Texture-based gesture verification

Abstract

Aspects of the disclosure relate to systems comprising computer-readable storage media storing a program and methods for detecting a pose of a user. The program and methods comprise the operations of receiving a monocular image comprising a depiction of a body of a user in a given pose, detecting a plurality of skeletal joints of the body depicted in the monocular image, generating a contour of the body of the user based on the plurality of skeletal joints, retrieving a mask representing a target pose, comparing the contour of the body depicted in the monocular image to the mask representing the target pose, and determining that the given pose of the body of the user matches the target pose in response to comparing the contour of the body to the mask.

Description

[0001] Priority requirements

[0002] This application claims priority to U.S. Patent Application Serial No. 15 / 929,333, filed April 27, 2020, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure generally relates to detecting a user's pose based on an image depicting the user. Background Technology

[0004] Image processing systems can be used to react to different actions performed by a user and captured by a camera. Such systems can modify the presentation of virtual objects or perform other application-specific functions. Presentation problems can arise due to environmental conditions, user actions, unexpected visual interruptions between the camera and the object being displayed, etc. Presentation problems can also occur due to the failure to accurately detect user actions. This may cause virtual objects to disappear or otherwise behave abnormally, or cause incorrect functions to be executed, thus disrupting the illusion that the virtual object exists in the real world. Attached Figure Description

[0005] In accompanying drawings that are not necessarily drawn to scale, similar numbers may describe similar parts in different views. For ease of identification of any particular element or action being discussed, one or more of the highest-order digits in the reference numerals indicate the drawing number in which that element was first introduced. Some embodiments are shown in the accompanying drawings by way of example, not limitation, in the drawings:

[0006] Figure 1 This is a block diagram illustrating an exemplary messaging system for exchanging data (e.g., messages and associated content) over a network, according to an example implementation.

[0007] Figure 2 This illustrates the situation according to an example implementation. Figure 1 A block diagram showing further details of the message sending and receiving system.

[0008] Figure 3 This is a schematic diagram illustrating data that can be stored in a database of a message transceiver server system according to an example implementation.

[0009] Figure 4 This is a schematic diagram illustrating the structure of a message generated by a messaging client application for transmission according to an example implementation.

[0010] Figure 5A This is a block diagram illustrating an example body posture verification system according to an example implementation.

[0011] Figure 5B This is a diagram illustrating the positions of body joints used to determine body posture according to an example embodiment.

[0012] Figure 6 This is a flowchart illustrating an example operation of a body posture verification system according to an example implementation.

[0013] Figure 7 An illustrative body pose mask according to an example implementation is shown.

[0014] Figure 8 The illustrative inputs and outputs of a body posture verification system according to an example implementation are shown.

[0015] Figure 9 It is a graphical representation of a machine in the form of a computer system, based on some examples, within which a set of instructions can be executed to cause the machine to perform any or more of the methods discussed herein.

[0016] Figure 10 It is a block diagram showing a software architecture in which examples can be implemented. Detailed Implementation

[0017] The following description includes systems, methods, techniques, instruction sequences, and computer program products embodying illustrative embodiments of this disclosure. In the following description, numerous specific details are set forth for illustrative purposes to provide an understanding of various embodiments. However, it will be apparent to those skilled in the art that embodiments can be practiced without these specific details. Generally, well-known examples of instructions, protocols, structures, and techniques are not necessarily shown in detail.

[0018] Typically, virtual reality (VR) and augmented reality (AR) systems display an avatar representing a given user by capturing an image of the user and additionally using a depth sensor to obtain a depth map of the real-world human body depicted in the image. By processing the depth map together with the image, VR and AR systems can detect and mimic actions performed by the user or react to such actions. While such systems excel at representing a user's avatar and reacting to actions performed by the user—for example, modifying virtual objects or performing application functions—the need for a depth sensor limits their application. This is because adding a depth sensor to the user device for the purpose of displaying an avatar or performing actions in response to detected user postures increases the overall cost and complexity of the device, thus reducing their appeal.

[0019] Some systems attempt to detect user actions, such as poses, received in an image based on the joint positions of the user's body depicted in the image. Such systems rely on predetermined angles for various joint positions to be specified. These systems calculate the angles of the detected joint positions in the image in real time for comparison with the predetermined angles to detect a given pose. Inputting such angles requires a certain level of skill and is particularly time-consuming when tracking large subsets of poses. This reduces the scalability of the system and increases the overall resource consumption of such systems.

[0020] Other systems attempt to detect user actions by applying previously trained neural networks that segment one or more images to detect a given pose. Such neural networks require significant time and resources to train accurately to predict a given pose. These systems also require the input image to have specific location, orientation, and scale to accurately detect poses within the input image. This reduces the system's scalability and increases the overall resource consumption of such systems, which may still fail to work effectively to detect user poses.

[0021] The disclosed implementation improves the efficiency of using electronic devices by identifying the skeletal joints of a user's body from one or more images of the user and generating a contour of the user's body for comparison with a mask associated with a target pose. If the contour of the body matches the target pose associated with the mask, the user's body pose is verified as matching the target pose. In response, a given set of application actions can be performed, or a virtual object can be displayed in an AR / VR environment. Specifically, a monocular image comprising a depiction of a user's body in a given pose is received, and multiple skeletal joints of the body depicted in the monocular image are detected. Such skeletal joints can be detected using one or more previously trained machine learning techniques or using any other suitable operation. The contour of the user's body is generated based on the multiple skeletal joints, and a mask representing the target pose is retrieved. The mask can be retrieved based on a target function of the application, such as counting jumping jacks, or based on a virtual object to be modified. The contour of the body depicted in the monocular image is compared with the mask representing the target pose, and in response, it is determined that the user's given body pose matches the target pose. As used herein, "contour" refers to the outline or silhouette of an object (e.g., a box representation of an object).

[0022] Determining a user's (or other object's) pose using a mask image eliminates the need for pre-inputting and calculating complex angles between different joint positions. This increases the ease of inputting and creating different target poses and reduces overall resource consumption during pose detection, at least because it eliminates the need to calculate different angles in real time to detect the target pose. Furthermore, according to the disclosed implementation, scalability is increased by aligning the mask with the center of the detected body in the input image, allowing the system to dynamically and continuously adjust to adapt to the user's position in the input image as the user moves left / right or toward / away from the camera device. This makes the disclosed implementation less sensitive to the specific position, orientation, and scale of the user's body in the input image when verifying a given pose performed by the user.

[0023] Virtual objects (e.g., 3D objects such as 3D captions, emojis, characters, avatars, animations, looping animations of personalized avatars or characters, looping or non-looping animated graphics such as dancing hot dogs, stylized words with animation, etc.) can be generated directly from a single red, green, and blue (RGB) image (e.g., a monocular RGB image) or a video of an RGB image depicting a real-world user's body in response to the detection of a target pose. The disclosed implementation generates virtual objects without requiring a depth map of the real-world user's body. This enables user devices with simple RGB camera setups (without depth sensors) to accurately and quickly display animated virtual objects based on the real-world user's body pose in VR or AR applications, allowing users to interact with VR or AR content in a more realistic environment.

[0024] Networked computing environment

[0025] Figure 1 This is a block diagram illustrating an example messaging system 100 for exchanging data (e.g., messages and associated content) over a network. The messaging system 100 includes multiple instances of client devices 102, each instance hosting several applications including a messaging client 104 and an AR / VR application 105. Each messaging client 104 and AR / VR application 105 is communicatively coupled to other instances of the messaging client 104 and AR / VR application 105, as well as a messaging server system 108, via a network 106 (e.g., the Internet).

[0026] The messaging client 104 and the AR / VR application 105 can communicate and exchange data with another messaging client 104 and the AR / VR application 105, as well as the messaging server system 108, via the network 106. The data exchanged between messaging clients 104 and between messaging clients 104 and the messaging server system 108 includes functions (e.g., commands to activate functions) and payload data (e.g., text, audio, video, or other multimedia data).

[0027] AR / VR application 105 is an application that includes a set of functions that allow client device 102 to access body pose verification system 126. In some implementations, AR / VR application 105 is a component or feature as part of messaging client 104. AR / VR application 105 uses an RGB camera device to capture one or more monocular images (e.g., video) of the user's real-world body. AR / VR application 105 applies one or more trained machine learning techniques to the captured body images to detect the positions of the body's skeletal joints. AR / VR application 105 generates the outline of the user's body, for example, by drawing lines connecting the different detected skeletal joint positions. AR / VR application 105 obtains one or more masks from a storage device, each mask depicting a different target pose, for example, performing a given set of application functions. For example, if AR / VR application 105 includes a function to count jumping jacks performed by the user, AR / VR application 105 retrieves a first mask depicting a first target pose and a second mask depicting a second target pose. Whenever the AR / VR application 105 determines that the user's silhouette matches the first target pose of the first mask and then the second target pose of the second mask, the AR / VR application 105 increments the number representing the total number of jumping jacks detected.

[0028] For example, when a user raises their hand above their head and then lowers it, the AR / VR application 105 determines that a single jumping jack has been completed and automatically increments the total number of runs by 1. In some cases, the AR / VR application 105 compares a first outline of the body depicted in a first image of the captured images with a first mask. When the outline substantially overlaps with the target pose depicted in the mask (e.g., when more than a threshold number of pixels in the outline overlap with pixels of the target pose depicted in the mask), the AR / VR application 105 determines that the pose depicted in the first image matches the first mask. The AR / VR application 105 then analyzes a second image subsequently received after the first image to generate a second outline. The AR / VR application 105 retrieves the second mask and compares the second outline with the second mask. When the second outline substantially overlaps with the target pose depicted in the second mask (e.g., when more than a threshold number of pixels in the outline overlap with pixels of the target pose depicted in the mask), the AR / VR application 105 determines that the pose depicted in the second image matches the second mask. Once the AR / VR application 105 determines that the second pose is verified sequentially after the first pose, the AR / VR application 105 performs application functions, such as incrementing a number representing the total number of jumping jacks performed by the user. Other functions may include: firing virtual weapons in a video game or modifying one or more avatars in some way in response to determining that the first and second poses are being performed sequentially by the user.

[0029] In some implementations, AR / VR application 105 directly detects joint positions of a body depicted in a captured RGB image from a first trained machine learning technique obtained from local or remote storage. The first trained machine learning technique processes the captured RGB image to extract one or more features corresponding to the body depicted in the captured RGB image. These features are analyzed to identify one or more skeletal joints and their respective alignments relative to each other. Specifically, these features are analyzed to determine the joint positions of a specified set of skeletal joints. AR / VR application 105 also obtains a second trained machine learning technique to process one or more previously captured frames (e.g., video frames immediately preceding the RGB image 1 to 2 seconds) to estimate or predict skeletal joint positions for subsequent frames. A threshold number of video frames (which may be user-defined, previously specified, and / or dynamically determined) can be stored continuously or periodically in a buffer, making video frames preceding the current RGB image accessible via the second trained machine learning technique. The output or prediction of the skeletal joint positions from the second trained machine learning technique is used to filter or refine the skeletal joint positions identified by the first trained machine learning technique. In some cases, a second trained machine learning technique processes the skeletal joint locations identified by the first trained machine learning technique together with previously captured frames to filter or improve the estimated skeletal joint locations. Techniques for detecting skeletal joint locations are described in more detail in U.S. Patent Application No. 16 / 710,980, filed December 11, 2019, by co-owned Assouline et al., the entire contents of which are incorporated herein by reference.

[0030] The message transceiver server system 108 provides server-side functionality to a specific message transceiver client 104 via network 106. While some functions of the message transceiver system 100 are described herein as being performed by either the message transceiver client 104 or the message transceiver server system 108, the location of certain functions within the message transceiver client 104 or the message transceiver server system 108 can be a design choice. For example, it may be technically preferred that certain technologies and functions be initially deployed within the message transceiver server system 108, but later migrated to the message transceiver client 104 once the client device 102 has sufficient processing power.

[0031] The messaging server system 108 supports various services and operations provided to the messaging client 104. Such operations include sending data to and receiving data from the messaging client 104, and processing data generated by the messaging client 104. This data may include, for example, message content, client device information, geolocation information, media enhancements and coverage, message content persistence conditions, social network information, and on-site event information. Data exchange within the messaging system 100 is triggered and controlled through functions available via the user interface (UI) of the messaging client 104.

[0032] Specifically, turning to message transceiver server system 108, application programming interface (API) server 110 is coupled to application server 112, which includes body posture verification system 126, and provides a programming interface to application server 112. Application server 112 is communicatively coupled to database server 118, which facilitates access to database 120, which stores data associated with messages processed by application server 112. Similarly, web server 124 is coupled to application server 112 and provides a web-based interface to application server 112. For this purpose, web server 124 processes incoming network requests via Hypertext Transfer Protocol (HTTP) and several other related protocols.

[0033] Application Programming Interface (API) server 110 receives and sends message data (e.g., commands and message payloads) between client device 102 and application server 112. Specifically, API server 110 provides a set of interfaces (e.g., routines and protocols) that message sending and receiving client 104 can call or query to invoke functions of application server 112. Application Programming Interface (API) server 110 exposes various functions supported by application server 112, including: account registration; login functionality; sending messages from one messaging client 104 to another messaging client 104 via application server 112; sending media files (e.g., images or videos) from messaging client 104 to messaging server 114; and setting up a set of media data (e.g., stories) to be accessible by another messaging client 104, retrieving the friend list of the user of client device 102, retrieving such a set, retrieving messages and content, adding and deleting entities (e.g., friends) from an entity graph (e.g., a social graph), locating friends in the social graph, and opening (e.g., in relation to messaging client 104) application events.

[0034] Application server 112 hosts several server applications and subsystems, including, for example, messaging server 114, image processing server 116, body pose verification system 126, and social networking server 122. Messaging server 114 implements several messaging techniques and functions, which specifically relate to the aggregation and other processing of content (e.g., text and multimedia content) included in messages received from multiple instances of messaging client 104. As will be described in further detail, text and media content from multiple sources can be aggregated into content collections (e.g., referred to as stories or galleries). These collections are then made available to messaging client 104. Such processing can also be performed on the server side by messaging server 114, taking into account the hardware requirements for other processor- and memory-intensive processing of data.

[0035] Application server 112 also includes image processing server 116, which is dedicated to performing various image processing operations, typically relative to the images or videos within the payload of messages sent from or received at message transceiver server 114.

[0036] Social networking server 122 supports various social networking functions and services and makes these functions and services available to messaging server 114. To this end, social networking server 122 maintains and accesses entity graph 306 (such as...) within database 120. Figure 3 (As shown). Examples of the functions and services supported by the social networking server 122 include identifying other users in the messaging system 100 who have a relationship with or are “following” that particular user, as well as identifying the interests and other entities of that particular user.

[0037] System Architecture

[0038] Figure 2 This is a block diagram illustrating further details of a messaging system 100 according to some examples. Specifically, the messaging system 100 is shown as including a messaging client 104 and an application server 112. The messaging system 100 includes several subsystems supported on the client side by the messaging client 104 and on the server side by the application server 112. These subsystems include, for example, a short-timer system 202, a collection management system 204, an enhancement system 206, a map system 208, and a game system 210. In some implementations, the enhancement system 206 implements some or all of the functionality of the body pose verification system 126.

[0039] The short-lived timer system 202 is responsible for enabling temporary or time-limited access to content by message transceiver client 104 and message transceiver server 114. The short-lived timer system 202 includes several timers that selectively enable access (e.g., for rendering and displaying) of messages and associated content via message transceiver client 104 based on duration and display parameters associated with a message or set of messages (e.g., a story). Further details regarding the operation of the short-lived timer system 202 are provided below.

[0040] The collection management system 204 is responsible for managing groups and collections of media (e.g., collections of text, image, video, and audio data). Collections of content (e.g., messages including images, videos, text, and audio) can be organized into "event galleries" or "event stories." Such collections can be made available for a specified time period, such as the duration of an event related to the content. For example, content related to a concert can be made available as a "story" during the duration of the concert. The collection management system 204 can also be responsible for publishing icons that provide notifications of the existence of specific collections to the user interface of the messaging client 104.

[0041] Furthermore, the collection management system 204 includes a curation interface 212, which allows the collection manager to manage and curate specific content collections. For example, the curation interface 212 enables an event organizer to curate content collections related to a specific event (e.g., removing inappropriate content or redundant messages). Additionally, the collection management system 204 employs machine vision (or image recognition technology) and content rules to automatically curate content collections. In some examples, users may be paid compensation for including user-generated content in the collection. In such cases, the curation management system 204 operates to automatically pay such users for using their content.

[0042] Enhancement system 206 provides various functions that enable users to enhance (e.g., annotate or otherwise modify or edit) media content associated with messages. For example, enhancement system 206 provides functions related to generating and publishing media overlays for messages processed by messaging system 100. Enhancement system 206 can operable to supply media overlays or enhancements (e.g., image filters) to messaging client 104 based on the geographic location of client device 102. In another example, enhancement system 206 can operable to supply media overlays to messaging client 104 based on other information such as the social network information of the user of client device 102. Media overlays can include audio and visual content and visual effects. Examples of audio and visual content include pictures, text, logos, animations, and sound effects. Examples of visual effects include color overlays. Audio and visual content or visual effects can be applied to media content items (e.g., photos) at client device 102. For example, media overlays can include text or images that can be overlaid on a photograph taken by client device 102. In another example, media overlays include location identifier overlays (e.g., Venice Beach), live event name overlays, or business name overlays (e.g., Beach Cafe). In yet another example, enhancement system 206 uses the geolocation of client device 102 to identify media overlays that include the name of a business located at the geographic location of client device 102. Media overlays may include other tags associated with the business. Media overlays may be stored in database 120 and accessed via database server 118.

[0043] In some examples, the enhancement system 206 provides a user-based publishing platform that allows users to select geographic locations on a map and upload content associated with those locations. Users can also specify the environment in which specific media coverage should be provided to other users. The enhancement system 206 generates media coverage that includes the uploaded content and associates the uploaded content with the selected geographic location.

[0044] In other examples, Enhancement System 206 provides a merchant-based publishing platform that enables merchants to select specific media coverage associated with geographic locations via a bidding process. For instance, Enhancement System 206 associates the media coverage of the highest-bidder merchant with a corresponding geographic location for a predefined amount of time.

[0045] Map system 208 provides various geolocation functions and supports the presentation of map-based media content and messages by messaging client 104. For example, map system 208 enables the display (e.g., stored in configuration data 308) of user icons or avatars on a map to indicate the current or past locations of a user's "friends" in the context of the map, as well as media content generated by such friends (e.g., a collection of messages including photos and videos). For example, a message posted by a user from a specific geolocation to messaging system 100 can be displayed at that specific location to a specific user's "friends" in the context of the map on the map interface of messaging client 104. A user can also share his or her location and status information with other users of messaging system 100 (e.g., using appropriate status avatars) via messaging client 104, where the location and status information is similarly displayed to the selected user in the context of the map interface of messaging client 104.

[0046] The gaming system 210 provides various gaming functions within the context of the messaging client 104. The messaging client 104 provides a game interface that offers a list of available games that can be started by a user within the context of the messaging client 104 and played with other users of the messaging system 100. The messaging system 100 also enables specific users to invite other users to participate in specific games by sending invitations from the messaging client 104. The messaging client 104 also supports both voice and text messaging (e.g., chat) within the context of gaming, provides leaderboards for the game, and supports in-game rewards (e.g., coins and items).

[0047] Data Architecture

[0048] Figure 3 This is a schematic diagram illustrating a data structure 300 that can be stored in a database 120 of a message transceiver server system 108, according to certain examples. Although the contents of the database 120 are shown as including several tables, it should be understood that the data can be stored in other types of data structures (e.g., as an object-oriented database).

[0049] Database 120 includes message data stored in message table 302. For any given message, this message data includes at least message sender data, message receiver (or recipient) data, and a payload. See below for reference. Figure 4 Further details are described regarding information that can be included in the message and in the message data stored in message table 302.

[0050] Entity table 304 stores entity data and (for example, links to entity diagram 306 and configuration data 308). Entities that maintain records within entity table 304 can include individuals, company entities, organizations, objects, locations, events, etc. Regardless of entity type, any entity whose data is stored in message transceiver server system 108 can be an identifiable entity. Each entity is provided with a unique identifier and an entity type identifier (not shown).

[0051] Entity graph 306 stores information about the relationships and associations between entities. Such relationships may be, for example, social, professional (e.g., working in the same company or organization), interest-based, or activity-based.

[0052] Profile data 308 stores various types of profile data about a specific entity. Based on privacy settings specified by the specific entity, profile data 308 can be selectively used and presented to other users of messaging system 100. In the case of an individual, profile data 308 includes, for example, a username, phone number, address, settings (e.g., notification and privacy settings), and an avatar representation (or a set of such avatar representations) selected by the user. A specific user can then selectively include one or more of these avatar representations in the content of messages transmitted via messaging system 100 and in a map interface displayed to other users by messaging client 104. The set of avatar representations may include “status avatars,” which present a graphical representation of a status or activity that the user can choose to communicate at a specific time.

[0053] In the case that the entity is a group, in addition to the group name, members and various settings of the associated group (e.g., notifications), the group’s profile data 308 may similarly include one or more avatars associated with the group.

[0054] Database 120 also stores enhancement data, such as overlays or filters, in enhancement table 310. This enhancement data is associated with and applied to videos (video data is stored in video table 314) and images (image data is stored in image table 316).

[0055] In one example, a filter is an overlay displayed as an image or video during presentation to the receiving user. Filters can be of various types, including filters selected by the user from a set of filters presented to the sending user by the messaging client 104 when the sending user is composing a message. Other types of filters include geolocation filters (also known as geographic filters), which can be presented to the sending user based on geographic location. For example, a geolocation filter specific to a nearby or particular location can be presented by the messaging client 104 within the user interface based on geographic location information determined by the Global Positioning System (GPS) unit of the client device 102.

[0056] Another type of filter is a data filter, which can be selectively presented to the sending user by the messaging client 104 based on other inputs or information collected by the client device 102 during the message creation process. Examples of data filters include the current temperature at a specific location, the current speed of the sending user, the battery life of the client device 102, or the current time.

[0057] Other augmented data that can be stored in image table 316 includes augmented reality content items (e.g., corresponding to an applied lens or augmented reality experience). Augmented reality content items can be real-time special effects and sounds that can be added to images or videos.

[0058] The trained machine learning technique 306 stores parameters that have been trained during the training of the body pose verification system 126. For example, the trained machine learning technique 306 stores training parameters for one or more neural network machine learning techniques.

[0059] Target pose mask 309 stores masks representing different target poses. Each target pose mask, or a combination or sequence of target pose masks, can be associated with different AR / VR application functions. Each target pose mask includes a black-and-white depiction of the target pose. For example, a mask can depict a target pose using white pixels on a black background. Any other suitable mask arrangement or color can be used in the mask to represent the target pose, such as black pixels representing the target pose on a white background. Masks can be user-defined or drawn using any suitable drawing tool and stored in target pose mask 309. Masks can depict the user's entire body (e.g., arms, head, neck, torso, and legs) or only a portion of the body that constitutes the subject of the target pose (e.g., only the head, neck, shoulders, and arms). Each mask can be associated with a pixel count or pixel threshold that specifies how much the mask must overlap with the outline of the user depicted in the input image for verification as a target pose. The threshold can also be defined as a more complex mathematical function for matching and not matching mask pixels. For example, a first mask may be associated with an 80% threshold, and a second mask may be associated with a 95% threshold. In this case, a first target pose is verified or detected when a pixel corresponding to the user's body contour overlaps 80% of the pixels depicting the target pose in the first mask. As another example, a second target pose is not verified or detected when a pixel corresponding to the user's body contour overlaps less than 95% of the pixels depicting the target pose in the second mask. In some cases, a default threshold may be applied to all masks stored in the target pose mask 309. Masks may also depict any non-human object (e.g., a dog, cat, animal, or other object). That is, the disclosed implementation is suitable for detecting the target pose of a user and the target pose of other objects.

[0060] In some implementations, a first threshold may be associated with a first portion of the first mask (e.g., the head region of the first pose may be associated with a 50% threshold), and a second threshold may be associated with a second portion of the first mask (e.g., the arm region of the first pose may be associated with an 85% threshold). In this case, a first target pose is verified or detected when the head region pixels of the user's body contour depicted in the image region overlap with at least 50% of the head region of the first mask, and when the arm region pixels of the contour overlap with more than 85% of the arm region of the first mask. A first target pose is not verified or detected when the head region pixels of the user's body contour depicted in the image region overlap with at least 50% of the head region of the first mask, and when the arm region pixels of the contour overlap with less than 85% of the arm region of the first mask.

[0061] A first mask stored in target pose mask 309 can be associated with a second mask. For example, the first mask can be positioned as first in the target pose sequence, and the second mask can be positioned as second in the target pose sequence. In this case, the application function is executed when the second target pose is detected sequentially after the first target pose is detected. If the second target pose is detected first and then the first target pose is detected, the application function is not executed, and the system continues to monitor the target pose sequence. In some cases, any combination of poses detected in the input image that matches all poses in the sequence, regardless of the sequence in which these poses are detected, results in the execution of the application function. For example, detecting the second pose in the target pose sequence and then detecting the first pose may cause the application function to be executed. In some implementations, the first application function is executed when the target pose sequence is detected (e.g., the first target pose is detected in the input image, followed by the second target pose), and the second application function is executed when the target poses are not detected in sequence (e.g., the second target pose is detected in the input image before the first target pose).

[0062] As described above, augmented data includes augmented reality content items, overlays, image transformations, AR images, and similar items referring to modifications that can be applied to image data (e.g., video or images). This includes real-time modifications, which modify an image as it is captured by the device sensors (e.g., one or more cameras) of client device 102 and then displayed on the screen of client device 102 in modified form. This also includes modifications to stored content (e.g., video clips in a modifiable gallery). For example, in client device 102 with access to multiple augmented reality content items, a user can use a single video clip with multiple augmented reality content items to see how different augmented reality content items will modify the stored clip. For example, by selecting different augmented reality content items for the same content, multiple augmented reality content items with different pseudo-random motion models can be applied to that same content. Similarly, real-time video capture can be used with the illustrated modifications to show how the video image currently captured by the sensors of client device 102 will modify the captured data. Such data can be simply displayed on the screen without being stored in memory, or the content captured by the device's sensors can be recorded and stored in memory with or without modification (or both). In some systems, preview features can show how different augmented reality content items will look simultaneously in different windows on the display. For example, this can make it possible to view multiple windows with different pseudo-random animations on the display at the same time.

[0063] Therefore, using augmented reality content items and various systems, or other such transformation systems that use that data to modify the content, can involve the detection of objects (e.g., faces, hands, bodies, cats, dogs, surfaces, objects, etc.), tracking such objects as they leave and enter the field of view in a video frame and move around the field of view, and modifying or transforming such objects while they are being tracked. In various implementations, different methods can be used to implement such transformations. Some examples may involve generating a 3D mesh model of one or more objects and using transformations of the model and animated textures within the video to implement the transformation. In other examples, tracking points on the object can be used to place an image or texture (which may be two-dimensional or three-dimensional) at the tracked location. In further examples, neural network analysis of video frames can be used to place images, models, or textures within the content (e.g., images or frames of a video). Thus, augmented reality content items refer both to the images, models, and textures used to create transformations within the content and to the additional modeling and analysis information required to implement such transformations using object detection, tracking, and placement.

[0064] Real-time video processing can be performed using any type of video data (e.g., video streams, video files, etc.) stored in the memory of any type of computerized system. For example, a user can load a video file and store it in the device's memory, or a video stream can be generated using the device's sensors. Furthermore, computer-animated models can be used to process any object, such as human faces and parts of the human body, animals, or inanimate objects (e.g., chairs, cars, or other objects).

[0065] In some examples, when a specific modification is selected along with the content to be transformed, the element to be transformed is identified by the computing device, and then, if the element to be transformed exists in a frame of the video, it is detected and tracked. The elements of the object are modified according to the modification request, thereby transforming the frames of the video stream. For different kinds of transformations, the transformation of the video stream frames can be performed using different methods. For example, for frame transformations that primarily refer to changes in the elements of an object, feature points of each element of the object are calculated (e.g., using an Active Shape Model (ASM) or other known methods). Then, a feature point-based mesh is generated for each of at least one element of the object. This mesh is used for subsequent stages of tracking the elements of the object in the video stream. During tracking, the mesh referenced for each element is aligned with the position of each element. Then, additional points are generated on the mesh. A first set of points is generated for each element based on the modification request, and a second set of points is generated for each element based on this first set of points and the second set of points, as well as the mesh, to transform the frames of the video stream. In such methods, the background of the modified object can also be altered or distorted by tracking and modifying the background.

[0066] In some examples, transformations that alter some regions of an object using its elements can be performed by calculating feature points for each element of the object and generating a mesh based on those calculated feature points. Points are generated on the mesh, and then various regions are generated based on these points. The elements of the object are then tracked by aligning the region of each element with the position of at least one of the elements, and the properties of the regions can be modified based on modification requests, thereby transforming frames of the video stream. Depending on the specific modification request, the properties of the mentioned region can be transformed in different ways. Such modifications can involve: changing the color of the region; removing at least a portion of the region from the frames of the video stream; including one or more new objects in the region based on the modification request; and modifying or distorting the elements of the region or object. In various implementations, any combination of such modifications or other similar modifications can be used. For certain models to be animated, some feature points can be selected as control points to determine the entire state space for options used in model animation.

[0067] In some examples of computer animation models that use face detection to transform image data, a specific face detection algorithm (e.g., Viola-Jones) is used to detect faces on the image. Then, the Active Shape Model (ASM) algorithm is applied to the facial regions of the image to detect facial feature reference points.

[0068] In other examples, other methods and algorithms suitable for face detection can be used. For example, in some implementations, landmarks are used to locate features that represent distinguishable points present in most of the images considered. For example, for a face landmark, the location of the left pupil could be used. If the initial landmark is not recognizable (e.g., if the person is wearing an eye patch), secondary landmarks can be used. Such a landmark recognition process can be used for any such object. In some examples, a set of landmarks forms a shape. The shape can be represented as a vector using the coordinates of the points in the shape. One shape is aligned with another shape using a similarity transformation (allowing translation, scaling, and rotation) that minimizes the average Euclidean distance between the points of the shapes. The average shape is the average of the aligned training shapes.

[0069] In some examples, the search begins by finding landmarks from an average shape aligned with the position and size of a face determined by a global face detector. This search then repeats the steps of adjusting the positions of shape points to suggest provisional shapes through template matching of the image texture around each point, and then conforming the provisional shapes to a global shape model until convergence occurs. In some systems, individual template matching is unreliable, and the shape model pools the results of weak template matching to form a stronger overall classifier. The entire search is repeated at each level of the image pyramid, from coarse to fine resolution.

[0070] The transformation system can capture image or video streams on a client device (e.g., client device 102) and perform complex image manipulations locally on client device 102 while maintaining an appropriate user experience, computation time, and power consumption. Complex image manipulations can include size and shape changes, emotion transfers (e.g., changing a face from frowning to smiling), state transfers (e.g., aging a subject, reducing apparent age, or changing gender), style transfers, application of graphic elements, and any other suitable image or video manipulations implemented by a convolutional neural network that has been configured to execute efficiently on client device 102.

[0071] In some examples, a computer animation model for transforming image data can be used by a system in which a user can capture an image or video stream (e.g., a selfie) using a client device 102 that operates as part of a messaging client 104 operating on client device 102. A transformation system operating within messaging client 104 determines the presence of a face within the image or video stream and provides a modification icon associated with the computer animation model for transforming the image data, or the computer animation model can be presented as associated with the interface described herein. The modification icon includes changes that can be the basis for modifying the user's face within the image or video stream as part of a modification operation. Once a modification icon is selected, the transformation system initiates a process of transforming the user's image to reflect the selected modification icon (e.g., generating a smiley face on the user). Once the image or video stream has been captured and the specified modification has been selected, the modified image or video stream can be presented in a graphical user interface displayed on client device 102. The transformation system can implement a complex convolutional neural network on a portion of the image or video stream to generate and apply the selected modification. In other words, users can capture image or video streams, and the changes are displayed in real-time or near real-time once an edit icon is selected. Furthermore, while a video stream is being captured, the changes can be persistent, and the selected edit icon continues to be toggled. Machine-trained neural networks can be used to achieve such modifications.

[0072] A graphical user interface (GUI) presenting modifications performed by the transformation system can provide users with additional interactive options. Such options can be based on an interface used to initiate content capture and selection for a specific computer animation model (e.g., initiated from a content creator user interface). In various implementations, modifications can be persistent after an initial selection of the modification icon. Users can turn modifications on or off by tapping or otherwise selecting a face modified by the transformation system and save it for later viewing or browsing to other areas of the imaging application. In cases where multiple faces are modified by the transformation system, users can globally turn modifications on or off by tapping or selecting a single face modified and displayed within the GUI. In some implementations, individual faces within a set of multiple faces can be modified individually, or such modifications can be toggled individually by tapping or selecting individual faces or a series of individual faces displayed within the GUI.

[0073] Story table 312 stores data about collections of messages, along with associated image, video, or audio data, compiled into collections (e.g., stories or galleries). The creation of a specific collection can be initiated by a specific user (e.g., each user maintaining a record in entity table 304). A user can create a "personal story" in the form of a collection of content that has been created and sent / broadcast by that user. For this purpose, the user interface of messaging client 104 can include user-selectable icons that allow the sending user to add specific content to his or her personal story.

[0074] The collection can also constitute a "live story" as a collection of content from multiple users, created manually, automatically, or using a combination of manual and automatic techniques. For example, a "live story" can constitute a curated stream of user-submitted content from various locations and events. For instance, the user interface of messaging client 104 can provide its client devices with options to enable location services and present content to specific live stories at public locations at specific times. The messaging client 104 can identify live stories to users based on their location. The end result is a "live story" told from a community perspective.

[0075] Another type of content collection is called a "location story," which allows users whose client device 102 is located within a specific geographic location (e.g., on a college or university campus) to contribute to a specific collection. In some implementations, contributing to a location story may require a second level of authentication to verify that the end user belongs to a specific organization or other entity (e.g., a student on a university campus).

[0076] As mentioned above, video table 314 stores video data, which, in one example, is associated with messages whose records are maintained within message table 302. Similarly, image table 316 stores image data associated with messages whose message data is stored in entity table 304. Entity table 304 can associate various enhancements from enhancement table 310 with various images and videos stored in image table 316 and video table 314.

[0077] Data communication architecture

[0078] Figure 4This is a schematic diagram illustrating the structure of message 400 according to some examples, generated by message transceiver client 104 for transmission to another message transceiver client 104 or message transceiver server 114. The content of a particular message 400 is used to populate message table 302 stored in database 120, which is accessible by message transceiver server 114. Similarly, the content of message 400 is stored in memory as "in transit" or "in flight" data of client device 102 or application server 112. Message 400 is shown to include the following example components:

[0079] • Message Identifier 402: A unique identifier that identifies message 400.

[0080] • Message text payload 404: The text to be generated by the user via the user interface of the client device 102 and included in message 400.

[0081] • Message image payload 406: Image data captured by the camera component of the client device 102 or retrieved from the memory component of the client device 102 and included in the message 400. The image data for the sent or received message 400 may be stored in the image table 316.

[0082] • Message video payload 408: Video data captured by the camera device component or retrieved from the memory component of the client device 102 and included in the message 400. The video data for the sent or received message 400 can be stored in the video table 314.

[0083] • Message audio payload 410: Audio data captured by the microphone or retrieved from the memory component of the client device 102 and included in message 400.

[0084] • Message enhancement data 412: Enhancement data (e.g., filters, labels, or other annotations or enhancements) representing enhancements to be applied to the message image payload 406, message video payload 408, or message audio payload 410 of message 400. Enhancement data for the sent or received message 400 can be stored in enhancement table 310.

[0085] • Message duration parameter 414: A parameter value, in seconds, indicating the amount of time the message content (e.g., message image payload 406, message video payload 408, message audio payload 410) will be presented to the user or accessible to the user via the message sending and receiving client 104.

[0086] • Message geolocation parameter 416: Geographic location data (e.g., latitude and longitude coordinates) associated with the message's content payload. Multiple message geolocation parameter 416 values ​​may be included in the payload, each of which is associated with a content item included in the content (e.g., a specific image in the message image payload 406, or a specific video in the message video payload 408).

[0087] • Message Story Identifier 418: An identifier value that identifies one or more content sets (e.g., “Stories” identified in Story Table 312), wherein a specific content item in the message image payload 406 of message 400 is associated with one or more content sets. For example, the identifier value can be used to associate multiple images within the message image payload 406 with multiple content sets, respectively.

[0088] • Message Tag 420: Each message 400 can be labeled with multiple tags, each of which indicates the subject of the content included in the message payload. For example, in the case where a specific image depicts an animal (e.g., a lion) is included in the message image payload 406, the tag value can be included within the message tag 420 indicating the relevant animal. Tag values ​​can be generated manually based on user input, or they can be automatically generated using, for example, image recognition.

[0089] • Message sender identifier 422: An identifier (e.g., a message sending system identifier, email address, or device identifier) ​​that indicates the user of the client device 102 on which message 400 is generated and from which message 400 is sent.

[0090] • Message receiver identifier 424: An identifier (e.g., message sending and receiving system identifier, email address, or device identifier) ​​indicating the user of the client device 102 to which message 400 is addressed.

[0091] The content (e.g., values) of each component of message 400 can be pointers to locations in tables where content data values ​​are stored. For example, an image value in message image payload 406 can be a pointer to a location within image table 316 (or an address of a location within image table 308). Similarly, a value in message video payload 408 can point to data stored in video table 314, a value in message enhancement data 412 can point to data stored in enhancement table 310, a value in message story identifier 418 can point to data stored in story table 312, and values ​​in message sender identifier 422 and message receiver identifier 424 can point to user records stored in entity table 304.

[0092] Figure 5AThis is a block diagram illustrating an example body posture verification system 126 according to an exemplary implementation. The body posture verification system 126 operates on a set of input data (e.g., a monocular image 501 depicting a user's real body and a target posture mask 502). A first portion of this set of input data is obtained from a database 120, and a second portion is obtained from an RGB camera device of a client device 102 when using an AR / VR application 105. The body posture verification system 126 includes a machine learning technology module 512, a skeletal joint position module 514, a posture verification module 516, a virtual object modification module 518, and a virtual object display module 520.

[0093] In some embodiments, the body pose verification system 126 includes a user detection component (not shown). The user detection component is activated in response to input from a user to an activating client device 102, either a forward-facing or backward-facing camera. Once activated, the user detection component analyzes features of a set of images captured by the client device's camera. The user detection component determines whether these features match a human or an object corresponding to a human. In this case, the user detection component initiates a process for determining whether the pose of the user depicted in the images matches a target pose. Specifically, the user detection component instructs the machine learning technology module 512, the skeletal joint position module 514, and the pose verification module 516 to compare the detected user poses in the images with one or more masks depicting the respective poses. In some cases, the user detection component is part of the machine learning technology module 512.

[0094] Machine learning module 512 extracts one or more features from a given input image to estimate the skeletal joint positions depicted in the image. For example, machine learning module 512 obtains a given image depicting a user's face, arms, torso, hips, and legs. Machine learning module 512 extracts features corresponding to the user's face and arms from the image to identify one or more skeletal joints (e.g., ...). Figure 5B The joints shown include the left / right wrist joints, left / right elbow joints, left / right shoulder joints, and the nose position.

[0095] The machine learning technology module 512 determines the relative position of the identified skeletal joints in order to determine the posture corresponding to the position of the skeletal joints.

[0096] In some implementations, the second machine learning module 512 extracts one or more features from a given input video to predict the skeletal joint positions in frames following the previous frame of the video. The second machine learning module 512 extracts features corresponding to the user's face and arms from the video to predict one or more skeletal joints in frames following the previous frame of the video (e.g., ...). Figure 5BThe joints shown include the left / right wrist joints, left / right elbow joints, left / right shoulder joints, and nose position. The second machine learning module 512 predicts the skeletal joint positions along one or more subsequent frames of a given input video. The second machine learning module 512 may receive the current video frame and / or the skeletal joint positions determined based on that current video frame. The second machine learning module 512 may process a set of previous frames depicting body movement along with image features of the current frame and predict the estimated skeletal joint positions for the next frame. Based on this prediction, the second machine learning module 512 compares the predicted estimated skeletal joint positions with the skeletal joint positions determined by the first machine learning module 512 for the current frame. The second machine learning module 512 may then determine any deviations and necessary corrections based on this comparison.

[0097] The features extracted by the machine learning technology module 512 are provided to the skeletal joint location module 514. The skeletal joint location module 514 analyzes the skeletal joint features to determine the coordinates of specific skeletal joints. For example, the skeletal joint location module 514 determines the x and y coordinates of specific points of each skeletal joint, such as the x and y coordinates of the left wrist, left elbow, left shoulder, nose (or other facial features, such as mouth, ears, or eyes), right wrist, right elbow, and right shoulder.

[0098] The pose verification module 516 determines whether the pose corresponding to the detected skeletal joint positions matches a target pose in one or more masks. The pose verification module 516 connects the joint positions with lines to generate a contour texture of the body depicted in the image. The contour texture records or stores a raster representation of the pose against the background. In some cases, the pose verification module 516 draws the contour of the body texture in a first color (e.g., gray).

[0099] The pose verification module 516 retrieves one or more masks from the target pose mask 309. In some cases, the user selects an operation or function of the AR / VR application via the user interface. The application or function can be selected by tapping an option to count the number of jumping jacks performed by the user. In response, the AR / VR application identifies a sequence of masks stored in the target pose mask 309 associated with the selected function or operation. For example, the AR / VR application determines that two masks representing two different target poses are associated with the selected function or operation. Figure 7An illustrative body pose mask 700 according to an example embodiment is shown. Specifically, the selected operation or function may be associated with a first mask 701 depicting a first target pose and a second mask 702 depicting a second target pose. The first mask 701 may include a set of white pixels representing the first target pose in which the head is centered and both arms are raised above the head. The second mask 702 may include a set of white pixels representing the second target pose in which the head is centered and the arms move down through the waist to a neutral position. The target poses depicted in the retrieved masks are marked with a second color (e.g., blue).

[0100] In some implementations, the posture verification module 516 calculates the distance between predetermined pairs of joints (e.g., neck and head or two shoulder joints). Based on this distance, the posture verification module 516 selects or adjusts the scale of one or more retrieved masks.

[0101] The pose verification module 516 aligns one or more of the retrieved masks with the contour texture of the user's body. For example, the pose verification module 516 identifies the center of the mask by recognizing the position of the head within the mask and aligns the mask based on the position of the head joints. That is, the pose verification module 516 covers the mask such that the head position in the mask is substantially aligned with the head joint position. The pose verification module 516 changes the color of the mask pixels covered by the contour texture from a second color to a third color (e.g., from blue to red). Next, the pose verification module 516 calculates how many pixels of the generated contour texture overlap with the region of the mask that includes pixels representing the pose. For example, the pose verification module 516 counts how many pixels of the contour texture overlap with the white pixels of the mask by counting how many pixels of the third color (e.g., red) are detected as a match or a mismatch. That is, the pose verification module 516 counts how many pixels match and mismatch between the current frame mask and the target mask. In response to determining that more than a certain percentage of pixels overlap between the contour texture and the mask, the pose verification module 516 verifies or determines that the user's body pose matches the target pose of the mask.

[0102] The pose verification module 516 determines whether the second mask is associated with an operation or function. For example, the pose verification module 516 determines whether an operation or function is associated with a sequence of masks or poses. In response, the pose verification module 516 retrieves the second mask from the mask sequence. The pose verification module 516 analyzes the contour texture generated based on joint positions detected in the second image or second set of images, comparing it to the pose represented by the second mask. When the pose verification module 516 determines that a threshold percentage or number of pixels of the contour texture overlaps with the pose depicted in the second mask, the pose verification module 516 verifies or determines that the pose of the user's body in the second image or second set of images matches the target pose of the second mask. Once the pose verification module 516 determines that a sequence or combination of poses depicted by a sequence or combination of masks has been detected in the received or captured image, the pose verification module 516 causes the function or operation of the AR / VR application to be executed.

[0103] The virtual object modification module 518 can adjust the skeletal rig of a given avatar based on the posture received from the posture verification module 516. The virtual object modification module 518 adjusts how the avatar is presented in the image, for example, by changing the avatar's posture, visual attributes, and / or position in the image. The adjusted avatar is provided by the virtual object modification module 518 to the virtual object display module 520. In some embodiments, the virtual object display module 520 combines the adjusted avatar into a received monocular image depicting the user's body, such that the adjusted avatar and the user are simultaneously presented in the image. This image is provided by the virtual object display module 520 to the client device 102 and can then be sent to another user or stored for subsequent access and display. In some embodiments, the virtual object display module 520 performs functions of an AR / VR application, such as updating a count representing the number of times a posture or posture sequence was detected based on the posture received from the posture verification module 516. For example, the virtual object display module 520 may present the cumulative total number of times the user performs an action or posture corresponding to jumping jacks. Specifically, each time the user raises their arm above their head and then lowers it all the way down, the virtual object display module 520 increments a counter that is displayed as an indication of the number of jumping jacks performed by the user.

[0104] Figure 6This is a flowchart illustrating example operation of the body posture verification system 126 during the execution of process 600 according to an exemplary embodiment. Process 600 can be implemented as computer-readable instructions for execution by one or more processors, such that the operations of process 600 can be performed partially or entirely by functional components of the messaging server system 108 and / or the AR / VR application 105; therefore, process 600 is described below by way of example. However, in other embodiments, at least some operations of process 600 can be deployed on various other hardware configurations. Therefore, process 600 is not intended to be limited to messaging server system 108 and can be implemented wholly or partially by any other component. Some or all of the operations of process 600 can be parallel, out of sequence, or completely omitted.

[0105] At operation 601, the body posture verification system 126 receives a monocular image comprising a depiction of a user's body in a given posture. For example, the machine learning technology module 512 receives the monocular image 501 depicting the user's body. The machine learning technology module 512 extracts one or more features indicating skeletal joints from the image.

[0106] At operation 602, the body pose verification system 126 detects multiple skeletal joints of the body depicted in the monocular image 501. For example, the skeletal joint position module 514 processes features extracted by the machine learning technology module 512 to determine the positions of a set of skeletal joints. These positions can be relative to (in...) Figure 5B The neutral position of each skeletal joint (as shown in the diagram) is used to determine this.

[0107] At operation 603, the body posture verification system 126 generates a contour texture of the user's body based on multiple skeletal joints. For example, the posture verification module 516 draws lines connecting the positions of multiple skeletal joints.

[0108] At operation 604, body pose verification system 126 retrieves a mask representing a target pose. For example, body pose verification system 126 retrieves one or more masks based on the target functionality of an AR / VR application. The mask uses, for example, black and white pixels to depict a given pose or combination or sequence of poses, where the white pixels correspond to the target pose.

[0109] At operation 605, the body pose verification system 126 compares the outline texture of the body depicted in the monocular image with a mask representing the target pose. For example, after aligning the body outline texture with the mask, the body pose verification system 126 covers the body outline texture with the mask. The body pose verification system 126 identifies pixels of the body outline texture that overlap or cover a portion of the mask depicting the target pose. The body pose verification system 126 counts how many pixels of the outline texture overlap or cover that portion of the mask depicting the target pose.

[0110] At operation 606, the body pose verification system 126, in response to a comparison of the body's contour texture with a mask, determines that a given pose of the user's body matches a target pose. For example, the body pose verification system 126 retrieves a threshold and determines whether the number of pixels in the body's contour texture that overlap with or cover a portion of the mask depicting the target pose exceeds the threshold. In this case, the body pose verification system 126 performs a function or operation of the AR / VR application corresponding to the target pose. In some embodiments, the body pose verification system 126 retrieves a second target pose in a sequence of target poses and, after determining that the initial set of images includes a depiction of a body in a first target pose, performs the function or operation only after determining that the second set of images includes a depiction of a user's body in a second target pose.

[0111] Although the described flowcharts may show operations as a sequential process, many operations within an operation can be executed in parallel or simultaneously. Furthermore, the order of operations can be rearranged. A process terminates when its operations are complete. A process can correspond to a method, program, algorithm, etc. The operations of a method can be executed in whole or in part, in combination with some or all of the operations of other methods, and can be executed by any number of different systems, such as the system described herein, or any part thereof, such as a processor included in any system.

[0112] Figure 8 Illustrative inputs and outputs of a body posture verification system according to an exemplary embodiment are shown. For example, a user of client device 102 can select an option to count jumping jacks. Specifically, client device 102 may present a UI for an AR / VR application with multiple options for performing functions associated with different body postures. The user can select the option to count jumping jacks from the multiple options. In response, a first mask and a second mask are retrieved ( Figure 7 (As shown in the image), it compares the user's contour texture to determine when a sequence of poses depicted in the mask matches the user's contour in the captured image. Regarding Figure 8Some or all of the indicators shown and described may be omitted and shown for illustrative purposes. That is, only the user's image in 810 may be presented along with the run counter 840. Figure 8 All other parts shown can be omitted and are used by the system in the background to count the opening and closing jumps to update the run counter 840.

[0113] As an example, a first user interface 800 is presented to a user. The first user interface 800 depicts a video 810 of the user performing different postures. The first user interface 800 includes indicators of the function of the AR / VR application being performed. In this example, the function is to calculate jumping jacks, and the indicator includes the current number of jumping jacks detected. The first user interface 800 includes a first portion 820 for identifying a first target posture and a second portion 830 for identifying a second target posture associated with the function being performed. As the video is captured, the image is processed to detect the user's joint positions and a contour is drawn by connecting the joint positions. The contour of the current skeletal joint position is represented by a first indicator 822 (e.g., gray). A second indicator 832 (e.g., blue) identifies the target posture. This contour is continuously updated in real time as the user moves around and changes their body position in the video. Each indicator maintains its respective color when the first indicator 822 does not overlap with any part of the second indicator 832. A body posture verification system 126 uses a reference (e.g., the user's head 834) to align a mask with the contour of the user's body. As shown in the first user interface 800, the portion of the mask corresponding to the head 834 is indicated by an indicator (e.g., red) to be aligned with the user's head joint.

[0114] Initially, the body pose verification system 126 selects a first mask corresponding to a first target pose represented in the first portion 820 for comparison against the contour of the user's body. Specifically, the first mask may be positioned as the first in a pose sequence corresponding to a selected application function. Therefore, any pose performed by the user that does not match the first target pose corresponding to the first mask fails verification, even if such a pose matches a second target pose in the pose sequence corresponding to a second mask. The body pose verification system 126 determines that the indicator 821 representing the first pose in the first mask overlaps with the contour of the skeletal joint position of the current body position. In response, the body pose verification system 126 displays a third indicator 824 (e.g., red) representing the area of ​​the first pose that overlaps with the contour texture. The body pose verification system 126 calculates how many pixels in the mask intersect with the contour texture and presents this information in region 850. The body pose verification system 126 calculates how many pixels in the mask are not covered or are outside the mask and presents this information in region 852. The body pose verification system 126 calculates the percentage of the mask that is covered or overlaps with the contour. The body pose verification system 126 compares this percentage with a threshold associated with a first mask. In response to determining that the percentage exceeds the threshold, the body pose verification system 126 verifies that the current body pose position in the received image or video matches a first target pose. In this case, the body pose verification system 126 indicates that the first target pose has been detected via an indicator 854.

[0115] In response to verification that a body pose matches a first target pose, body pose verification system 126 retrieves a second target pose corresponding to a second mask in the sequence. Body pose verification system 126 determines that the body pose represented by indicator 822 does not match the second target pose represented by indicator 832. In this case, body pose verification system 126 indicates via indicator 854 that no second target pose was detected. After detecting the first target pose, body pose verification system 126 receives a set of images representing a user in another target pose as shown in the second user interface 801. In these images, the body contour texture shows the user's arms outstretched and does not match either the second or first target pose. In this case, body pose verification system 126 indicates that neither the first nor the second target pose was detected.

[0116] Once the arm is lowered and the contour position is updated to overlap with the second target pose corresponding to the second mask by a predetermined threshold amount, the body pose verification system 126 detects or verifies that the body pose matches the second target pose in the sequence. In response, the body pose verification system 126 updates indicator 854 to indicate that the second target pose has been detected. In response to determining that the target pose sequence does not include any additional target poses (e.g., all target poses in the sequence have been detected in the input image in the corresponding sequence), the body pose verification system 126 performs the functions of the AR / VR application. For example, the body pose verification system 126 updates or increments the run counter 840 of the target pose sequence.

[0117] Machine architecture

[0118] Figure 9 This is a schematic representation of machine 900, in which instructions 908 (e.g., software, programs, applications, applets, or other executable code) can be executed to cause machine 900 to perform any one or more of the methods discussed herein. For example, instructions 908 can cause machine 900 to perform any one or more of the methods described herein. Instructions 908 transform the general, non-programmed machine 900 into a specific machine 900 programmed to perform the described and illustrated functions in the described manner. Machine 900 can operate as a standalone device or can be coupled (e.g., networked) to other machines. In a networked deployment, machine 900 can operate as a server machine or client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. Machine 900 may include, but is not limited to: server computers, client computers, personal computers (PCs), tablet computers, laptop computers, netbooks, set-top boxes (STBs), personal digital assistants (PDAs), entertainment media systems, cellular phones, smartphones, mobile devices, wearable devices (e.g., smartwatches), smart home devices (e.g., smart appliances), other smart devices, network devices, network routers, network switches, network bridges, or any machine capable of sequentially or otherwise executing instructions 908 specifying actions to be taken by machine 900. Furthermore, although only a single machine 900 is shown, the term "machine" should also be considered as a collection of machines that individually or jointly execute instructions 908 to perform any one or more of the methods discussed herein. For example, machine 900 may include client device 102 or any of several server devices forming part of message transceiver server system 108. In some examples, machine 900 may also include both client and server systems, wherein certain operations of a particular method or algorithm are performed on the server side, and wherein certain operations of a particular method or algorithm are performed on the client side.

[0119] Machine 900 may include a processor 902, a memory 904, and an input / output (I / O) unit 938 that can be configured to communicate with each other via a bus 940. In the example, processor 902 (e.g., a central processing unit (CPU), a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a graphics processing unit (GPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a radio frequency integrated circuit (RFIC), another processor, or any suitable combination thereof) may include, for example, processor 906 and processor 910 that execute instructions 908. The term "processor" is intended to include multi-core processors, which may include two or more independent processors (sometimes referred to as "cores") capable of executing instructions simultaneously. Although Figure 9 Multiple processors 902 are shown, but machine 900 may include a single processor with a single core, a single processor with multiple cores (e.g., a multi-core processor), multiple processors with a single core, multiple processors with multiple cores, or any combination thereof.

[0120] Memory 904 includes main memory 912, static memory 914, and memory cells 916, all of which are accessible by processor 902 via bus 940. Main memory 904, static memory 914, and memory cells 916 store instructions 908 that implement any one or more of the methods or functions described herein. Instructions 908 may also reside wholly or partially in main memory 912, in static memory 914, in machine-readable medium 918 within memory cells 916, in at least one of the processors 1802 (e.g., in the processor's cache memory), or in any suitable combination thereof during execution by machine 900.

[0121] I / O component 938 may include various components for receiving input, providing output, generating output, transmitting information, exchanging information, capturing measurement results, etc. The specific I / O component 938 included in a particular machine will depend on the type of machine. For example, a portable machine such as a mobile phone may include a touch input device or other such input mechanism, while a headless server machine may not include such a touch input device. It should be recognized that I / O component 938 may include... Figure 9Many other components are not shown. In various examples, I / O component 938 may include user output component 924 and user input component 926. User output component 924 may include visual components (e.g., displays such as plasma display panels (PDPs), light-emitting diode (LED) displays, liquid crystal displays (LCDs), projectors, or cathode ray tube (CRTs), acoustic components (e.g., speakers), haptic components (e.g., vibration motors, resistance mechanisms), other signal generators, etc. User input component 926 may include alphanumeric input components (e.g., keyboards, touchscreens configured to receive alphanumeric input, optical keyboards, or other alphanumeric input components), point-based input components (e.g., mice, touchpads, trackballs, joysticks, motion sensors, or other pointing instruments), haptic input components (e.g., physical buttons, touchscreens or other haptic input components that provide positioning and / or force for touch or touch gestures), audio input components (e.g., microphones), etc.

[0122] In another example, I / O component 938 may include: biometric component 928, motion component 930, environmental component 932, or positioning component 934, as well as a variety of other components. For example, biometric component 928 includes components for detecting expressions (e.g., hand expressions, facial expressions, voice expressions, body posture, or eye tracking), measuring biosignals (e.g., blood pressure, heart rate, body temperature, sweating, or brain waves), and identifying people (e.g., voice recognition, retinal recognition, facial recognition, fingerprint recognition, or EEG-based recognition). Motion component 930 includes accelerometer components (e.g., accelerometer), gravity sensor components, and rotation sensor components (e.g., gyroscope).

[0123] Environmental component 932 includes, for example: one or more camera devices (with still image / photograph and video capabilities), lighting sensor components (e.g., photometers), temperature sensor components (e.g., one or more thermometers for detecting ambient temperature), humidity sensor components, pressure sensor components (e.g., barometers), acoustic sensor components (e.g., one or more microphones for detecting background noise), proximity sensor components (e.g., infrared sensors for detecting nearby objects), gas sensors (e.g., gas detection sensors for detecting the concentration of hazardous gases or measuring pollutants in the atmosphere for safety purposes), or other components that can provide indications, measurements, or signals corresponding to the surrounding physical environment.

[0124] Regarding the camera device, client device 102 may have a camera device system including, for example, a front-facing camera on the front surface of client device 102 and a rear-facing camera on the rear surface of client device 102. The front-facing camera may be used, for example, to capture still images and videos (e.g., "selfies") of the user of client device 102, which can then be enhanced with the aforementioned enhancement data (e.g., filters). For example, the rear-facing camera may be used to capture still images and videos in a more conventional camera device mode, which are similarly enhanced with the enhancement data. In addition to the front and rear-facing cameras, client device 102 may also include a 360° camera for capturing 360° photos and videos.

[0125] Furthermore, the camera system of the client device 102 may include dual rear cameras (e.g., a main camera and a depth-sensing camera), or even include triple, quadruple, or quintuple rear camera configurations on the front and rear sides of the client device 102. For example, these multi-camera systems may include wide-angle cameras, ultra-wide-angle cameras, telephoto cameras, macro cameras, and depth sensors.

[0126] The position component 934 includes a positioning sensor component (e.g., a GPS receiver component), an altitude sensor component (e.g., an altimeter or barometer that detects air pressure and from which altitude can be obtained), an orientation sensor component (e.g., a magnetometer), etc.

[0127] Various technologies can be used to achieve communication. I / O component 938 also includes communication component 936, which is operable to couple machine 900 to network 920 or device 922 via appropriate coupling or connection. For example, communication component 936 may include a network interface component or other suitable device that interfaces with network 920. In further examples, communication component 936 may include wired communication component, wireless communication component, cellular communication component, near field communication (NFC) component, etc. Components (e.g.) (low power consumption) Components and other communication components that provide communication via other modes. Device 922 can be any peripheral device from another machine or various peripheral devices (e.g., a peripheral device coupled via USB).

[0128] Furthermore, the communication component 936 can detect identifiers, or include components operable to detect identifiers. For example, the communication component 936 may include a radio frequency identification (RFID) tag reader component, an NFC smart tag detection component, an optical reader component (e.g., an optical sensor for detecting one-dimensional barcodes such as Universal Product Code (UPC) barcodes, multi-dimensional barcodes such as Quick Response (QR) codes, Aztec codes, Data Matrix, Dataglyph, MaxiCode, PDF417, Ultra Code, UCC RSS-2D barcodes, and other optical codes), or an acoustic detection component (e.g., a microphone for identifying tagged audio signals). Additionally, various information can be obtained via the communication component 936, such as location via Internet Protocol (IP) geolocation, etc. Positioning methods include signal triangulation and NFC beacon signal detection, where the NFC beacon signal can indicate a specific location.

[0129] Various memories (e.g., main memory 912, static memory 914, and the memory of processor 902) and storage units 916 may store one or more sets of instructions and data structures (e.g., software) implemented or used by any one or more of the methods or functions described herein. When executed by processor 902, these instructions (e.g., instruction 908) enable various operations to implement the disclosed examples.

[0130] Instructions 908 can be sent or received over network 920 via a network interface device (e.g., a network interface component included in communication component 936), using a transmission medium and employing any of a plurality of known transmission protocols (e.g., Hypertext Transfer Protocol (HTTP)). Similarly, instructions 908 can be sent or received via a transmission medium coupled to device 922 (e.g., peer-to-peer coupling).

[0131] Software Architecture

[0132] Figure 10This is a block diagram 1000 illustrating a software architecture 1004 that can be installed on any one or more of the devices described herein. The software architecture 1004 is supported by hardware such as a machine 1002 including a processor 1020, memory 1026, and I / O components 1038. In this example, the software architecture 1004 can be conceptualized as a stack of layers, where each layer provides a specific function. The software architecture 1004 includes layers such as an operating system 1012, libraries 1010, frameworks 1008, and applications 1006. Operationally, application 1006 activates API calls 1050 via the software stack and receives messages 1052 in response to API calls 1050.

[0133] Operating system 1012 manages hardware resources and provides public services. Operating system 1012 includes, for example, a kernel 1014, services 1016, and drivers 1022. Kernel 1014 acts as an abstraction layer between the hardware layer and other software layers. For example, kernel 1014 provides memory management, processor management (e.g., scheduling), component management, networking and security settings, and other functions. Service 1016 can provide other public services to other software layers. Driver 1022 is responsible for controlling the underlying hardware or interfacing with the underlying hardware. For example, driver 1022 may include a display driver, a camera driver, etc. or Low-power drivers, flash drives, serial communication drivers (e.g., USB drives), Drivers, audio drivers, power management drivers, etc.

[0134] Library 1010 provides common low-level infrastructure used by application 1006. Library 1010 may include system library 1018 (e.g., the C standard library), which provides functions such as memory allocation, string manipulation, and mathematical functions. Furthermore, library 1010 may include API library 1024, such as media libraries (e.g., libraries for supporting the rendering and manipulation of various media formats, such as Moving Picture Experts Group 4 (MPEG4), Advanced Video Coding (H.264 or AVC), Moving Picture Experts Group Layer 3 (MP3), Advanced Audio Coding (AAC), Adaptive Multi-Rate (AMR) audio codec, Joint Picture Experts Group (JPEG or JPG) or Portable Web Graphics (PNG)), graphics libraries (e.g., the OpenGL framework for rendering graphic content on a display in two-dimensional (2D) and three-dimensional (3D) formats), database libraries (e.g., SQLite, which provides various relational database functions), web libraries (e.g., WebKit, which provides web browsing functionality), and so on. Library 1010 may also include various other libraries 1028 to provide many other APIs to application 1006.

[0135] Framework 1008 provides common high-level infrastructure for use by application 1006. For example, framework 1008 provides various graphical user interface (GUI) functions, advanced resource management, and advanced location services. Framework 1008 can provide a wide range of other APIs that can be used by application 1006, some of which may be specific to a particular operating system or platform.

[0136] In the example, application 1006 may include home application 1036, contact application 1030, browser application 1032, book reader application 1034, location application 1042, media application 1044, messaging application 1046, game application 1048, and a variety of other applications such as third-party application 1040. Application 1006 is a program that performs the functions defined in the program. One or more applications 1006 can be created using various programming languages, such as object-oriented programming languages ​​(e.g., Objective-C, Java, or C++) or procedural programming languages ​​(e.g., C or assembly language). In a particular example, third-party application 1040 (e.g., used by an entity other than the vendor of a particular platform using Android) TM or iOS TM Applications developed using a Software Development Kit (SDK) can be used on platforms such as iOS. TM ANDROID TM , Mobile software running on the phone's mobile operating system or another mobile operating system. In this example, a third-party application 1040 can activate API calls 1050 provided by the operating system 1012 to facilitate the functions described herein.

[0137] Glossary

[0138] "Carrier signal" refers to any intangible medium capable of storing, encoding, or carrying instructions to be executed by a machine, and includes digital or analog communication signals or other intangible media to facilitate the communication of such instructions. Instructions can be sent or received over a network using a transmission medium via a network interface device.

[0139] "Client device" refers to any machine that interfaces with a communication network to obtain resources from one or more server systems or other client devices. Client devices can be, but are not limited to, mobile phones, desktop computers, laptop computers, portable digital assistants (PDAs), smartphones, tablet computers, ultrabooks, netbooks, laptop computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, game consoles, set-top boxes, or any other communication device that a user can use to access the network.

[0140] "Communication network" refers to one or more parts of a network, which can be an ad hoc network, intranet, extranet, virtual private network (VPN), local area network (LAN), wireless LAN (WLAN), wide area network (WAN), wireless WAN (WWAN), metropolitan area network (MAN), the Internet, a part of the Internet, a part of the Public Switched Telephone Network (PSTN), a POTS (Plain Old-Style Telephone Service) network, a cellular telephone network, a wireless network, etc. A network, another type of network, or a combination of two or more such networks. For example, a network or part of a network may include a wireless network or a cellular network, and the coupling may be a Code Division Multiple Access (CDMA) connection, a Global System for Mobile Communications (GSM) connection, or other types of cellular or wireless coupling. In this example, the coupling can implement any data transmission technology of various types, such as Single Carrier Radio Transmission (1xRTT), Evolved Data Optimized (EVDO) technology, General Packet Radio Service (GPRS) technology, Enhanced Data Rate Evolution (EDGE) technology of GSM, the 3rd Generation Partnership Project (3GPP) including 3G, fourth-generation wireless (4G) networks, Universal Mobile Telecommunications System (UMTS), High-Speed ​​Packet Access (HSPA), Global Microwave Access Interoperability (WiMAX), Long Term Evolution (LTE) standards, other data transmission technologies defined by various standards setting organizations, other long-distance protocols, or other data transmission technologies.

[0141] A "component" is a device, physical entity, or logic having boundaries defined by function or subroutine calls, branch points, APIs, or other technologies provided for partitioning or modularizing specific processing or control functions. A component can be combined with other components via its interface to perform machine processes. A component can be an encapsulated functional hardware unit designed for use with other components and can be part of a program that typically performs a specific function within a related function. A component can constitute a software component (e.g., code implemented on a machine-readable medium) or a hardware component.

[0142] A “hardware component” is a tangible unit capable of performing certain operations and can be configured or arranged in some physical manner. In various example implementations, one or more computer systems (e.g., standalone computer systems, client computer systems, or server computer systems) or one or more hardware components (e.g., processors or processor groups) of a computer system can be configured by software (e.g., an application or application portion) to operate to perform certain operations as described herein. Hardware components can also be implemented mechanically, electronically, or in any suitable combination thereof. For example, a hardware component may include dedicated circuitry or logic permanently configured to perform certain operations. A hardware component may be a dedicated processor, such as a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). A hardware component may also include programmable logic or circuitry temporarily configured by software to perform certain operations. For example, a hardware component may include software executed by a general-purpose processor or other programmable processor. Once configured by such software, the hardware component becomes a specific machine (or a specific part of a machine) uniquely tailored to perform the configured function and is no longer a general-purpose processor.

[0143] It will be understood that the decision to implement hardware components mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., software-configured) can be driven by cost and time considerations. Accordingly, the phrase "hardware component" (or "hardware-implemented component") should be understood to include tangible entities, i.e., entities physically constructed, permanently configured (e.g., hardwired), or temporarily configured (e.g., programmed) to operate in a certain way or perform certain operations described herein. Considering the implementation where hardware components are temporarily configured (e.g., programmed), each of the hardware components does not need to be configured or instantiated at any given time. For example, in the case where the hardware components include a general-purpose processor that is configured by software to become a dedicated processor, the general-purpose processor can be configured as different dedicated processors (e.g., including different hardware components) at different times. Thus, the software configures one or more particular processors to constitute a particular hardware component at one time and different hardware components at different times. Hardware components can provide information to and receive information from other hardware components. Therefore, the described hardware components can be considered communicatively coupled. In the presence of multiple hardware components, communication can be achieved through signal transmission between or among two or more hardware components (e.g., via appropriate circuitry and buses). In embodiments where multiple hardware components are configured or instantiated at different times, such communication between hardware components can be achieved, for example, by storing information in a memory structure accessible to the multiple hardware components and retrieving information from that memory structure. For instance, one hardware component can perform an operation and store the output of that operation in a memory device communicatively coupled to it. Other hardware components can then access the memory device at a subsequent time to retrieve and process the stored output. Hardware components can also initiate communication with input or output devices and can operate on resources (e.g., information collection).

[0144] Various operations of the example methods described herein can be performed at least partially by one or more processors, which may be temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors can constitute components of a processor implementation that operate to perform one or more operations or functions described herein. As used herein, "processor-implemented component" refers to a hardware component implemented using one or more processors. Similarly, the methods described herein can be implemented at least partially by processors, where a particular processor or one or more processors are examples of hardware. For example, at least some operations of the methods can be performed by one or more processors 902 or processor-implemented components. Furthermore, one or more processors can also operate to support the execution of relevant operations in a "cloud computing" environment or as a "Software as a Service" (SaaS) operation. For example, at least some operations can be performed by a group of computers (as an example of a machine including processors), where these operations are accessible via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., APIs). The execution of certain operations can be distributed among processors, residing not only within a single machine but also deployed across several machines. In some example implementations, the processor or processor-implemented components may be located in a single geographic location (e.g., within a home environment, an office environment, or a server cluster). In other example implementations, the processor or processor-implemented components may be distributed across several geographic locations.

[0145] "Computer-readable storage medium" refers to both machine-readable storage media and transmission media. Therefore, the term includes both storage devices / media and carrier / modulated data signals. The terms "machine-readable medium," "computer-readable medium," and "apparatus-readable medium" refer to the same thing and may be used interchangeably in this disclosure.

[0146] A "brief message" is a message that is accessible for a limited time. Brief messages can be text, images, videos, etc. The access time for a brief message can be set by the message sender. Alternatively, the access time can be a default setting or a setting specified by the recipient. Regardless of the setting method, the message is temporary.

[0147] "Machine storage medium" refers to one or more storage devices and media (e.g., centralized or distributed databases, and associated caches and servers) that store executable instructions, routines, and data. Therefore, this term should be considered to include, but is not limited to, solid-state memory and optical and magnetic media, including memory internal or external to the processor. Specific examples of machine storage media, computer storage media, and device storage media include: non-volatile memory, including, for example, semiconductor memory devices such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), FPGAs, and flash memory devices; disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The terms "machine storage medium," "device storage medium," and "computer storage medium" refer to the same thing and are used interchangeably in this disclosure. The terms "machine storage medium," "computer storage medium," and "device storage medium" expressly exclude carrier waves, modulated data signals, and other such media, at least some of which are covered by the term "signal medium."

[0148] "Non-transitory computer-readable storage medium" refers to a tangible medium capable of storing, encoding, or carrying instructions that can be executed by a machine.

[0149] "Signal medium" means any intangible medium capable of storing, encoding, or carrying instructions executable by a machine, and includes digital or analog communication signals or other intangible media for the transmission of software or data. The term "signal medium" should be considered to include any form of modulated data signal, carrier wave, etc. The term "modulated data signal" refers to a signal in which one or more characteristics are set or altered in a manner that encodes information. The terms "transmission medium" and "signal medium" refer to the same thing and may be used interchangeably in this disclosure.

[0150] Changes and modifications may be made to the disclosed embodiments without departing from the scope of this disclosure. Such and other changes or modifications are intended to be included within the scope of this disclosure as set forth in the appended claims.

Claims

1. A method for pose verification, the method comprising: receiving, by one or more processors, a monocular image, the monocular image comprising a depiction of a body of a user in a given pose; detecting, by the one or more processors, a plurality of skeletal joints of the body depicted in the monocular image; generating an outline of the body of the user based on the plurality of skeletal joints by drawing lines connecting the plurality of skeletal joints; retrieving a mask representing a target pose, the mask being associated with a verification criterion, the verification criterion comprising a first threshold percentage of the given pose overlapping a first portion of the mask and a second threshold percentage of the given pose overlapping a second portion of the mask, the first threshold percentage being different from the second threshold percentage, such that each of the first and second portions of the mask is associated with a different verification criterion; and determining that the given pose of the body of the user matches the target pose by: computing a first percentage of a first portion of the mask overlapping a first set of pixels of a first portion of the outline of the body, the first portion of the outline of the body corresponding to a first portion of the lines connecting the plurality of skeletal joints; computing a second percentage of a second portion of the mask overlapping a second set of pixels of a second portion of the outline of the body, the second portion of the outline of the body corresponding to a second portion of the lines connecting the plurality of skeletal joints; and determining that the verification criterion is satisfied without obtaining a depth map of the body of the user depicted in the monocular image from a depth sensor by determining that the first percentage of the first portion of the mask overlapping the first set of pixels of the first portion of the outline of the body corresponds to the first threshold percentage and that the second percentage of the second portion of the mask overlapping the second set of pixels of the second portion of the outline of the body corresponds to the second threshold percentage.

2. The method of claim 1, further comprising: receiving a plurality of images from an image capture device; detecting a presence of the user in the plurality of images; and in response to detecting the presence of the user, initiating a process for determining that a pose of the user matches the target pose.

3. The method of claim 1, further comprising: computing a number of pixels of the lines connecting the plurality of skeletal joints that fall within the target pose in the mask.

4. The method of claim 1, further comprising: aligning a center of the mask with a center of the body of the user depicted in the monocular image.

5. The method of claim 1, wherein, detecting the plurality of skeletal joints of the body comprises identifying points respectively associated with a right wrist, a right elbow, a right shoulder, a nose on a face of the user, a left shoulder, a left elbow, and a left wrist.

6. The method of claim 1, further comprising: applying a black and white mask to the monocular image prior to detecting the plurality of skeletal joints.

7. The method of claim 1, wherein, the mask comprises a black portion and a white portion, wherein the white portion represents an outline corresponding to the target pose, and the method further comprises comparing the outline of the body depicted in the monocular image with the white portion of the mask.

8. The method of claim 1, further comprising: generating an image that combines the mask and the silhouette, wherein the image includes a first visual indicator of the silhouette, a second visual indicator of the target pose, and a third visual indicator of a portion of the silhouette that lies within the target pose.

9. The method of claim 1, wherein, the target pose includes a sequence of two or more poses, wherein the mask is a first mask that corresponds to a first pose of the two or more poses, wherein the monocular image includes a first monocular image and the silhouette includes a first silhouette, and wherein the given pose of the user is the first pose, the method further comprising: responsive to comparing the first silhouette to the first mask, determining that the first pose of the user's body matches the first pose of the two or more poses; receiving a second monocular image that includes a depiction of a second pose of the user's body; generating a second silhouette of the user's body based on a plurality of skeletal joints detected from the second monocular image; retrieving a second mask that represents a second pose of the two or more poses; comparing the second silhouette of the body depicted in the second monocular image to the second mask; and responsive to comparing the second silhouette of the body to the second mask, determining that the second pose of the user's body matches the second pose of the two or more poses.

10. The method of claim 9, further comprising: accumulating a number that represents how many times the first and second poses of the user's body match the sequence of two or more poses.

11. The method of claim 10, further comprising: receiving a video that includes a first portion and a second portion, wherein the first portion includes a first sequence of monocular images, the first sequence of monocular images including the first monocular image and a second monocular image, and wherein the second portion includes a second sequence of monocular images, the second sequence of monocular images including a set of monocular images that depict the user's body in the first and second poses; and incrementing a number that represents how many times the first and second poses of the user's body match the sequence of two or more poses each time a portion of the video is determined to include a sequence of monocular images that depict the user's body in the first and second poses.

12. The method of claim 1, further comprising: incrementing a number that represents how many times the first and second poses of the user's body match the sequence of two or more poses each time a portion of the video is determined to include a sequence of monocular images that depict the user's body in the first and second poses.

13. The method of claim 1, further comprising: adjusting a size of the mask based on skeletal tracking of the plurality of skeletal joints.

14. The method of claim 13, wherein, adjusting a size of the mask based on a calculated distance between a predetermined pair of skeletal joints of the plurality of skeletal joints.

15. The method of claim 1, further comprising: scaling a depiction of the user's body in the monocular image; and selecting a size of the mask based on the scaled depiction of the body.

16. A system for pose verification, the system comprising: ​ a processor configured to perform operations comprising: receiving a monocular image, the monocular image comprising a depiction of a body of a user in a given pose; detecting a plurality of skeletal joints of the body depicted in the monocular image; generating an outline of the body of the user based on the plurality of skeletal joints by drawing lines connecting the plurality of skeletal joints; retrieving a mask representing a target pose, the mask being associated with a verification criterion, the verification criterion comprising a first threshold percentage of the given pose overlapping a first portion of the mask and a second threshold percentage of the given pose overlapping a second portion of the mask, the first threshold percentage being different from the second threshold percentage, such that each of the first and second portions of the mask is associated with a different verification criterion; and determining that the given pose of the body of the user matches the target pose by: computing a first percentage of a first portion of the mask overlapping a first set of pixels of a first portion of the outline of the body, the first portion of the outline of the body corresponding to a first portion of the lines connecting the plurality of skeletal joints; computing a second percentage of a second portion of the mask overlapping a second set of pixels of a second portion of the outline of the body, the second portion of the outline of the body corresponding to a second portion of the lines connecting the plurality of skeletal joints; and determining that the verification criterion is satisfied by determining that the first percentage of the first portion of the mask overlapping the first set of pixels of the first portion of the outline of the body corresponds to the first threshold percentage and the second percentage of the second portion of the mask overlapping the second set of pixels of the second portion of the outline of the body corresponds to the second threshold percentage, without obtaining a depth map of the body of the user depicted in the monocular image from a depth sensor.

17. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising: receiving a monocular image, the monocular image comprising a depiction of a body of a user in a given pose; detecting a plurality of skeletal joints of the body depicted in the monocular image; generating an outline of the body of the user based on the plurality of skeletal joints by drawing lines connecting the plurality of skeletal joints; retrieving a mask representing a target pose, the mask being associated with a verification criterion, the verification criterion comprising a first threshold percentage of the given pose overlapping a first portion of the mask and a second threshold percentage of the given pose overlapping a second portion of the mask, the first threshold percentage being different from the second threshold percentage, such that each of the first and second portions of the mask is associated with a different verification criterion; and determining that the given pose of the body of the user matches the target pose by: computing a first percentage of a first portion of the mask overlapping a first set of pixels of a first portion of the outline of the body, the first portion of the outline of the body corresponding to a first portion of the lines connecting the plurality of skeletal joints; computing a second percentage of a second portion of the mask overlapping a second set of pixels of a second portion of the outline of the body, the second portion of the outline of the body corresponding to a second portion of the lines connecting the plurality of skeletal joints; and determining that the verification criterion is satisfied by determining that the first percentage of the first portion of the mask overlapping the first set of pixels of the first portion of the outline of the body corresponds to the first threshold percentage and the second percentage of the second portion of the mask overlapping the second set of pixels of the second portion of the outline of the body corresponds to the second threshold percentage, without obtaining a depth map of the body of the user depicted in the monocular image from a depth sensor. computing a second percentage of a second set of pixels of the second portion of the silhouette of the body overlapped by the second portion of the mask, the second portion of the silhouette of the body corresponding to a second portion of the lines connecting the plurality of skeletal joints; and determining that the verification criterion is satisfied by determining that the first percentage of the first set of pixels of the first portion of the silhouette of the body overlapped by the first portion of the mask corresponds to the first threshold percentage, and the second percentage of the second set of pixels of the second portion of the silhouette of the body overlapped by the second portion of the mask corresponds to the second threshold percentage, without obtaining a depth map of the body of the user depicted in the monocular image from a depth sensor.

Images