances, multimodal computing devices can enable a user to provide multiple types of input to communicate with computing-device architecture 1300. Communication interface 1326 can generally govern and manage the user input and computing device output. There is no restriction on operating on any particular hardware arrangement and therefore the basic features here may easily be substituted for improved hardware or firmware arrangements as they are developed.
[0183] Storage device 1314 is a non-volatile memory and can be a hard disk or other types of computer readable media which can store data that are accessible by a computer, such as magnetic cassettes, flash memory cards, solid state memory devices, digital versatile discs (DVDs) , cartridges, random-access memories (RAMs) 1306, read only memory (ROM) 1308, and hybrids thereof. Storage device 1314 can include services 1316, 1318, and 1320 for controlling processor 1302. Other hardware or software modules are contemplated. Storage device 1314 can be connected to the computing device connection 1312. In one aspect, a hardware module that performs a particular function can include the software component stored in a computer-readable medium in connection with the necessary hardware components, such as processor 1302, connection 1312, output device 1324, and so forth, to carry out the function.
[0184] The term “substantially, ” in reference to a given parameter, property, or condition, may refer to a degree that one of ordinary skill in the art would understand that the given parameter, property, or condition is met with a small degree of variance, such as, for example, within acceptable manufacturing tolerances. By way of example, depending on the particular parameter, property, or condition that is substantially met, the parameter, property, or condition may be at least 90%met, at least 95%met, or even at least 99%met.
[0185] Aspects of the present disclosure are applicable to any suitable electronic device (such as security systems, smartphones, tablets, laptop computers, vehicles, drones, or other devices) including or coupled to one or more active depth sensing systems. While described below with respect to a device having or coupled to one light projector, aspects of the present disclosure are applicable to devices having any number of light projectors and are therefore not limited to specific devices.
[0186] The term “device” is not limited to one or a specific number of physical objects (such as one smartphone, one controller, one processing system and so on) . As used herein, a device may be any electronic device with one or more parts that may implement at least some portions of this disclosure. While the below description and examples use the term “device” to describe various aspects of this disclosure, the term “device” is not limited to a specific configuration, type, or number of objects. Additionally, the term “system” is not limited to multiple components or specific aspects. For example, a system may be implemented on one or more printed circuit boards or other substrates and may have movable or static components. While the below description and examples use the term “system” to describe various aspects of this disclosure, the term “system” is not limited to a specific configuration, type, or number of objects.
[0187] Specific details are provided in the description above to provide a thorough understanding of the aspects and examples provided herein. However, it will be understood by one of ordinary skill in the art that the aspects may be practiced without these specific details. For clarity of explanation, in some instances the present technology may be presented as including individual functional blocks including functional blocks including devices, device components, steps or routines in a method embodied in software, or combinations of hardware and software. Additional components may be used other than those shown in the figures and / or described herein. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the aspects in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the aspects.
[0188] Individual aspects may be described above as a process or method which is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function.
[0189] Processes and methods according to the above-described examples can be implemented using computer-executable instructions that are stored or otherwise available from computer-readable media. Such instructions can include, for example, instructions and data which cause or otherwise configure a general-purpose computer, special purpose computer, or a processing device to perform a certain function or group of functions. Portions of computer resources used can be accessible over a network. The computer executable instructions may be, for example, binaries, intermediate format instructions such as assembly language, firmware, source code, etc.
[0190] The term “computer-readable medium” includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other mediums capable of storing, containing, or carrying instruction (s) and / or data. A computer-readable medium may include a non-transitory medium in which data can be stored and that does not include carrier waves and / or transitory electronic signals propagating wirelessly or over wired connections. Examples of a non-transitory medium may include, but are not limited to, a magnetic disk or tape, optical storage media such as compact disk (CD) or digital versatile disk (DVD) , flash memory, magnetic or optical disks, USB devices provided with non-volatile memory, networked storage devices, any suitable combination thereof, among others. A computer-readable medium may have stored thereon code and / or machine-executable instructions that may represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, or the like.
[0191] In some aspects the computer-readable storage devices, mediums, and memories can include a cable or wireless signal containing a bit stream and the like. However, when mentioned, non-transitory computer-readable storage media expressly exclude media such as energy, carrier signals, electromagnetic waves, and signals per se.
[0192] Devices implementing processes and methods according to these disclosures can include hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof, and can take any of a variety of form factors. When implemented in software, firmware, middleware, or microcode, the program code or code segments to perform the necessary tasks (e.g., a computer-program product) may be stored in a computer-readable or machine-readable medium. A processor (s) may perform the necessary tasks. Typical examples of form factors include laptops, smart phones, mobile phones, tablet devices or other small form factor personal computers, personal digital assistants, rackmount devices, standalone devices, and so on. Functionality described herein also can be embodied in peripherals or add-in cards. Such functionality can also be implemented on a circuit board among different chips or different processes executing in a single device, by way of further example.
[0193] The instructions, media for conveying such instructions, computing resources for executing them, and other structures for supporting such computing resources are example means for providing the functions described in the disclosure.
[0194] In the foregoing description, aspects of the application are described with reference to specific aspects thereof, but those skilled in the art will recognize that the application is not limited thereto. Thus, while illustrative aspects of the application have been described in detail herein, it is to be understood that the inventive concepts may be otherwise variously embodied and employed, and that the appended claims are intended to be construed to include such variations, except as limited by the prior art. Various features and aspects of the above-described application may be used individually or jointly. Further, aspects can be utilized in any number of environments and applications beyond those described herein without departing from the broader spirit and scope of the specification. The specification and drawings are, accordingly, to be regarded as illustrative rather than restrictive. For the purposes of illustration, methods were described in a particular order. It should be appreciated that in alternate aspects, the methods may be performed in a different order than that described.
[0195] One of ordinary skill will appreciate that the less than ( “< “) and greater than ( “> “) symbols or terminology used herein can be replaced with less than or equal to ( “≤” ) and greater than or equal to ( “≥” ) symbols, respectively, without departing from the scope of this description.
[0196] Where components are described as being “configured to” perform certain operations, such configuration can be accomplished, for example, by designing electronic circuits or other hardware to perform the operation, by programming programmable electronic circuits (e.g., microprocessors, or other suitable electronic circuits) to perform the operation, or any combination thereof.
[0197] The phrase “coupled to” refers to any component that is physically connected to another component either directly or indirectly, and / or any component that is in communication with another component (e.g., connected to the other component over a wired or wireless connection, and / or other suitable communication interface) either directly or indirectly.
[0198] Claim language or other language reciting “at least one of” a set and / or “one or more” of a set indicates that one member of the set or multiple members of the set (in any combination) satisfy the claim. For example, claim language reciting “at least one of A and B” or “at least one of A or B” means A, B, or A and B. In another example, claim language reciting “at least one of A, B, and C” or “at least one of A, B, or C” means A, B, C, or A and B, or A and C, or B and C, A and B and C, or any duplicate information or data (e.g., A and A, B and B, C and C, A and A and B, and so on) , or any other ordering, duplication, or combination of A, B, and C. The language “at least one of” a set and / or “one or more” of a set does not limit the set to the items listed in the set. For example, claim language reciting “at least one of A and B” or “at least one of A or B” may mean A, B, or A and B, and may additionally include items not listed in the set of A and B. The phrases “at least one” and “one or more” are used interchangeably herein.
[0199] Claim language or other language reciting “at least one processor configured to, ” “at least one processor being configured to, ” “one or more processors configured to, ” “one or more processors being configured to, ” or the like indicates that one processor or multiple processors (in any combination) can perform the associated operation (s) . For example, claim language reciting “at least one processor configured to: X, Y, and Z” means a single processor can be used to perform operations X, Y, and Z; or that multiple processors are each tasked with a certain subset of operations X, Y, and Z such that together the multiple processors perform X, Y, and Z; or that a group of multiple processors work together to perform operations X, Y, and Z. In another example, claim language reciting “at least one processor configured to: X, Y, and Z” can mean that any single processor may only perform at least a subset of operations X, Y, and Z.
[0200] Where reference is made to one or more elements performing functions (e.g., steps of a method) , one element may perform all functions, or more than one element may collectively perform the functions. When more than one element collectively performs the functions, each function need not be performed by each of those elements (e.g., different functions may be performed by different elements) and / or each function need not be performed in whole by only one element (e.g., different elements may perform different sub-functions of a function) . Similarly, where reference is made to one or more elements configured to cause another element (e.g., an apparatus) to perform functions, one element may be configured to cause the other element to perform all functions, or more than one element may collectively be configured to cause the other element to perform the functions.
[0201] Where reference is made to an entity (e.g., any entity or device described herein) performing functions or being configured to perform functions (e.g., steps of a method) , the entity may be configured to cause one or more elements (individually or collectively) to perform the functions. The one or more components of the entity may include at least one memory, at least one processor, at least one communication interface, another component configured to perform one or more (or all) of the functions, and / or any combination thereof. Where reference to the entity performing functions, the entity may be configured to cause one component to perform all functions, or to cause more than one component to collectively perform the functions. When the entity is configured to cause more than one component to collectively perform the functions, each function need not be performed by each of those components (e.g., different functions may be performed by different components) and / or each function need not be performed in whole by only one component (e.g., different components may perform different sub-functions of a function) .
[0202] The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the aspects disclosed herein may be implemented as electronic hardware, computer software, firmware, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
[0203] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices such as general-purposes computers, wireless communication device handsets, or integrated circuit devices having multiple uses including application in wireless communication device handsets and other devices. Any features described as modules or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be realized at least in part by a computer-readable data storage medium including program code including instructions that, when executed, performs one or more of the methods described above. The computer-readable data storage medium may form part of a computer program product, which may include packaging materials. The computer-readable medium may include memory or data storage media, such as random-access memory (RAM) such as synchronous dynamic random-access memory (SDRAM) , read-only memory (ROM) , non-volatile random-access memory (NVRAM) , electrically erasable programmable read-only memory (EEPROM) , flash memory, magnetic or optical data storage media, and the like. The techniques additionally, or alternatively, may be realized at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and that can be accessed, read, and / or executed by a computer, such as propagated signals or waves.
[0204] The program code may be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs) , general-purpose microprocessors, an application specific integrated circuits (ASICs) , field programmable logic arrays (FPGAs) , or other equivalent integrated or discrete logic circuitry. Such a processor may be configured to perform any of the techniques described in this disclosure. A general-purpose processor may be a microprocessor; but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Accordingly, the term “processor, ” as used herein may refer to any of the foregoing structure, any combination of the foregoing structure, or any other structure or apparatus suitable for implementation of the techniques described herein.
[0205] Illustrative aspects of the disclosure include:
[0206] Aspect 1. An apparatus for tracking a human-machine-interface device, the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and configured to: determine image-based data comprising a position associated with a controller in an image; determine audio-based data based on an audio signal output by the controller and captured at one or more microphones; and determine a pose of the controller based on the image-based data and the audio-based data.
[0207] Aspect 2. The apparatus of aspect 1, wherein, to determine the image-based data, the at least one processor is configured to track the position associated with the controller across multiple images.
[0208] Aspect 3. The apparatus of aspect 2, wherein the at least one processor is configured to limit a search space for the position associated with the controller in the image based on an estimated pose of the controller, wherein the estimated pose of the controller is estimated based on at least one of the audio-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.
[0209] Aspect 4. The apparatus of any one of aspects 1 to 3, further comprising a camera configured to capture the image.
[0210] Aspect 5. The apparatus of any one of aspects 1 to 4, wherein the position associated with the controller in the image is determined is based on a light source on the controller.
[0211] Aspect 6. The apparatus of any one of aspects 1 to 5, wherein the image-based data comprises a plurality of positions of a respective plurality of points of the controller in the image of the controller.
[0212] Aspect 7. The apparatus of any one of aspects 1 to 6, wherein the at least one processor is configured to determine the audio-based data based on an estimated pose of the controller, wherein the estimated pose of the controller is estimated based on at least one of the image-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.
[0213] Aspect 8. The apparatus of any one of aspects 1 to 7, wherein the at least one processor is configured to determine the audio-based data based on an estimated velocity of the controller, wherein the estimated velocity of the controller is estimated based on at least one of the image-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.
[0214] Aspect 9. The apparatus of any one of aspects 1 to 8, further comprising the one or more microphones.
[0215] Aspect 10. The apparatus of any one of aspects 1 to 9, wherein the audio-based data comprises a plurality of delays based on a corresponding plurality of audio signals output by a corresponding plurality of speakers of the controller, and wherein the plurality of audio signals are different one from another.
[0216] Aspect 11. The apparatus of any one of aspects 1 to 10, wherein the at least one processor is configured to determine motion-based data based on inertia measurements from an inertial measurement unit (IMU) of the controller, wherein the pose of the controller is determined further based on the motion-based data.
[0217] Aspect 12. The apparatus of any one of aspects 1 to 11, wherein, to determine the pose of the controller, the at least one processor is configured to track the pose of the controller using a recursive filter algorithm.
[0218] Aspect 13. The apparatus of aspect 12, wherein the recursive filter algorithm comprises at least one of an extended Kalman filter (EKF) algorithm, an unscented Kalman filter (UKF) algorithm, or a particle filter algorithm.
[0219] Aspect 14. The apparatus of any one of aspects 1 to 13, wherein, to determine the pose of the controller, the at least one processor is configured to: propagate a state vector; determine an image-based measurement model based on the image-based data; determine an audio-based measurement model based on the audio-based data; and update the state vector based on the image-based measurement model and the audio-based measurement model.
[0220] Aspect 15. The apparatus of aspect 14, wherein: the state vector is based on motion-based data based on inertia measurements from an inertial measurement unit (IMU) of the controller; the image-based measurement model is determined further based on the motion-based data; and the audio-based measurement model is determined further based on the motion-based data.
[0221] Aspect 16. An apparatus for human-machine interface, the apparatus comprising: a controller configured to be held in a hand of a user; a plurality of light sources positioned on the controller, wherein the plurality of light sources are configured to be illuminated to enable a tracking system to track the controller; and a plurality of transducers positioned on the controller, wherein the plurality of transducers are configured to output an audio signal to enable the tracking system to track the controller.
[0222] Aspect 17. The apparatus of aspect 16, further comprising: an inertial measurement unit (IMU) configured to measure inertial data; and a communication unit configured to transmit the inertial data to the tracking system.
[0223] Aspect 18. A system for human-machine interface, the system comprising: a camera configured to capture images of a controller; a microphone configured to capture an audio signal output by a transducer of the controller; at least one memory; and at least one processor coupled to the at least one memory and configured to determine a pose of the controller based on the images of the controller and the audio signal captured by the microphone.
[0224] Aspect 19. The system of aspect 18, further comprising a communication unit, wherein the at least one processor is configured to determine the pose of the controller further based on inertial data measured by an inertial measurement unit (IMU) of the controller and received by the communication unit.
[0225] Aspect 20. The system of any one of aspects 18 or 19, wherein the apparatus comprises a head-mounted display.
[0226] Aspect 21. A method for tracking a human-machine-interface device, the method comprising: determining image-based data comprising a position associated with a controller in an image; determining audio-based data based on an audio signal output by the controller and captured at one or more microphones; and determining a pose of the controller based on the image-based data and the audio-based data.
[0227] Aspect 22. The method of aspect 21, wherein determining the image-based data comprises tracking the position associated with the controller across multiple images.
[0228] Aspect 23. The method of aspect 22, further comprising limiting a search space for the position associated with the controller in the image based on an estimated pose of the controller, wherein the estimated pose of the controller is estimated based on at least one of the audio-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.
[0229] Aspect 24. The method of any one of aspects 21 to 23, further comprising capturing the image at a camera of a device that is configured to interpret the pose of the controller as an input.
[0230] Aspect 25. The method of any one of aspects 21 to 24, wherein the position associated with the controller is based on a light source on the controller.
[0231] Aspect 26. The method of any one of aspects 21 to 25, wherein the image-based data comprises a plurality of positions of a respective plurality of points of the controller in the image of the controller.
[0232] Aspect 27. The method of any one of aspects 21 to 26, further comprising determining the audio-based data based on an estimated pose of the controller, wherein the estimated pose of the controller is estimated based on at least one of the image-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.
[0233] Aspect 28. The method of any one of aspects 21 to 27, further comprising determining the audio-based data based on an estimated velocity of the controller, wherein the estimated velocity of the controller is estimated based on at least one of the image-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.
[0234] Aspect 29. The method of any one of aspects 21 to 28, further comprising capturing the audio signal at the one or more microphones of a device that is configured to interpret the pose of the controller as an input.
[0235] Aspect 30. The method of any one of aspects 21 to 29, wherein the audio-based data comprises a plurality of delays based on a corresponding plurality of audio signals output by a corresponding plurality of speakers of the controller, and wherein the plurality of audio signals are different one from another.
[0236] Aspect 31. The method of any one of aspects 21 to 30, further comprising: determining motion-based data based on inertia measurements from an inertial measurement unit (IMU) of the controller; wherein the pose of the controller is determined further based on the motion-based data.
[0237] Aspect 32. The method of any one of aspects 21 to 31, wherein determining the pose of the controller comprises tracking the pose of the controller using a recursive filter algorithm.
[0238] Aspect 33. The method of aspect 32, wherein the recursive filter algorithm comprises at least one of an extended Kalman filter (EKF) algorithm, an unscented Kalman filter (UKF) algorithm, or a particle filter algorithm.
[0239] Aspect 34. The method of any one of aspects 21 to 33, wherein determining the pose of the controller comprises: propagating a state vector; determining an image-based measurement model based on the image-based data; determining an audio-based measurement model based on the audio-based data; and updating the state vector based on the image-based measurement model and the audio-based measurement model.
[0240] Aspect 35. The method of aspect 34, wherein: the state vector is based on motion-based data based on inertia measurements from an inertial measurement unit (IMU) of the controller; the image-based measurement model is determined further based on the motion-based data; and the audio-based measurement model is determined further based on the motion-based data.
[0241] Aspect 36. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations according to any of aspects 21 to 35.
[0242] Aspect 37. An apparatus for providing virtual content for display, the apparatus comprising one or more means for perform operations according to any of aspects 21 to 35.
Claims
An apparatus for tracking a human-machine-interface device, the apparatus comprising:at least one memory; andat least one processor coupled to the at least one memory and configured to:determine image-based data comprising a position associated with a controller in an image;determine audio-based data based on an audio signal output by the controller and captured at one or more microphones; anddetermine a pose of the controller based on the image-based data and the audio-based data.The apparatus of claim 1, wherein, to determine the image-based data, the at least one processor is configured to track the position associated with the controller across multiple images.The apparatus of claim 2, wherein the at least one processor is configured to limit a search space for the position associated with the controller in the image based on an estimated pose of the controller, wherein the estimated pose of the controller is estimated based on at least one of the audio-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.The apparatus of claim 1, further comprising a camera configured to capture the image.The apparatus of claim 1, wherein the position associated with the controller in the image is determined is based on a light source on the controller.The apparatus of claim 1, wherein the image-based data comprises a plurality of positions of a respective plurality of points of the controller in the image of the controller.The apparatus of claim 1, wherein the at least one processor is configured to determine the audio-based data based on an estimated pose of the controller, wherein the estimated pose of the controller is estimated based on at least one of the image-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.The apparatus of claim 1, wherein the at least one processor is configured to determine the audio-based data based on an estimated velocity of the controller, wherein the estimated velocity of the controller is estimated based on at least one of the image-based data or inertial data measured by an inertial measurement unit (IMU) of the controller.The apparatus of claim 1, further comprising the one or more microphones.The apparatus of claim 1, wherein the audio-based data comprises a plurality of delays based on a corresponding plurality of audio signals output by a corresponding plurality of speakers of the controller, and wherein the corresponding plurality of audio signals is different one from another.The apparatus of claim 1, wherein the at least one processor is configured to determine motion-based data based on inertia measurements from an inertial measurement unit (IMU) of the controller, wherein the pose of the controller is determined further based on the motion-based data.The apparatus of claim 1, wherein, to determine the pose of the controller, the at least one processor is configured to track the pose of the controller using a recursive filter algorithm.The apparatus of claim 12, wherein the recursive filter algorithm comprises at least one of an extended Kalman filter (EKF) algorithm, an unscented Kalman filter (UKF) algorithm, or a particle filter algorithm.The apparatus of claim 1, wherein, to determine the pose of the controller, the at least one processor is configured to:propagate a state vector;determine an image-based measurement model based on the image-based data;determine an audio-based measurement model based on the audio-based data; andupdate the state vector based on the image-based measurement model and the audio-based measurement model.The apparatus of claim 14, wherein:the state vector is based on motion-based data based on inertia measurements from an inertial measurement unit (IMU) of the controller;the image-based measurement model is determined further based on the motion-based data; andthe audio-based measurement model is determined further based on the motion-based data.An apparatus for human-machine interface, the apparatus comprising:a controller configured to be held in a hand of a user;a plurality of light sources positioned on the controller, wherein the plurality of light sources are configured to be illuminated to enable a tracking system to track the controller; anda plurality of transducers positioned on the controller, wherein the plurality of transducers are configured to output an audio signal to enable the tracking system to track the controller.The apparatus of claim 16, further comprising:an inertial measurement unit (IMU) configured to measure inertial data; anda communication unit configured to transmit the inertial data to the tracking system.A system for human-machine interface, the system comprising:a camera configured to capture images of a controller;a microphone configured to capture an audio signal output by a transducer of the controller;at least one memory; andat least one processor coupled to the at least one memory and configured to determine a pose of the controller based on the images of the controller and the audio signal captured by the microphone.The system of claim 18, further comprising a communication unit, wherein the at least one processor is configured to determine the pose of the controller further based on inertial data measured by an inertial measurement unit (IMU) of the controller and received by the communication unit.The system of claim 18, wherein the system comprises a head-mounted display.