Abstract: A method of tracking a target includes receiving from a source a depth image of a scene including the human subject. The depth image includes a depth for each of a plurality of pixels. The method further includes identifying pixels of the depth image that belong to the human subject and deriving from the identified pixels of the depth image one or more machine readable data structures representing the human subject as a body model including a plurality of shapes.

Abstract: Embodiments are disclosed herein that relate to generating a decision tree through graphical processing unit (GPU) based machine learning. For example, one embodiment provides a method including, for each level of the decision tree: performing, at each GPU of the parallel processing pipeline, a feature test for a feature in a feature set on every example in an example set. The method further includes accumulating results of the feature tests in local memory blocks. The method further includes writing the accumulated results from each local memory block to global memory to generate a histogram of features for every node in the level, and for each node in the level, assigning a feature having a lowest entropy in accordance with the histograms to the node.

Abstract: A computerized decision tree training system may include a distributed control processing unit configured to receive input of training data for training a decision tree. The system may further include a plurality of data batch processing units, each data batch processing unit being configured to evaluate each of a plurality of split functions of a decision tree for respective data batch of the training data, to thereby compute a partial histogram for each split function, for each datum in the data batch. The system may further include a plurality of node batch processing units configured to aggregate the associated partial histograms for each split function to form an aggregated histogram for each split function for each of a subset of frontier tree nodes and to determine a selected split function for each frontier tree node by computing the split function that produces highest information gain for the frontier tree node.

Abstract: A method of tracking a target includes receiving an observed depth image of the target from a source and analyzing the observed depth image with a prior-trained collection of known poses to find an exemplar pose that represents an observed pose of the target. The method further includes rasterizing a model of the target into a synthesized depth image having a rasterized pose and adjusting the rasterized pose of the model into a model-fitting pose based, at least in part, on differences between the observed depth image and the synthesized depth image. Either the exemplar pose or the model-fitting pose is then selected to represent the target.

Abstract: A method of tracking a target includes receiving an observed depth image of the target from a source and analyzing the observed depth image with a prior-trained collection of known poses to find an exemplar pose that represents an observed pose of the target. The method further includes rasterizing a model of the target into a synthesized depth image having a rasterized pose and adjusting the rasterized pose of the model into a model-fitting pose based, at least in part, on differences between the observed depth image and the synthesized depth image. Either the exemplar pose or the model-fitting pose is then selected to represent the target.

Abstract: A method of tracking a target includes receiving from a source an observed depth image of a scene including the target. Each pixel of the observed depth image is labeled as either a foreground pixel belonging to the target or a background pixel not belonging to the target. Each foreground pixel is labeled with body part information indicating a likelihood that that foreground pixel belongs to one or more body parts of the target. The target is modeled with a skeleton including a plurality of skeletal points, each skeletal point including a three dimensional position derived from body part information of one or more foreground pixels.

Abstract: A method of tracking a target includes receiving an observed depth image of the target from a source and analyzing the observed depth image with a prior-trained collection of known poses to find an exemplar pose that represents an observed pose of the target. The method further includes rasterizing a model of the target into a synthesized depth image having a rasterized pose and adjusting the rasterized pose of the model into a model-fitting pose based, at least in part, on differences between the observed depth image and the synthesized depth image. Either the exemplar pose or the model-fitting pose is then selected to represent the target.

Abstract: Systems and methods for mapping natural input devices to legacy system inputs are disclosed. One example system may include a computing device having an algorithmic preprocessing module configured to receive input data containing a natural user input and to identify the natural user input in the input data. The computing device may further include a gesture module coupled to the algorithmic preprocessing module, the gesture module being configured to associate the natural user input to a gesture in a gesture library. The computing device may also include a mapping module to map the gesture to a legacy controller input, and to send the legacy controller input to a legacy system in response to the natural user input.

Abstract: A method and system to generate graphical user interface via a collection of application programming interfaces are provided. The application programming interfaces utilize views and models that define the elements and values associated with the graphical user interface. The views and models may be defined in different languages, are separately alterable, and may be communicatively connected with each other when generating visuals of the elements associated with the graphical user interface. The views and models related with a primary application may be utilized by a third-party application to extend the graphical user interface of the primary application.

Abstract: An exemplary computer-implementable method includes declaring a template for a user interface component in a markup language where the template specifies one or more parameters for the user interface component and declaring a parent template for a user interface assembly of components in the markup language where the parent template calls for consumption of the template for the user interface component and provides at least one value for the one or more parameters or optionally relies exclusively on a default value or default values for one or more parameters. Various other exemplary methods, devices, systems, etc., are also disclosed.

Abstract: Disclosed is a theme property sheet system that supports presentation themes by coordinating values provided to elements used in a user interface. When an interface user expresses a preference for a particular presentation theme, that theme's property sheet is given precedence over other mechanisms for setting property values. By appropriately setting these values in the interface, the theme property sheet enhances the coherence of the interface. The theme property sheet allows an interface designer to add new presentation elements to a user interface without being concerned about presentation themes. The default for each property as set by the designer is overridden, when necessary, by the theme sheet. In a few particular cases, an application designer needs to override even the user's theme preferences. A mechanism is provided to support these exceptional cases.

Abstract: A system and method for handling properties of objects is provided. More specifically, the system and method provide a dependency mechanism for expressing the relationship between the properties in a formal manner. This relationship may either be applied globally or locally. Using the dependency mechanism, the property system monitors relationships between properties and detects circularities between the different properties during runtime. The system and method also provide an evaluation mechanism for calculating a value for any of the properties. Because the property system is on-demand, the value need not be stored in local storage. The dependency mechanism and the evaluation mechanism are extensible, which allows the property system to model any type of relationship, such as a direct relationship, inheritance, reverse inheritance, property sheets, encapsulation, and the like.

Abstract: The application programming interfaces described herein are directed at property management mechanisms that operate within an on-demand property system. The property management mechanisms support the caching of property values on an as needed basis, allow a plurality of object instances to utilize the same property via attached properties, overriding default information associated with a property on a per type basis, obtaining values for a property from an external source, and the like. In addition, the on-demand property system provides validation and control for each property instance. The property management mechanisms minimize the storage requirements and provide flexibility without requiring additional code from the developers.

Abstract: The techniques and mechanisms described herein are directed at property management mechanisms that operate within an on-demand property system. The property management mechanisms support the caching of property values on an as needed basis, allow a plurality of object instances to utilize the same property via attached properties, overriding default information associated with a property on a per type basis, obtaining values for a property from an external source, and the like. In addition, the on-demand property system provides validation and control for each property instance. The property management mechanisms minimize the storage requirements and provide flexibility without requiring additional code from the developers.