HK1172984B - Living room movie creation - Google Patents

Description

Living room movie creation

Technical Field

The present invention relates to a technique of creating a movie, and more particularly, to a technique of creating a movie in an environment such as a living room.

Background

It has been some time for a user to be able to use a camcorder to produce a home movie. More recently, electronic devices such as cellular telephones may allow users to make short movies. However, these devices have limitations in the ability to create, administer, and edit movies. Also, the ability to produce any kind of animated movie can be very difficult for many people.

In the past, computing applications such as computer games and multimedia applications have used controllers, remote controls, keyboards, mice, etc. to allow a user to manipulate game characters or other aspects of the application. Some may even allow the user to create content to some extent. However, the ability to create content may be hidden behind a complex set of tools. Moreover, some technologies are primarily directed to role customization, and thus do not allow for richer development of content such as movies.

Disclosure of Invention

Systems and methods for providing living room movie creation are disclosed herein. Movies may be directed, captured, and edited using a system that includes a depth camera. The system can capture the motion of an actor using a depth camera and can generate a movie based thereon. Thus, there is no need for the actors to wear any special markers to detect their movements. A set of virtual movies may be generated based on common objects within the living room serving as virtual props. Other aspects related to practicing, capturing, and editing movies are disclosed herein.

One embodiment includes a method that may be implemented within a motion capture system having a depth camera. The method includes collecting depth information of an environment, such as a living room, using a depth camera. A model of the actor in the environment is generated and tracked based on the depth information. Scenes of the movie are generated based on tracking the model of the actor. The system creates a movie based on scenes in response to a user command.

One embodiment includes a system for creating a movie in an environment such as a living room. The system may include a depth camera, one or more processors coupled to the depth camera, and a computer storage medium coupled to the one or more processors. The computer storage medium has instructions stored thereon that, when executed on one or more processors, cause the one or more processors to collect depth information of an environment using a depth camera. The processor captures the motion of an actor in the environment using a depth camera using a markerless technique. A scene is generated by a processor based on the captured motion of the actor. The processor determines one or more locations of an electronic device in the environment to be used as a virtual viewfinder. These locations may be associated with the scene over a period of time. The processor generates a version of a scene from the perspective of the electronic device at one or more locations and provides the version of the scene to the electronic device.

One embodiment includes a method comprising the following. A depth camera is used to collect depth information of the environment and generate a model of the environment based on the depth information. A set of virtual movies is generated based on the depth information. Depth information is used to develop a skeletal model of the actor in the environment. The skeletal model is tracked over a period of time. A scene is generated based on the set of virtual movies and the tracking of the skeletal model. One or more locations of an electronic device to be used as a virtual viewfinder are determined for a period of time during which the skeletal model is tracked. A version of the scene is generated from an angle of the electronic device at each of the one or more locations and the version of the scene is provided to the electronic device. A request to record a scene is received from an electronic device. Metadata describing tracking of the skeletal model and one or more locations of the electronic device is stored for the time period.

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. Furthermore, the claimed subject matter is not limited to implementations that solve any or all disadvantages noted in any part of this disclosure.

Drawings

Fig. 1A illustrates an example embodiment of a target recognition, analysis, and tracking system for providing living room movie creation.

Fig. 1B illustrates an example embodiment of a target recognition, analysis, and tracking system for providing networked living room movie creation.

FIG. 2 illustrates an example embodiment of a capture device that may be used in a target recognition, analysis, and tracking system.

FIG. 3A illustrates an example embodiment of a computing environment that may be used to interpret one or more gestures in a target recognition, analysis, and tracking system.

FIG. 3B illustrates another example embodiment of a computing environment that may be used to interpret one or more gestures in a target recognition, analysis, and tracking system.

FIG. 4 illustrates a skeletal mapping of a user that has been generated from the target recognition, analysis, and tracking system of FIGS. 1A-2.

Fig. 5 is a high level flow chart of the operation of an embodiment of the current technology for providing living room movie creation.

FIG. 6 is a flow diagram of an embodiment of a process for incorporating virtual items into a movie.

Fig. 7 depicts a flow chart of a process of developing a model of an actor.

Fig. 8 is a flow diagram of one embodiment of a process for retargeting a model of an actor.

FIG. 9 is a flow diagram of one embodiment of a process for creating a movie.

FIG. 10 is a flow diagram of one embodiment of a process for viewing a scene at an electronic device.

FIG. 11 is a flow diagram of one embodiment of a process for capturing a scene from a filmed movie.

FIG. 12 is a flow diagram of one embodiment of a process for editing a movie.

Detailed Description

Systems and methods for providing living room movie creation are disclosed herein. Movies may be directed, captured, and edited using a system that includes a depth camera. A set of movies may be created by using common objects in the living room as virtual props. For example, a couch in a living room may be represented on a display screen as a rock in a virtual collection. A director of a movie may move objects around within the living room to create and modify a virtual collection in which scenes will be captured. The system may generate a 3D model of the room and determine what images should be presented for the virtual props. Virtual collections can also be created without using objects within the living room. For example, a virtual set of sand beach or spacecraft may be shown on the display screen. The director may modify this virtual set by, for example, "grabbing" the palm tree and moving it. The system can capture the motion of the actor using a depth camera and can generate a movie based thereon. Thus, there is no need for the actors to wear any special markers to detect their movements. To allow better freedom in the production of the movie, the actions of human actors may be retargeted to be non-human. For example, a human actor may be represented as an animal in a movie. The director may place the electronic device, which acts as a "virtual camera," in a vantage point where the scene is to be captured. The system may detect the location of the virtual camera and determine how to generate the scene from the vantage point. Note that the scene need not be recorded using a virtual camera. Instead, depth and/or RGB data from a depth camera may be used as a theme for the movie. Note that there may be multiple virtual cameras so that the director can view and capture the scene from multiple angles. The system may also be used to edit movies. As one example, a depth camera may be used to allow a user to enter commands to edit a movie.

Fig. 1A shows a system 10 for creating a movie in an environment such as a living room. System 10 may refer to a target recognition, analysis, and/or tracking system 10 that may be used to recognize, analyze, and/or track a human target such as user 18. In general, the system 10 includes a computing environment 12, a depth camera system 20, and a display 16. The depth camera system 20 may include a camera for determining depth information as well as an RGB camera. Note that the RGB camera may be a separate component from the depth camera system 20. The depth camera system 20 may be used to collect data on which the movie will be based.

In this example, user 18 is an actor in a movie being created. Thus, user 18 may also be referred to herein as an actor. The system 10 can use the depth camera 20 to capture the user's movements and can generate movies based thereon. Accordingly, a movie may be generated based on the depth information. Note that other data from an RGB camera, such as video data, may also be used to generate the movie. The display 16 depicts a scene 19 based at least in part on information captured by the depth camera system 20. Note that the term "scene" may refer to an action that occurs over a certain period of time. For example, a "scene" in a movie may refer to an action that occurs over a period of time. Scene 19 may have multiple frames of data presented sequentially.

In this example, actor 18 is retargeted to monster 17 in scene 19. System 10 may present monster 17 in a manner that mimics the actions of actor 18. By "retargeting" the actor, it is meant that scene 19 includes some element that is based on actor 18 but is modified or added in some way. In some embodiments of retargeting, system 10 develops a skeletal model of actor 18 based on the depth information and then maps the skeletal model to some non-human skeletal model. Features such as fur, eyes, clothing, etc. may then be overlaid on the non-human skeletal model.

The room may also have various objects that may be used as virtual items. In this example, the chair 13 in the environment is presented as a house 21 in a scene 19. It will be appreciated that the system 10 allows the creation of a "virtual movie collection" by allowing various real-world objects to be used as different kinds of props.

Thus, at least some of the elements in the scene 19 may be computer-created graphics. However, as mentioned above, the scene 19 may also be based on video data. For example, instead of retargeting actor 18, actual video data from an RGB camera may be used to represent actor 18 in scene 19. Other objects may also be represented in the scene 19 by the video data.

A director 11 and a photographer 15 are also depicted, each of them holding an electronic device 14 that can be used as a virtual camera. By a virtual camera, it is meant that the device 14 is not actually able to capture video, but is available to show the user how the scene 19 will appear from a vantage point of the electronic device 14. The system 10 may determine the location and orientation of the electronic device 14 being held by the director 11 so that it can determine how the scene 19 will appear from that perspective. The system 10 may then transmit a signal to the director's electronic device 14 so that the director 11 can view how the scene 19 will appear from the director's perspective. In this example, the director 11 may see the monster 17 in front of the house 21. Note that the director 11 can see that the scene is real-time. Thus, if actor 18 is moving his/her arm, director 11 may see monster 17 is moving its "arm". Note that the director 11 may move around the room to test how different camera angles will appear. Likewise, the system 10 may perform similar functions for the electronic device 14 of the camera person 15.

The electronic device 14 may be any electronic device 14, such as a cellular telephone, notebook computer, or the like. Generally, the electronic device 14 has some type of display screen for viewing the scene 19. Note that the electronic device 14 itself need not capture any video or the like, although this is one possibility. Instead, the data on which the scene 19 is generated may be collected from the depth camera system 20. The electronic device 14 may have one or more sensors that determine the location and orientation of the device 14 within the room.

In one embodiment, the director 11 or camera 15 may use an electronic device to capture the scene 19. In other words, the director 11 may decide to record the scene 19 from the selected camera angle. As one example, director 11 enters input on electronic device 14 that causes system 10 to both record metadata describing the movements of actors and to enter the location and orientation of electronic device 14. The metadata may then be used to edit the movie based on one or more recorded scenes 19.

Further details of one embodiment of the system 10 will now be discussed. Hardware for implementing the present technology includes a target recognition, analysis, and tracking system 10, which system 10 may be used to recognize, analyze, and/or track a human target such as a user 18. Various embodiments of the target recognition, analysis, and tracking system 10 include a computing environment 12 for executing games or other applications such as movie creation and editing. The computing environment 12 may include hardware components and/or software components such that the computing environment 12 may be used to execute gaming and non-gaming applications. In one embodiment, the computing environment 12 may include a processor, such as a standardized processor, a specialized processor, a microprocessor, or the like that may execute instructions stored on a processor readable storage device for performing the processes described herein.

The system 10 also includes a capture device 20, the capture device 20 for capturing image and audio data related to one or more users and/or objects sensed by the capture device. In embodiments, the capture device 20 may be used to capture information related to the movement, gestures, and voice of one or more users, which is received by the computing environment and used to create or edit a movie. Examples of the computing environment 12 and the capture device 20 are explained in more detail below.

Embodiments of the target recognition, analysis, and tracking system 10 may be connected to an audio/visual device 16 having a display. The device 16 may be, for example, a television, a monitor, a High Definition Television (HDTV), or the like that may provide game or application visuals and/or audio to a user. For example, the computing environment 12 may include a video adapter such as a graphics card and/or an audio adapter such as a sound card that may provide audio/visual signals associated with a game or other application. The audio/visual device 16 may receive the audio/visual signals from the computing environment 12 and may then output game or application visuals and/or audio associated with the audio/visual signals to the user 18. According to one embodiment, the audio/visual device 16 may be connected to the computing environment 12 via, for example, an S-video cable, a coaxial cable, an HDMI cable, a DVI cable, a VGA cable, a component video cable, or the like.

Suitable examples of the system 10 and its components are found in the following co-pending patent applications, which are all hereby incorporated by reference in their entirety: U.S. patent application serial No. 12/475,094 entitled "environmental and/or object segmentation" filed on 29.5.2009; U.S. patent application serial No. 12/511,850 entitled "automated generation a visual representation" filed on 29.7.2009; U.S. patent application serial No. 12/474,655 entitled "gestalto" filed on 29.5.2009; U.S. patent application serial No. 12/603,437 entitled "postrackingpipeline" filed on 21/10/2009; U.S. patent application serial No. 12/475,308 entitled "device for identifying and tracking multiple human devices over time" filed on 29.5.2009; U.S. patent application serial No. 12/575,388 entitled "human tracking system" filed on 7/10/2009; U.S. patent application serial No. 12/422,661 entitled "gesture recognizer system architecture" filed on 13.4.2009; U.S. patent application serial No. 12/391,150 entitled "standard getroots" filed on 23.2.2009; and U.S. patent application serial No. 12/474,655 entitled "gestural tool" filed on 29.5.2009.

The example of fig. 1A shows a system that is contained in a single environment, such as a living room. However, in some cases, different actors 18 may be at different physical locations. In one embodiment, the target recognition, analysis, and tracking system 10 is networked to the remote target recognition, analysis, and tracking system 10 to allow the actors 18 to be at different locations. FIG. 1B illustrates a system for creating a movie using a networked shooting environment. In this example, two target recognition, analysis, and tracking systems 10a, 10b are connected by a network 240. The network 240 may be a Wide Area Network (WAN) such as the internet. The network 240 may be (or include) a Local Area Network (LAN) such as IEEE1394 or bluetooth. Network 240 may actually be comprised of one or more networks.

Thus, one system 10a may monitor the actor 18 and collect motion data and/or depth information, which may be transmitted to the other system 10b over the network 240. The system 10a may also collect and transmit RGB data. System 10b may also monitor actor 18 and collect motion data as well as RGB data. The system 10b may generate a movie using motion data (and possibly RGB data) from any source based on editing commands from the user. This may allow separate scenes of the movie to be taken at separate locations. However, it may also be allowed to take the same scene at separate locations, where the data collected at two or more locations are merged to form a single scene. The merging of data may be performed by the system 10 in response to an edit command from a user.

FIG. 2 illustrates an example embodiment of a capture device 20 that may be used in the target recognition, analysis, and tracking system 10. In an example embodiment, the capture device 20 may be configured to capture video having a depth image that may include depth values via any suitable technique including, for example, time-of-flight, structured light, stereo image, or the like. According to one embodiment, the capture device 20 may organize the calculated depth information into "Z layers," or layers perpendicular to a Z axis extending from the depth camera along its line of sight.

As shown in FIG. 2, the capture device 20 may include an image camera component 22. According to one exemplary embodiment, the image camera component 22 may be a depth camera that may capture a depth image of a scene. The depth image may include a two-dimensional (2-D) pixel area of the captured scene where each pixel in the 2-D pixel area may represent a depth value, such as, for example, a length or distance in centimeters, millimeters, or the like of an object in the captured scene from the camera.

As shown in FIG. 2, according to an exemplary embodiment, the image camera component 22 may include an IR light component 24, a three-dimensional (3-D) camera 26, and an RGB camera 28 that may be used to capture a depth image of a scene. For example, in time-of-flight analysis, the IR light component 24 of the capture device 20 may emit an infrared light onto the scene and may then detect the backscattered light from the surface of one or more targets and objects in the scene using sensors (not shown), for example, with the 3-D camera 26 and/or the RGB camera 28.

In some embodiments, pulsed infrared light may be used such that the time between an outgoing light pulse and a corresponding incoming light pulse may be measured and used to determine a physical distance from the capture device 20 to a particular location on a target or object in the scene. Additionally, in other exemplary embodiments, the phase of the outgoing light wave may be compared to the phase of the incoming light wave to determine the phase shift. This phase shift may then be used to determine a physical distance from the capture device 20 to a particular location on the targets or objects.

According to another exemplary embodiment, time-of-flight analysis may be used to indirectly determine a physical distance from the capture device 20 to a particular location on the targets or objects by analyzing the intensity of the reflected beam of light over time via various techniques including, for example, shuttered light pulse imaging.

In another exemplary embodiment, the capture device 20 may use a structured light to capture depth information. In such an analysis, patterned light (i.e., light displayed as a known pattern such as a grid pattern or a stripe pattern) may be projected onto the scene via, for example, the IR light component 24. Upon falling onto the surface of one or more targets or objects in the scene, the pattern may become distorted in response. Such a deformation of the pattern may be captured by, for example, the 3-D camera 26 and/or the RGB camera 28, and may then be analyzed to determine a physical distance from the capture device 20 to a particular location on the targets or objects.

According to another embodiment, the capture device 20 may include two or more physically separated cameras that may view a scene from different angles to obtain visual stereo data that may be resolved to generate depth information. In another example embodiment, the capture device 20 may use point cloud data (pointclouddata) and target digitization techniques to detect features of the user.

The capture device 20 may also include one or more microphones 30. The microphone 30 may include a transducer or sensor that may receive sound and convert it into an electrical signal. According to one embodiment, the microphone 30 may be used to reduce feedback between the capture device 20 and the computing environment 12 in the target recognition, analysis, and tracking system 10. Additionally, the microphone 30 may be used to receive audio signals that may also be provided by the user to control applications such as gaming applications, non-gaming applications, etc., that may be executed by the computing environment 12.

In an exemplary embodiment, the capture device 20 may also include a processor 32 that may be in operative communication with the image camera component 22. Processor 32 may include a standard processor, a special purpose processor, a microprocessor, etc. that may execute instructions, which may include instructions for receiving a depth image, determining whether a suitable target may be included in a depth image, converting a suitable target into a skeletal representation or model of the target, or any other suitable instructions.

The capture device 20 may also include a memory component 34, where the memory component 34 may store instructions executable by the processor 32, images or frames of images captured by the 3-D camera or RGB camera, or any other suitable information, images, or the like. According to an example embodiment, the memory component 34 may include Random Access Memory (RAM), Read Only Memory (ROM), cache, flash memory, a hard disk, or any other suitable storage component. As shown in FIG. 2, in one embodiment, the memory component 34 may be a separate component in communication with the image camera component 22 and the processor 32. According to another embodiment, the memory component 34 may be integrated into the processor 32 and/or the image camera component 22. In one embodiment, rather than having a processor 32, the capture device 20 has an Application Specific Integrated Circuit (ASIC) for processing information from the light sensor.

As shown in FIG. 2, the capture device 20 may communicate with the computing environment 12 via a communication link 36. The communication link 36 may be a wired connection including, for example, a USB connection, a firewire connection, an ethernet cable connection, etc., and/or a wireless connection such as a wireless 802.11b, 802.11g, 802.11a, or 802.11n connection, etc. According to one embodiment, the computing environment 12 may provide a clock to the capture device 20 via the communication link 36 that may be used to determine when to capture, for example, a scene.

Additionally, the capture device 20 may provide the depth information and images captured by, for example, the 3-D camera 26 and/or the RGB camera 28, as well as a skeletal model that may be generated by the capture device 20 to the computing environment 12 via the communication link 36. Various known techniques exist for determining whether a target or object detected by capture device 20 corresponds to a human target. Skeletal mapping techniques may thus be used to determine various points on the user's skeleton, joints of the hands, wrists, elbows, knees, nose, ankles, shoulders, and where the pelvis meets the spine. Other techniques include: transforming the image into a mannequin representation of the person and transforming the image into a mesh model representation of the person.

The skeletal model may then be provided to the computing environment 12 so that the computing environment may perform various actions. In some embodiments, retargeting is performed such that actors are presented in a manner that is different from their actual appearance. In some embodiments, system 10 determines those controls to be performed in an application executing on the computer environment based on, for example, gestures of the user that have been recognized from the skeletal model. For example, as shown in FIG. 2, the computing environment 12 may include a gesture recognition engine 190 for determining when a user has performed a predefined gesture. Also shown is a movie editing engine 192 that allows a user to enter commands through natural input (e.g., voice commands and/or gestures).

FIG. 3A illustrates an example embodiment of a computing environment that may be used to create and edit movies, among other purposes. The computing environment may be used for the computing environment 12 of FIG. 1A, FIG. 1B, or FIG. 2. The computing environment of FIG. 3A is a multimedia console 100, which may be used for gaming applications. As shown in FIG. 3A, the multimedia console 100 includes a Central Processing Unit (CPU)101 having a level one cache 102, a level two cache 104, and a flash ROM 106. The level one cache 102 and the level two cache 104 temporarily store data and thus reduce the number of memory access cycles, thereby improving processing speed and throughput. The CPU101 may be provided with more than one core and thus with additional level one caches 102 and level two caches 104. The flash ROM106 may store executable code that is loaded during an initial phase of a boot process when the multimedia console 100 is powered ON.

A Graphics Processing Unit (GPU)108 and a video encoder/video codec (coder/decoder) 114 form a video processing pipeline for high speed and high resolution graphics processing. Data is carried from the GPU108 to the video encoder/video codec 114 via a bus. The video processing pipeline outputs data to an a/V (audio/video) port 140 for transmission to a television or other display. A memory controller 110 is connected to the GPU108 to facilitate processor access to various types of memory 112, such as, but not limited to, RAM.

The multimedia console 100 includes an I/O controller 122, a system management controller 123, an audio processing unit 124, a network interface controller 126, a first USB host controller 128, a second USB host controller 130, and a front panel I/O subassembly 330 that are preferably implemented on a module 120. The USB controllers 126 and 128 serve as hosts for optional peripheral controllers 142(1) - (142) (2), a wireless adapter 148, and an external memory device 146 (e.g., flash memory, external CD/DVDROM drive, removable media, etc.). The network interface 124 and/or wireless adapter 148 provide access to a network (e.g., the Internet, home network, etc.) and may be any of a wide variety of various wired or wireless adapter components including an Ethernet card, a modem, a Bluetooth module, a cable modem, and the like.

System memory 143 is provided to store application data that is loaded during the boot process. A media drive 144 is provided and may comprise a DVD/CD drive, hard drive, or other removable media drive, among others. The media drive 144 may be internal or external to the multimedia controller 100. Application data may be accessed via the media drive 144 for execution, playback, etc. by the multimedia console 100. The media drive 144 is connected to the I/O controller 120 via a bus, such as a Serial ATA bus or other high speed connection (e.g., IEEE 1394).

The system management controller 122 provides various service functions related to ensuring availability of the multimedia console 100. The audio processing unit 123 and the audio codec 132 form a corresponding audio processing pipeline with high fidelity and stereo processing. Audio data is transmitted between the audio processing unit 123 and the audio codec 132 via a communication link. The audio processing pipeline outputs data to the A/V port 140 for reproduction by an external audio player or device having audio capabilities.

The front panel I/O subassembly 130 supports the functionality of the power button 150 and the eject button 152, as well as any LEDs (light emitting diodes) or other indicators exposed on the outer surface of the multimedia console 100. The system power supply module 136 provides power to the components of the multimedia console 100. A fan 138 cools the circuitry within the multimedia console 100.

The CPU101, GPU108, memory controller 110, and various other components within the multimedia console 100 are interconnected via one or more buses, including serial and parallel buses, a memory bus, a peripheral bus, and a processor or local bus using any of a variety of bus architectures. By way of example, these architectures may include a Peripheral Component Interconnect (PCI) bus, a PCI-Express bus, and the like.

When the multimedia console 100 is powered ON, application data may be loaded from the system memory 143 into memory 112 and/or caches 102, 104, and executed on the CPU 101. The application may present a graphical user interface that provides a consistent user experience when navigating to different media types available on the multimedia console 100. In operation, applications and/or other media contained within the media drive 144 may be launched or played from the media drive 144 to provide additional functionalities to the multimedia console 100.

The multimedia console 100 may be operated as a standalone system by simply connecting the system to a television or other display. In the standalone mode, the multimedia console 100 allows one or more users to interact with the system, watch movies, or listen to music. However, with the integration of broadband connectivity made available through the network interface 124 or the wireless adapter 148, the multimedia console 100 may further be operated as a participant in a larger network community.

When the multimedia console 100 is powered on, a set amount of hardware resources may be reserved for system use by the multimedia console operating system. These resources may include a reserve of memory (such as 16MB), a reserve of CPU and GPU cycles (such as 5%), a reserve of network bandwidth (such as 8kbs), and so on. Because these resources are reserved at system boot time, the reserved resources are not present from an application perspective.

In particular, the memory reservation is preferably large enough to contain the launch kernel, concurrent system applications and drivers. The CPU reservation is preferably constant such that if the reserved CPU usage is not used by the system applications, the idle thread will consume any unused cycles.

With regard to the GPU reservation, lightweight messages generated by system applications (e.g., popups) are displayed by using a GPU interrupt to schedule code to render popup into an overlay. The amount of memory required for the overlay depends on the overlay area size, and the overlay preferably scales with the screen resolution. Where a complete user interface is used by a concurrent system application, it is preferable to use a resolution that is independent of the application resolution. A scaler may be used to set this resolution so that there is no need to change the frequency and cause a TV resynch.

After the multimedia console 100 boots and system resources are reserved, concurrent system applications execute to provide system functionality. The system functions are encapsulated in a set of system applications that execute within the reserved system resources described above. The operating system kernel identifies threads that are either system application threads or game application threads. The system applications are preferably scheduled to run on the CPU101 at predetermined times and intervals in order to provide a consistent view of system resources to the application. The scheduling is to minimize cache disruption for the gaming application running on the console.

When the concurrent system application requires audio, audio processing is asynchronously scheduled to the gaming application due to time sensitivity. A multimedia console application manager (described below) controls the audio level (e.g., mute, attenuate) of the gaming application while system applications are active.

The input devices (e.g., controllers 142(1) and 142(2)) are shared by the gaming application and the system application. Rather than reserving resources, the input devices are switched between the system application and the gaming application so that each has a focus of the device. The application manager preferably controls the switching of input stream without knowledge of the gaming application's knowledge, and the driver maintains state information regarding focus switches. The cameras 26, 28 and capture device 20 may define additional input devices for the console 100.

FIG. 3B illustrates another example embodiment of a computing environment 220 that may be the computing environment 12 illustrated in FIGS. 1A-2. The computing system environment 220 is only one example of a suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality of the presently disclosed subject matter. Neither should the computing environment 220 be interpreted as having any dependency or requirement relating to any one or combination of components illustrated in the exemplary operating environment 220. In some embodiments, each illustrated computing element may include circuitry configured to instantiate certain aspects of the present disclosure. For example, the term circuitry used in this disclosure may include dedicated hardware components configured to perform functions through firmware or switches. In other example embodiments, the term "circuitry" may include a general purpose processing unit, memory, etc., configured by software instructions embodying logic operable to perform functions. In example embodiments where circuitry includes a combination of hardware and software, an implementer may write source code embodying logic and the source code can be compiled into machine readable code that can be processed by the general purpose processing unit.

In FIG. 3B, the computing environment 220 includes a computer 241, the computer 241 typically including a variety of computer-readable media. A computer 241 may be connected to the depth camera system 20 to receive, for example, skeletal data and other metadata from which movies may be created and edited.

Computer readable media can be any available media that can be accessed by computer 241 and includes both volatile and nonvolatile media, removable and non-removable media. The system memory 222 includes computer storage media in the form of volatile and/or nonvolatile memory such as ROM223 and RAM 260. A basic input/output system 224(BIOS), containing the basic routines that help to transfer information between elements within computer 241, such as during start-up, is typically stored in ROM 223. RAM260 typically contains data and/or program modules that are immediately accessible to and/or presently being operated on by processing unit 259. By way of example, and not limitation, FIG. 3B illustrates operating system 225, application programs 226, other program modules 227, and program data 228. One example of an application program 226 is a story application 226 for presenting an interactive story experience as explained herein to a user. Fig. 3B also includes a Graphics Processor Unit (GPU)229, the graphics processor unit 229 having an associated video memory 230 for high speed and high resolution graphics processing and storage. The GPU229 may be connected to the system bus 221 through a graphics interface 231.

The computer 241 may also include other removable/non-removable, volatile/nonvolatile computer storage media. By way of example only, FIG. 3B illustrates a hard disk drive 238 that reads from or writes to non-removable, nonvolatile magnetic media, a magnetic disk drive 239 that reads from or writes to a removable, nonvolatile magnetic disk 254, and an optical disk drive 240 that reads from or writes to a removable, nonvolatile optical disk 253 such as a CDROM or other optical media. Other removable/non-removable, volatile/nonvolatile computer storage media that can be used in the exemplary operating environment include, but are not limited to, magnetic tape cassettes, flash memory cards, digital versatile disks, digital video tape, solid state RAM, solid state ROM, and the like. The hard disk drive 238 is typically connected to the system bus 221 through a non-removable memory interface such as interface 234, and magnetic disk drive 239 and optical disk drive 240 are typically connected to the system bus 221 by a removable memory interface, such as interface 235.

The drives and their associated computer storage media discussed above and illustrated in FIG. 3B, provide storage of computer readable instructions, data structures, program modules and other data for the computer 241. In FIG. 3B, for example, hard disk drive 238 is illustrated as storing operating system 258, application programs 257, other program modules 256, and program data 255. Note that these components can either be the same as or different from operating system 225, application programs 226, other program modules 227, and program data 228. Operating system 258, application programs 257, other program modules 256, and program data 255 are given different numbers here to illustrate that, at a minimum, they are different copies. A user may enter commands and information into the computer 241 through input devices such as a keyboard 251 and pointing device 252, commonly referred to as a mouse, trackball or touch pad. Other input devices (not shown) may include a microphone, joystick, game pad, satellite dish, scanner, or the like. These and other input devices are often connected to the processing unit 259 through a user input interface 236 that is coupled to the system bus, but may be connected by other interface and bus structures, such as a parallel port, game port or a Universal Serial Bus (USB). The cameras 26, 28 and capture device 20 may define additional input devices for the console 100. A monitor 242 or other type of display device is also connected to the system bus 221 via an interface, such as a video interface 232. In addition to the monitor, computers may also include other peripheral output devices such as speakers 244 and printer 243, which may be connected through an output peripheral interface 233.

The computer 241 may operate in a networked environment using logical connections to one or more remote computers, such as a remote computer 246. The remote computer 246 may be a personal computer, a server, a router, a network PC, a peer device or other common network node, and typically includes many or all of the elements described above relative to the computer 241, although only a memory storage device 247 has been illustrated in fig. 3B. The logical connections depicted in FIG. 3B include a Local Area Network (LAN)245 and a Wide Area Network (WAN)249, but may also include other networks. Such networking environments are commonplace in offices, enterprise-wide computer networks, intranets and the Internet.

When used in a LAN networking environment, the computer 241 is connected to the LAN 245 through a network interface or adapter 237. When used in a WAN networking environment, the computer 241 typically includes a modem 250 or other means for establishing communications over the WAN249, such as the Internet. The modem 250, which may be internal or external, may be connected to the system bus 221 via the user input interface 236, or other appropriate mechanism. In a networked environment, program modules depicted relative to the computer 241, or portions thereof, may be stored in the remote memory storage device. By way of example, and not limitation, FIG. 3B illustrates remote application programs 248 as residing on memory device 247. It will be appreciated that the network connections shown are exemplary and other means of establishing a communications link between the computers may be used.

FIG. 4 depicts an example skeletal mapping of a user that may be generated from the capture device 20. In this embodiment, the individual joints and bones are identified: each hand 302, each forearm 304, each elbow 306, each upper arm 308, each shoulder 310, each hip 312, each upper leg 314, each knee 316, each lower leg 318, each foot 320, the head 322, the torso 324, the top 326 and bottom 328 of the spine, and the waist 330. Where more points are tracked, additional features may be identified, such as the bones and joints of the fingers or toes, or individual features of the face, such as the nose and eyes.

FIG. 5 is a high-level flow diagram of the operation of one embodiment of a process 500 for providing movie creation. Process 500 may be performed by system 10 or another system. For purposes of illustration, reference will be made to the example system 10 of fig. 1A, 1B, and 2, but the process 500 is not limited to this example. At step 502, depth information of an environment is collected using a depth camera. For example, depth information is collected using the depth camera system 20. This information may be collected over time as process 500 may be used for the creation of a movie. For purposes of discussion, data collection occurs over a certain "period of time" in step 502. Note that step 504-508 occurs over the same time period. In one embodiment, the system 10 maintains a 3D model of the room based on the depth information. In some embodiments, step 502 includes collecting RGB data. For example, the RGB camera 28 may be used to collect video data that may be used in movies. As an example, the video data may be an MPEG stream.

The depth information may be downsampled to a lower processing resolution so that it may be more easily used and processed with less computational overhead. Additionally, one or more highly variable and/or noisy depth values may be removed and/or smoothed from the depth information; portions of missing and/or removed depth information may be filled in and/or reconstructed; and/or any other suitable processing may be performed on the received depth information such that the depth information may be used to generate a model, such as a skeletal model.

In step 504, a model of the actor 18 in the environment is developed based on the depth information. In one embodiment, the model is a skeletal model. Note that the model can be developed without requiring the actor to wear any special markers. This model may be stored for later use.

In step 506, the depth information is used to track a model of the actor. Such as, for example, the tracking may occur over a "time period" referred to in step 502. Further details of tracking the model of the actor are discussed below.

In step 508, a scene is generated based at least on tracking of the model of the actor. Note that a "scene" may include multiple frames of data. For example, a scene may include 30 frames of data per second. The scene may be based on information other than tracking of the skeletal model. In some embodiments, objects within a room are used as virtual props for a scene. For example, referring to fig. 1A, chair 13 is presented as a house 21 and actor 18 is presented as a monster 17. In this example, chair 13 is used as a virtual prop. Further details of working with virtual props are discussed below. In this example, actor 18 is retargeted. Further details of retargeting actor 18 are discussed below. Such as retargeting actor 18 is not necessary. Video data from the RGB camera 28 may be used in the scene. Thus, scenes may be generated from computer generated graphics, video data, or a combination thereof.

In step 510, the system 10 creates a movie based at least on the scene in response to a user command. The creation of the movie includes allowing the user to practice, capture, and edit the movie. In some embodiments, a version of the scene is provided to an electronic device held by the director 11 or other person. The version may come from the perspective of the electronic device 14. Thus, the electronic device 14 may function as a "virtual viewfinder". In some embodiments, step 510 includes capturing a scene in response to a request from the electronic device 14. For example, the director 11 may make a selection on the electronic device 14 such that the electronic device 14 instructs the system 10 that a scene should be recorded. In some embodiments, step 508 includes allowing the user to edit the movie using system 10. Further details allowing the user to practice, capture, and edit the movie are discussed below.

FIG. 6 is a flow diagram of one embodiment of a process 600 for incorporating virtual items into a movie. In general, the process 600 allows the director 11 to use certain objects as items in a movie. Process 600 is one technique that may be used in generating a scene. Accordingly, process 600 provides more details of one embodiment of step 508 of process 500. In step 602, the system 10 receives a request from a director 11 or other user to use an object in an environment as a prop. In one embodiment, this includes the system 10 taking a "still picture" of the room and displaying the still picture on the display 16. Thus, initially the user may see an object such as the chair 13 on the display 16. If desired, the user may cause the system to "retargete" the chair 13 so that the chair is represented as some other object. The system 10 may have a library of possible objects for the user to select from. After the user selects the "virtual object," the system 10 may then display the virtual object on a display for viewing by the user. The user may then be able to modify the virtual item by, for example, modifying an attribute such as size, color, shape, and the like. The system 10 then stores this information when linking an object in the real world to it so that the system 10 can track the location of the object if the user moves the real world object. Note that step 602 may occur during initial setup prior to process 500.

Some time may elapse after the initial setup phase of step 602. In step 604, while "filming" the scene, system 10 determines a 3D model of the environment based on the depth information collected from the depth camera in process 500. In step 606, the system 10 determines the location (or locations) of the real world object in the 3D model. Since the object may move during the shot, the system 10 may track the object.

At step 608, the system incorporates the virtual item in the movie based on the location of the real-world object. Referring to the example of FIG. 1, the system 10 may incorporate a house 21 into a scene 19 on a display 16.

In one embodiment, a virtual collection is created without, at least in part, using objects within the living room. For example, a user may wish to have a movie with a beach background. The system 10 may create a set of beaches without relying on any object within the living room. System 10 may display this set on any of the various display screens (e.g., display 16, a display on electronic device 14, etc.). In one embodiment, this is a computer-generated scenario. The director 11 may modify the virtual collection by, for example, "grabbing" the virtual item and moving it. For example, the director 11 may point at a palm tree on the display 16. The system 10 may use a depth camera to determine what the director is pointing at. The virtual items may be highlighted on the display, but this is not required. The director 11 may then take a catch action and move the virtual prop. Likewise, the system may use a depth camera to track the director's movements to determine where the virtual items are to be moved. Fig. 7 depicts a flow diagram of a process 700 for developing and tracking a model of actor 18. The process 700 is one embodiment of step 504-506 of the process 500. The example method may be implemented using, for example, the depth camera system 20. Actor 18 may be scanned to generate a model such as a skeletal model, a mesh human model, or any other suitable representation of a human. At step 702, depth information (e.g., a depth image) is accessed. This may be depth information from step 502 or process 500. The depth image may be a matrix of depth values. Each element of the matrix may represent a region of the environment. The depth value may define a distance from the depth camera 20 to an object in the region. The elements in the matrix may be referred to as pixels.

At decision step 704, it is determined whether the depth image includes a human target. This may include flood filling each target or object in the depth image, comparing the target or object to the pattern to determine whether the depth image includes a human target. For example, various depth values of pixels in a selected area or point of the depth image may be compared as described above to determine an edge that may define a target or object. The possible Z values for the Z layer may be flood filled based on the determined edges. For example, pixels associated with the determined edge and pixels of the area within the edge may be associated with each other to define a target or object in the capture area that may be compared to the pattern, as will be described in more detail below.

If decision step 704 is true, then step 706 is performed. If decision step 704 is false, additional depth information is accessed at step 702.

The pattern with which each target or object is compared may include one or more data structures having a set of variables that collectively define a typical body of the person. Information associated with, for example, pixels of a human target and a non-human target within a field of view, may be compared to a variable to identify the human target. In one embodiment, each variable in the set may be weighted based on body part. For example, various body parts in the pattern, such as the head and/or shoulders, may have weight values associated therewith, which may be greater than weight values of other body parts, such as the legs. According to one embodiment, weight values may be used when comparing targets to variables to determine whether and which targets are likely to be human. For example, a match between a variable and a target with a larger weight value may yield a greater likelihood that the target is a human than a match with a smaller weight value.

Step 706 includes scanning the human target for body parts. The human target may be scanned to provide measurements such as length, width, etc. associated with one or more body parts of the person to provide an accurate model of the person. In an example embodiment, a human target may be isolated and a bitmask of the human target may be created to scan for one or more body parts. The bitmask may be created by, for example, flood filling the human target so that the human target may be separated from other targets or objects in the capture area elements. The bitmask may then be analyzed for one or more body parts to generate a model of the human target, such as a skeletal model, a mesh human model, and so forth.

Step 708 includes generating a model of the human target. In one embodiment, measurements determined from a scanned bitmask may be used to define one or more joints in a skeletal model. One or more joints are used to define one or more bones corresponding to a body part of a human. In general, each body part may be characterized as a mathematical vector defining the joints and bones of the skeletal model. The body parts are movable relative to each other at the joints. The model may include information describing the rotation of the user's head so that the orientation of the user's ear is known.

In step 710, the model is tracked by updating the position of the person multiple times per second. As the user moves in physical space, information from the depth camera system is used to adjust the skeletal model so that the skeletal model represents a person. Optionally, user 18 may wear inertial sensors; however, an inertial sensor is not required. If inertial sensors are used, the data from the inertial sensors may also be used to track the user. In particular, one or more forces may be applied to one or more force-receiving aspects of the skeletal model to adjust the pose of the skeletal model to more closely correspond to the pose of the human target in physical space. In general, any known technique for tracking the motion of one or more persons may be used.

Note that process 700 may be used more than once to generate a single scene. In this manner, a scene may be constructed on a multiple pass basis, with the actor 18 playing a different role with each pass. For example, process 700 may be used to track users 18 over various non-overlapping time periods. System 10 may incorporate a model of tracked actor 18 into a scene in which the actor's movements overlap in time. As one example, a different skeletal model may be tracked for each of the different time periods. Each skeletal model may correspond to a different role.

Fig. 8 is a flow diagram of one embodiment of a process 800 for retargeting a model of an actor 18. Process 800 may be used in generating a scene based on a model of actor 18. Accordingly, process 800 is one embodiment of step 508 of process 500. In one embodiment, process 800 creates a non-human image that tracks the behavior of actor 18. Note that prior to process 800, the user may have notified system 10 how actor 18 should be retargeted. For example, the user enters a command (perhaps with a gesture or voice) to instruct the system 10 that the actor 18 should be retargeted to a tiger. Meanwhile, prior to process 800, a model of actor 18 may have been developed. For example, process 700 may be executed to develop a skeletal model.

In step 802, the reconfigured target object is accessed. For example, system 10 accesses stored information based on a user's prior request to retarget actor 18 to a tiger or monster.

In step 804, retargeting is performed. In one embodiment, system 10 maps the skeletal model to a retargeted skeletal model. For example, monsters may have very long arms relative to actors 18. Accordingly, the length of the arm bone may be modified in step 804. In some cases, the joint angle may be modified. For example, the head of the monster may be shortened and angled downward relative to the actual position of the actor's head. After remapping, various textures may be overlaid on the remapped skeletal model. Overlaying the texture may include adding features such as hair, clothing, skin, and the like. These elements may or may not be related to the characteristics of actor 18. For example, a monster may wear clothing that does not have any relevance to the clothing worn by the actor 18.

FIG. 9 is a flow diagram of one embodiment of a process 900 for creating a movie based on scenes in response to a user command. Process 900 is one embodiment of step 510 of process 500. The process 900 describes high-level details of creating a movie based on scenes. As described above, scene 19 may refer to an action that occurs over a period of time and may include multiple frames of data presented sequentially.

At step 902, the scene 19 is presented on the electronic device 14 so that the director 11 may view the scene 19. Note that the scene 19 may be presented from the perspective of the director 11. Also, the director 11 may view the scene 19 in real time. For example, referring to fig. 1A, the director 11 views the scene 19 from the perspective of the electronic device 14. In one case, the electronic device 14 is used as a virtual viewfinder to allow the director 11, cameraman 15, etc. to determine the appropriate camera angle.

In step 904, the scene 19 is captured by the system 10 in response to a request from the electronic device 14. Step 904 allows the director 11 (or others) to capture the scene 19 once it is determined that a suitable camera angle has been found. In one embodiment, metadata describing a scene (e.g., skeletal data) and camera position is captured in step 904. Further details are described below.

As indicated by decision step 906, the director 11 may capture as many scenes 19 as desired. In step 908, the movie is edited using system 10. Editing allows a user to create a movie based on all captured scenes. As noted, in some embodiments, the user enters editing commands using voice commands and/or gestures that may be recognized by the system 10.

FIG. 10 is a flow diagram of one embodiment of a process 1000 of viewing scene 19 at electronic device 14. Process 1000 is one embodiment of step 902 of process 900. At step 1002, a location of the electronic device 14 in the environment is determined. For example, the system 10 determines the location of the director's electronic device 14. Note that the position may include a location in 3D space as well as a direction.

A variety of techniques may be used to determine the location of the electronic device 14. Further, the location may be determined based on various types of data. One example is for the depth camera system 20 to identify 3D coordinates of the electronic device 14. One technique for accomplishing this is to track the position of the director's hands based on skeletal data. In this case, the director 11 may notify the system 10 that the electronic device 14 is in, for example, the director's right hand. As an alternative, the system 10 may be capable of identifying the electronic device 14 based on pattern recognition. In this case, the director 11 may inform the system 10 that there is some type of electronic device 14 being used. The system 10 may instruct the director 11 to hold the electronic device 14 in a position so that the system 10 can learn to identify the electronic device 14. The system 10 may communicate this positioning to the director 11 by displaying the living room on the display 16 and highlighting the target area. Another way to locate the electronic device 14 is to place markers on the electronic device 14 that the system 10 is able to detect.

In one embodiment, the electronic device 14 runs an application that allows it to be used as a virtual pre-viewer of the scene 19. This application may be configured to communicate with system 10 to send information that helps determine the location of electronic device 14. For example, the electronic device 14 may have GPS data, compass data, and/or accelerometer data that can be transmitted to the system 10. The accelerometer data can be used to determine what angle the electronic device 14 is tilted with respect to the floor. This can be used to determine the angle at which the virtual viewfinder is pointing. The GPS data may be used to determine the location of the electronic device 14 within the room.

In step 1004, a version of the scene 19 may be determined from the perspective of the electronic device 14. Note that this may be performed in real time in order to allow the scene to be viewed by the director in real time. The scene 19 created in process 500 may be from the perspective of the depth camera system 20. In some embodiments, system 10 stores metadata such as a 3D model of the room and a model of actor 18. The 3D model of the room may include information such as the 3D coordinates of the objects to be used as virtual props. The model of actor 18 may include time-based skeletal data. With this information, the system 10 is able to determine how the scene 19 will appear from the perspective of the electronic device 14.

In step 1006, the version of the scene 19 is transmitted to the electronic device 14. Typically this will be by wireless transmission, but wired transmission may be used. The transmission may use various mechanisms such as 802.11, bluetooth, cellular telephone transmission, and the like.

In step 1008, the version of scene 19 is displayed on electronic device 14. The aforementioned application on electronic device 14 may be used to communicate with system 10 to receive this version of scene 19 and render scene 19 on a display. As previously described, this version of scene 19 may be a real-time version. As used before the term "real-time," there may be some small delay, transmission delay, presentation delay, or other possible delay due to the time it takes the system 10 to generate this version of the scene 19.

In some embodiments, step 1008 includes presenting the retargeted actor. For example, the director 11 may see that the actor 18 is retargeted to Godzilla (Cowsla) while viewing a display on the electronic device 14. More specifically, the director 11 may see that Godzilla is moving in real time based on the actor's motion.

Since the director 11 may change the location of the electronic device 14, the process 1000 may return to step 1002 to again determine the location of the electronic device 14. Other steps of determining, communicating, and displaying the scene 19 from the perspective of the electronic device 14 may then be performed. Process 1000 may end in response to a user input instructing system 10 to record a command that should end.

FIG. 11 is a flow diagram of one embodiment of a process 1100 for capturing scenes of a movie being filmed. Process 1100 is one embodiment of step 904 of process 900. Process 1100 may be performed in response to a request to record scene 19. Thus, process 1100 may begin in response to a request to make a recording and end in response to a request to stop recording. In step 1102, a request from the electronic device 14 to record metadata for a scene 19 is received. For example, the electronic device 14 may be running an application that allows it to communicate with the system 10 in response to a command from the director 11.

At step 1104, system 10 stores metadata describing a model of actor 18. As one example, skeletal data is stored. Additional metadata may continue to be stored until the user requests the recording to stop. The metadata may also include data describing the location of objects to be used as virtual props.

At step 1106, the system 10 stores metadata describing the location of the electronic device 14. As one example, the 3D coordinates of the electronic device 14 are stored. Additional metadata may continue to be stored until the user requests the recording to stop. Thus, the system 10 may store data pairs that each include a 3D location and a time value. The metadata may also include data describing the orientation of the electronic device 14 (e.g., compass data, accelerometer data, etc.).

In step 1108, the system 10 receives a request to stop recording the scene. As described above, the request may come from the electronic device 14.

FIG. 12 is a flow diagram of one embodiment of a process 1200 for editing a movie. Process 1200 is one embodiment of step 906 of process 900. The process 1200 allows a user to edit a movie using natural user input such as gestures and voice commands. Process 1200 may begin in response to a user request to enter an editing mode. A variety of techniques may be used to enter the edit mode. In one embodiment, the user makes one or more gestures that may be interpreted by system 12 as a request to enter an edit mode.

In step 1202, stored metadata for one or more scenes of a movie is accessed. For example, metadata stored when process 900 is performed one or more times is accessed. Note that many different sets of metadata may be accessed so that many different scenes may be edited. The system 10 may present a snapshot of at least some of the scenes to allow the user to select a scene for editing.

At step 1204, depth camera system 20 receives input that is interpreted by system 12 as an editing command. Note that the depth camera system 20 may have one or more microphones that may allow a user to input voice commands. For example, the user may point to one of these scenes and say "selectscene" or "playcene". After viewing the various scenes, the user may select and sort certain scenes for sequential presentation. The system 12 may also allow the user to make modifications to the scene. For example, after viewing the scene, the user may decide that the actor 18 being retargeted to a lion should instead be retargeted to a tiger. To perform retargeting, the user may say "re-targetaliser". In response, system 12 may play a scene in which the actor is retargeted to a tiger. To accomplish this, system 12 may access a skeletal model of actor 18, remap it to a tiger's skeleton, and overlay the tiger's features. The user may also change the angle of the scene. For example, the user may say "zoomin" or "zoolout" to cause system 12 to create versions of the scene with different zoom levels. The user may also overlay music in the scene. These are just some of the possible editing possibilities; many other editing possibilities exist.

The foregoing detailed description of the inventive system has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the present system to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. The described embodiments were chosen in order to best explain the principles of the inventive system and its practical application to thereby enable others skilled in the art to best utilize the inventive system in various embodiments and with various modifications as are suited to the particular use contemplated. It is intended that the scope of the present system be defined by the claims appended hereto.

Claims (7)

1. In a system having a depth camera, a method comprising:

collecting depth information of an environment using the depth camera at a first real-world location;

generating a skeletal model of an actor in the environment using the depth information;

tracking the skeletal model using the depth information;

generating a scene based on the tracking of the skeletal model of the actor, wherein generating a scene comprises retargeting the skeletal model to create a non-human image that tracks behavior of the actor; and

creating a movie based on the scene in response to a user command;

wherein said creating a movie based on said scenes in response to a user command comprises:

providing the scene to an electronic device in real-time, determining one or more real-world locations of the electronic device in the environment for a period of time, wherein the one or more real-world locations of the electronic device in the environment are different from the first real-world location;

generating a version of the scene from the perspective of the electronic device for the time period; and

transmitting the version of the scene to the electronic device.

2. The method of claim 1, wherein said creating a movie based on the scenes in response to a user command comprises:

receiving a request from the electronic device to record the scene;

storing first metadata describing a tracking of the skeletal model of the actor for the period of time; and

storing second metadata describing the one or more real-world locations of the electronic device in the environment for the period of time.

3. The method of claim 1, wherein the generating the scene further comprises:

receiving a request to use an object in the environment as a virtual item;

determining one or more locations of the object in a 3D model of the environment based on the depth information; and

incorporating virtual props into the scene based on one or more positions of the objects in the 3D model.

4. The method of claim 1, wherein the generating the scene further comprises:

generating a virtual scene; and

placing the actor in the virtual scene.

5. The method of claim 1, wherein said creating a movie based on the scenes in response to a user command comprises:

receiving input via the depth camera to edit the movie;

accessing stored metadata describing a plurality of scenes generated according to the method of claim 1; and

receiving, via the depth camera, an input command to edit the movie based on the stored metadata.

6. A method for creating a movie, the method comprising:

collecting depth information of an environment using a depth camera at a first real-world location;

generating and tracking a skeletal model of an actor in the environment based on the depth information, the skeletal model capturing motion of the actor using the depth camera;

generating a scene based on the skeletal model, wherein generating a scene comprises retargeting the skeletal model of the actor to create a non-human image that tracks behavior of the actor;

determining one or more real-world locations of an electronic device to be used as a virtual viewfinder, the one or more real-world locations being associated with the scene over a period of time, and the one or more real-world locations of the electronic device being different from the first real-world location;

generating a version of the scene from the perspective of the electronic device at the one or more real-world locations; and

providing the version of the scene to the electronic device.

7. The method of claim 6, further comprising:

receiving a request from the electronic device to record metadata of the scene;

storing first metadata describing the captured motion of the actor; and

storing second metadata describing the one or more real-world locations of the electronic device.