摘要:
Techniques for performing accurate and automatic head pose estimation are disclosed. According to one aspect of the techniques, head pose estimation is integrated with a scale-invariant head tracking method along with facial features detected from a located head in images. Thus the head pose estimation works efficiently even when there are large translational movements resulting from the head motion. Various computation techniques are used to optimize the process of estimation so that the head pose estimation can be applied to control one or more objects in a virtual environment and virtual character gaze control.
摘要:
Techniques for non-disruptive embedding of specialized elements are disclosed. In one aspect of the techniques, ontology is defined to specify an application domain. A program interface (API) is also provided for creating raw features by a developer. Thus a module is provided for at least one form of statistical analysis within the ontology. The module is configured automatically in a computing device with the API in response to a system consistent with the ontology, wherein the system has no substantial requirement for specialized knowledge of that form of statistical analysis, and the module has no substantial requirement for specialized knowledge of particular functions provided by the system.
摘要:
Techniques for motion recognition using multiple data streams are disclosed. Multiple data streams from inertia sensors as well as non-inertial sensors are received to derive a motion recognition signal from motion recognizers. These motion recognizers are originally constructed from a training set of motion signals and may be updated with received multiple sensing signals. In one aspect, multiple data streams are converted to device-independent motion signals that are applied with the motion recognizers to provide a generalized motion recognition capability.
摘要:
Techniques for controlling movements of an object in a videogame are disclosed. At least one video camera is used at a location where at least a player plays the videogame, the video camera captures various movements of the player. A designated device (e.g., a game console or computer) is configured to the video data to derive the movements of the player from the video data, and cause the object to respond to the movements of the player. When the designated device receives video data from more than one locations, players at the respective locations can play a networked videogame that may be built upon a shared space representing some or all of the real-world spaces of the locations. The video game is embedded with objects, some of which respond to the movements of the players and interact with other objects in accordance with rules of the video games.
摘要:
Techniques for creating a shared virtual space based on one or more real-world spaces are disclosed. Representations of the real-world spaces are combined in different ways to create a shared virtual game space within which each person's real-world movements are interpreted to create a shared feeling of physical proximity and physical interaction with other people on the network. One or more video cameras in one real-world area are provided to generate video data capturing the users as well as the environment of the users. The shared virtual space is created in reference to the respective real-world spaces that may be combined in various ways. Depending on a particular application, the shared virtual space will be embedded with various virtual objects and representative objects. Together with various rules and scoring mechanisms, such a shared virtual space may be used in a videogame that can be played by multiple players in a game space within which player's movements are interpreted to create a shared feeling of physical proximity and physical interaction with other players on the network.
摘要:
Techniques for performing motion recognition with minimum delay are disclosed. A processing unit is provided to receive motion signals from at least one motion sensing device, where the motion signal describes motions made by a user. The processing unit is configured to access a set of prototypes included in a motion recognizer to generate corresponding recognition signals from the motion signals in response to the motion recognizer without considering one or more of the prototypes completely in the motion recognizer. Movements of at least one of the objects in a virtual interactive environment is responsive to the recognition signals such that feedback from the motions to control the one of the objects is immediate and substantially correct no matter how much of the motion signals have been received.
摘要:
Techniques for interpreting orientation invariant motion are disclosed. Unlike a prior art controller (e.g., a WII game controller) that has a specific physical design to induce or force a user to grip the controller in a consistent way, a disclosed controller does not have such a physical design and allow a user to grip the controller in any way that is comfortable to the user (e.g., around an axis z), one or more transformation or rotations are designed to transform or rotate readings from inertial sensors housed in the controller to readings independent from how the controller is being gripped by a user.
摘要:
Techniques for using a variety of motion sensitive signals to remotely control an existing electronic device or system are described. Output signals from a motion sensitive device may be in a different form from those of a pre-defined controlling device. According to one aspect of the present invention, a controlled device is designed to respond to signals from a touch screen or touch screen-like signals. The output signals from a motion sensitive device include motion sensitive inputs to a controlled device and converted into touch-screen like signals that are coupled to the controlled device or programs being executed in the controlled device, subsequently causing the behavior of the controlled device to change or respond thereto, without reconfiguration of the applications running on the controlled device.