Systems and methods herein describe using a neural network to identify a first set of joint location coordinates and a second set of joint location coordinates and identifying a three-dimensional hand pose based on both the first and second sets of joint location coordinates.

Embodiments of the present invention provide a system for determining real-time resource capacity of entity devices based on performing predictive analysis. In particular, the system may be configured to identify one or more users at a location of an entity device waiting to perform one or more interactions via the entity device, establish a communication link with the entity device, determine identity of the one or more users based on communicating with the entity device, calculate an estimated interaction amount associated with the one or more interactions of the one or more users, determine capacity of the entity device in real-time, identify that the capacity of the entity device does not meet the calculated estimated interaction amount, and transmit a notification to at least one user of the one or more users via the entity application present on a user device of the at least one user.

The present disclosure describes techniques of improving video matting. The techniques comprise extracting features from each frame of a video by an encoder of a model, wherein the video comprises a plurality of frames; incorporating, by a decoder of the model, into any particular frame temporal information extracted from one or more frames previous to the particular frame, wherein the particular frame and the one or more previous frames are among the plurality of frames of the video, and the decoder is a recurrent decoder; and generating a representation of a foreground object included in the particular frame by the model, wherein the model is trained using segmentation dataset and matting dataset.

An electronic device and a method for tracking an object thereof are provided. The electronic device identifies whether there is a first object being tracked, when obtaining an image and rotation information of a camera of the electronic device, corrects state information of the first object using the rotation information, when there is the first object, detects a second object matched to the first object from the image based on the corrected state information, and tracks a position of the second object using an object tracking algorithm.

A structured 3D model of a real-world object is generated from a series of 2D photographs of the object, using photogrammetry, a keypoint detection deep learning network (DLN), and retopology. In addition, object parameters of the object are received. A pressure map of the object is then generated by a pressure estimation DLN based on the structured 3D model and the object parameters. The pressure estimation DLN was trained on structured 3D models, object parameters, and pressure maps of a plurality of objects belonging to a given object category. The pressure map of the real-world object can be used in downstream processes, such as custom manufacturing.

Provided are a body size estimation apparatus, a body size estimation method, and a program that enable the estimation of the body size of a user even when the user has not taken a T-pose in advance. A body size data storage unit (50) stores body size data indicating a body size of a user. A posture data acquisition unit (52) acquires position data indicating positions of a plurality of body parts away from each other of the user. A body size estimation unit (54) estimates a body size of the user based on positions of two or more body parts indicated by the position data. A body size update unit (56) updates, in a case where the estimated body size is larger than the body size indicated by the body size data stored in the body size data storage unit (50), the body size indicated by the body size data to the estimated body size.

A situationally aware surgical system configured for use during a surgical procedure performed on a patient by an operating clinician is disclosed including a surgical instrument configured to generate a signal and a cloud-based analytics subsystem including a memory and a control circuit. The memory is configured to store a plurality of baseline variables. The control circuit is configured to receive the signal, determine a type of surgical procedure being performed, at least in part, on the received signal, determine that a baseline variable of the plurality of baseline variables corresponds to the determined type of surgical procedure, determine a procedural variable of the surgical procedure based, at least in part, on the received signal, compare the determined procedural variable to the corresponding baseline variable, and generate an alert for the operating clinician based, at least in part, on the comparison.

Multiple cameras capture videos within a secure room. When individuals are detected as entering the room, identities of the individuals are resolved. When an asset is exposed in a field of view of one of the cameras, the individuals' eye and head movements are tracked from the videos with respect to one another and the asset. Additionally, touches made by any of the individuals on the asset are tracked from the videos. The eye and head movements are correlated with the touches or lack of touches according to a security policy for the asset. Any violations of the security policy are written to a secure audit log for the room and the asset.

An image processing apparatus includes obtaining distance information and subject information with respect to a captured image, specifying, based on the obtained distance information, a first subject region in which images of subjects that exist in a predetermined distance range are distributed in the captured image, specifying, based on the subject information and independently of the obtained distance information, specifying a second subject region that includes a region from which the predetermined subject has been detected in the captured image, and determining a target region for which the image processing is executed with reference to at least one of the first subject region and the second subject region. A subject region varies depending on at least one of an image capture condition of the captured image and a state of the captured image.

Systems, methods and computer readable media comprising a virtual exercise board, which is represented by images on the screen of a pad device; wearable devices configured to attach to each shoe of a user and to collect and transmit touch data to the pad device; cameras for tracking movement and calibrating with the data collected by the wearable devices; and computer programs for collecting user data, processing user data, and generating outputs. In embodiments, features include augmented reality; ratings of performance; automated workouts/protocols; real-time progress bar; multi-location database capabilities; and reports.