US20110150271A1 - Motion detection using depth images - Google Patents

Abstract

A sensor system creates a sequence of depth images that are used to detect and track motion of objects within range of the sensor system. A reference image is created and updated based on a moving average (or other function) of a set of depth images. A new depth images is compared to the reference image to create a motion image, which is an image file (or other data structure) with data representing motion. The new depth image is also used to update the reference image. The data in the motion image is grouped and associated with one or more objects being tracked. The tracking of the objects is updated by the grouped data in the motion image. The new positions of the objects are used to update an application. For example, a video game system will update the position of images displayed in the video based on the new positions of the objects. In one implementation, avatars can be moved based on movement of the user in front of a camera.

Description

BACKGROUND
• Many computing applications such as computer games, multimedia applications, or the like use controls to allow users to manipulate game characters or other aspects of an application. Typically such controls are input using, for example, controllers, remotes, keyboards, mice, or the like. Unfortunately, such controls can be difficult to learn, thus creating a barrier between a user and such games and applications. Furthermore, such controls may be different than actual game actions or other application actions for which the controls are used. For example, a game control that causes a game character to swing a baseball bat may not correspond to an actual motion of swinging the baseball bat.
SUMMARY
• Disclosed herein are systems and methods for tracking motion of a user or other objects in a scene using depth images. The tracked motion is then used to update an application. Therefore, a user can manipulate game characters or other aspects of the application by using movement of the user's body and/or objects around the user, rather than (or in addition to) using controllers, remotes, keyboards, mice, or the like.
• A sensor system creates a sequence of depth images that are used to detect and track motion of objects within range of the sensor system. A reference image is created and updated based on a moving average (or other function) of a set of depth images. A new depth images is compared to the reference image to create a motion image, which is an image file (or other data structure) with data representing motion. The new depth image is also used to update the reference image. The data in the motion image is grouped and associated with one or more objects being tracked. The tracking of the objects is updated by the grouped data in the motion image. The new positions of the objects are used to update an application. For example, a video game system will update the position of images displayed in the video based on the new positions of the objects. In one implementation, avatars can be moved based on movement of the user in front of a camera.
• One embodiment includes creating a reference image that includes foreground data and background data based on multiple previous depth images, receiving a new depth image, creating a motion image based on the new depth image and the reference image, identifying one or more objects in the motion image, using position information for the identified one or more objects to update an application, and updating the reference image based on the new depth image.
• One embodiment includes a communication interface that receives depth images, one or more storage devices that store depth images, a display interface, and one or more processors in communication with the one or more storage devices and the display interface. The one or more processors access a new depth image received from the communication interface and identify motion based comparing the new depth image to a reference image stored in the one or more storage devices. The one or more processors create a motion image representing identified motion. The one or more processors group pixels of the motion image and associate one or more groups of pixels with one or more objects identified in object history data stored in the one or more storage devices. The one or more processors use position information for the identified one or more objects to update an application running on the apparatus and provide signals on the display interface that indicate the update to the application.
• One embodiment includes receiving a new depth image, identifying motion based on comparing the new depth image to a reference image, creating a motion image representing identified forward motion and discarding identified backward motion when creating the motion image, identifying one or more objects in the motion image, and reporting the identified one or more objects in the motion image.
• 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 features 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.
BRIEF DESCRIPTION OF THE DRAWINGS
• FIGS. 1A and 1B illustrate an example embodiment of a tracking system with a user playing a game.
• FIG. 2 illustrates an example embodiment of a capture device that may be used as part of the tracking system.
• FIG. 3 illustrates an example embodiment of a computing system that may be used to track motion and update an application based on the tracked motion.
• FIG. 4 illustrates another example embodiment of a computing system that may be used to track motion and update an application based on the tracked motion.
• FIG. 5 is an example depth image.
• FIG. 6 depicts the data in a depth image.
• FIG. 7 is a flow chart describing one embodiment of a process for capturing a sequence depth images.
• FIG. 8 is a flow chart describing one embodiment of a process for operating a computing system to track motion and update an application based on that tracked motion.
• FIG. 9 is a flow chart describing one embodiment of a process for creating a motion image based on a depth image and a reference image.
• FIG. 10 is an example of a motion image.
• FIG. 11 is a flow chart describing one embodiment of a process for grouping pixels of a motion image.
• FIG. 12 is a flow chart describing one embodiment of a process for associating groups of pixels in a motion image with objects being tracked.
• FIG. 13 is a flow chart describing another embodiment of a process for associating groups of pixels in a motion image with objects being tracked.
DETAILED DESCRIPTION
• Depth images are captured by a sensor and used by a computing system to track motions of a user and/or other objects. The tracked motion is then used to update an application. Therefore, a user can manipulate game characters or other aspects of the application by using movement of the user's body and/or objects around the user, rather than (or in addition to) using controllers, remotes, keyboards, mice, or the like. For example, a video game system will update the position of images displayed in the video based on the new positions of the objects or update an avatar based on motion of the user.
• FIGS. 1A and 1B illustrate an example embodiment of atracking system10 with auser18 playing a boxing video game. In an example embodiment, thetracking system10 may be used to recognize, analyze, and/or track a human target such as theuser18 or other objects within range oftracking system10.
• As shown inFIG. 1A,tracking system10 may include acomputing system12. Thecomputing system12 may be a computer, a gaming system or console, or the like. According to an example embodiment, thecomputing system12 may include hardware components and/or software components such thatcomputing system12 may be used to execute applications such as gaming applications, non-gaming applications, or the like. In one embodiment,computing system12 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.
• As shown inFIG. 1A,tracking system10 may further include acapture device20. Thecapture device20 may be, for example, a camera that may be used to visually monitor one or more users, such as theuser18, such that gestures and/or movements performed by the one or more users may be captured, analyzed, and tracked to perform one or more controls or actions within the application and/or animate an avatar or on-screen character, as will be described in more detail below.
• According to one embodiment, thetracking system10 may be connected to anaudiovisual device16 such as 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 such as theuser18. For example, thecomputing system12 may include a video adapter such as a graphics card and/or an audio adapter such as a sound card that may provide audiovisual signals associated with the game application, non-game application, or the like. Theaudiovisual device16 may receive the audiovisual signals from thecomputing system12 and may then output the game or application visuals and/or audio associated with the audiovisual signals to theuser18. According to one embodiment, theaudiovisual device16 may be connected to thecomputing system12 via, for example, an S-Video cable, a coaxial cable, an HDMI cable, a DVI cable, a VGA cable, component video cable, or the like.
• As shown inFIGS. 1A and 1B, thetracking system10 may be used to recognize, analyze, and/or track a human target such as theuser18. For example, theuser18 may be tracked using thecapture device20 such that the gestures and/or movements ofuser18 may be captured to animate an avatar or on-screen character and/or may be interpreted as controls that may be used to affect the application being executed bycomputer environment12. Thus, according to one embodiment, theuser18 may move his or her body to control the application and/or animate the avatar or on-screen character.
• In the example depicted inFIGS. 1A and 1B, the application executing on thecomputing system12 may be a boxing game that theuser18 is playing. For example, thecomputing system12 may use theaudiovisual device16 to provide a visual representation of aboxing opponent38 to theuser18. Thecomputing system12 may also use theaudiovisual device16 to provide a visual representation of aplayer avatar40 that theuser18 may control with his or her movements. For example, as shown inFIG. 1B, theuser18 may throw a punch in physical space to cause theplayer avatar40 to throw a punch in game space. Thus, according to an example embodiment, thecomputer system12 and thecapture device20 recognize and analyze the punch of theuser18 in physical space such that the punch may be interpreted as a game control of theplayer avatar40 in game space and/or the motion of the punch may be used to animate theplayer avatar40 in game space.
• Other movements by theuser18 may also be interpreted as other controls or actions and/or used to animate the player avatar, such as controls to bob, weave, shuffle, block, jab, or throw a variety of different power punches. Furthermore, some movements may be interpreted as controls that may correspond to actions other than controlling theplayer avatar40. For example, in one embodiment, the player may use movements to end, pause, or save a game, select a level, view high scores, communicate with a friend, etc. According to another embodiment, the player may use movements to select the game or other application from a main user interface. Thus, in example embodiments, a full range of motion of theuser18 may be available, used, and analyzed in any suitable manner to interact with an application.
• In example embodiments, the human target such as theuser18 may have an object. In such embodiments, the user of an electronic game may be holding the object such that the motions of the player and the object may be used to adjust and/or control parameters of the game. For example, the motion of a player holding a racket may be tracked and utilized for controlling an on-screen racket in an electronic sports game. In another example embodiment, the motion of a player holding an object may be tracked and utilized for controlling an on-screen weapon in an electronic combat game. Objects not held by the user can also be tracked, such as objects thrown, pushed or rolled by the user (or a different user) as well as self propelled objects. In addition to boxing, other games can also be implemented.
• According to other example embodiments, thetracking system10 may further be used to interpret target movements as operating system and/or application controls that are outside the realm of games. For example, virtually any controllable aspect of an operating system and/or application may be controlled by movements of the target such as theuser18.
• FIG. 2 illustrates an example embodiment of thecapture device20 that may be used in thetracking system10. According to an example embodiment, thecapture device20 may be configured to capture video with depth information including 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, thecapture device20 may organize the depth information into “Z layers,” or layers that may be perpendicular to a Z axis extending from the depth camera along its line of sight.
• As shown inFIG. 2, thecapture device20 may include animage camera component22. According to an example embodiment, theimage camera component22 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 a distance in, for example, centimeters, millimeters, or the like of an object in the captured scene from the camera.
• As shown inFIG. 2, according to an example embodiment, theimage camera component22 may include an infra-red (IR)light component24, a three-dimensional (3-D)camera26, and anRGB camera28 that may be used to capture the depth image of a scene. For example, in time-of-flight analysis, theIR light component24 of thecapture device20 may emit an infrared light onto the scene and may then use sensors (not shown) to detect the backscattered light from the surface of one or more targets and objects in the scene using, for example, the 3-D camera26 and/or theRGB camera28. 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 thecapture device20 to a particular location on the targets or objects in the scene. Additionally, in other example embodiments, the phase of the outgoing light wave may be compared to the phase of the incoming light wave to determine a phase shift. The phase shift may then be used to determine a physical distance from the capture device to a particular location on the targets or objects.
• According to another example embodiment, time-of-flight analysis may be used to indirectly determine a physical distance from thecapture device20 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 example embodiment, thecapture device20 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 grid pattern, a stripe pattern, or different pattern) may be projected onto the scene via, for example, theIR light component24. Upon striking the surface of one or more targets or objects in the scene, the pattern may become deformed in response. Such a deformation of the pattern may be captured by, for example, the 3-D camera26 and/or theRGB camera28 and may then be analyzed to determine a physical distance from the capture device to a particular location on the targets or objects. In some implementations, theIR Light component24 is displaced from thecameras24 and26 so triangulation can be used to determined distance fromcameras24 and26. In some implementations, thecapture device20 will include a dedicated IR sensor to sense the IR light.
• According to another embodiment, thecapture device20 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. Other types of depth image sensors can also be used to create a depth image.
• Thecapture device20 may further include amicrophone30. Themicrophone30 may include a transducer or sensor that may receive and convert sound into an electrical signal. According to one embodiment, themicrophone30 may be used to reduce feedback between thecapture device20 and thecomputing system12 in the target recognition, analysis, and trackingsystem10. Additionally, themicrophone30 may be used to receive audio signals that may also be provided by the user to control applications such as game applications, non-game applications, or the like that may be executed by thecomputing system12.
• In an example embodiment, thecapture device20 may further include aprocessor32 that may be in operative communication with theimage camera component22. Theprocessor32 may include a standardized processor, a specialized processor, a microprocessor, or the like that may execute instructions including, for example, instructions for receiving a depth image, generating the appropriate data format (e.g., frame) and transmitting the data tocomputing system12.
• Thecapture device20 may further include amemory component34 that may store the instructions that may be executed by theprocessor32, images or frames of images captured by the 3-D camera and/or RGB camera, or any other suitable information, images, or the like. According to an example embodiment, thememory component34 may include random access memory (RAM), read only memory (ROM), cache, Flash memory, a hard disk, or any other suitable storage component. As shown inFIG. 2, in one embodiment, thememory component34 may be a separate component in communication with theimage capture component22 and theprocessor32. According to another embodiment, thememory component34 may be integrated into theprocessor32 and/or theimage capture component22.
• As shown inFIG. 2, thecapture device20 may be in communication with thecomputing system12 via acommunication link36. Thecommunication link36 may be a wired connection including, for example, a USB connection, a Firewire connection, an Ethernet cable connection, or the like and/or a wireless connection such as a wireless 802.11b, g, a, or n connection. According to one embodiment, thecomputing system12 may provide a clock to thecapture device20 that may be used to determine when to capture, for example, a scene via thecommunication link36. Additionally, thecapture device20 provides the depth information and visual (e.g., RGB) images captured by, for example, the 3-D camera26 and/or theRGB camera28 to thecomputing system12 via thecommunication link36. In one embodiment, the depth images and visual images are transmitted at 30 frames per second. Thecomputing system12 may then use the model, depth information, and captured images to, for example, control an application such as a game or word processor and/or animate an avatar or on-screen character.
• Computing system12 includesgestures library190,structure data192, depth image processing andobject reporting module194 andapplication196. Depth image processing andobject reporting module194 uses the depth images to track motion of objects, such as the user and other objects. To assist in the tracking of the objects, depth image processing andobject reporting module194 usesgestures library190 andstructure data192.
• Structure data192 includes structural information about objects that may be tracked. For example, a skeletal model of a human may be stored to help understand movements of the user and recognize body parts. Structural information about inanimate objects may also be stored to help recognize those objects and help understand movement.
• Gestures library190 may include a collection of gesture filters, each comprising information concerning a gesture that may be performed by the skeletal model (as the user moves). The data captured by thecameras26,28 and thecapture device20 in the form of the skeletal model and movements associated with it may be compared to the gesture filters in thegesture library190 to identify when a user (as represented by the skeletal model) has performed one or more gestures. Those gestures may be associated with various controls of an application. Thus, thecomputing system12 may use thegestures library190 to interpret movements of the skeletal model and to controlapplication196 based on the movements. As such, gestures library may be used by depth image processing andobject reporting module194 andapplication196.
• Application196 can be a video game, productivity application, etc. In one embodiment, depth image processing andobject reporting module194 will report toapplication196 an identification of each object detected and the location of the object for each frame.Applicant196 will use that information to update the position or movement of an avatar or other images in the display.
• FIG. 3 illustrates an example embodiment of a computing system that may be thecomputing system12 shown inFIGS. 1A-2 used to track motion and/or animate (or otherwise update) an avatar or other on-screen object displayed by an application. The computing system such as thecomputing system12 described above with respect toFIGS. 1A-2 may be amultimedia console100, such as a gaming console. As shown inFIG. 3, themultimedia console100 has a central processing unit (CPU)101 having alevel 1cache102, alevel 2cache104, and a flash ROM (Read Only Memory)106. Thelevel 1cache102 and alevel 2cache104 temporarily store data and hence reduce the number of memory access cycles, thereby improving processing speed and throughput. TheCPU101 may be provided having more than one core, and thus,additional level 1 andlevel 2caches102 and104. Theflash ROM106 may store executable code that is loaded during an initial phase of a boot process when themultimedia console100 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 thegraphics processing unit108 to the video encoder/video codec114 via a bus. The video processing pipeline outputs data to an A/V (audio/video)port140 for transmission to a television or other display. Amemory controller110 is connected to theGPU108 to facilitate processor access to various types ofmemory112, such as, but not limited to, a RAM (Random Access Memory).
• Themultimedia console100 includes an I/O controller120, asystem management controller122, anaudio processing unit123, anetwork interface controller124, a firstUSB host controller126, asecond USB controller128 and a front panel I/O subassembly130 that are preferably implemented on amodule118. TheUSB controllers126 and128 serve as hosts for peripheral controllers142(1)-142(2), awireless adapter148, and an external memory device146 (e.g., flash memory, external CD/DVD ROM drive, removable media, etc.). Thenetwork interface124 and/orwireless adapter148 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 memory143 is provided to store application data that is loaded during the boot process. A media drive144 is provided and may comprise a DVD/CD drive, Blu-Ray drive, hard disk drive, or other removable media drive, etc. The media drive144 may be internal or external to themultimedia console100. Application data may be accessed via the media drive144 for execution, playback, etc. by themultimedia console100. The media drive144 is connected to the I/O controller120 via a bus, such as a Serial ATA bus or other high speed connection (e.g., IEEE 1394).
• Thesystem management controller122 provides a variety of service functions related to assuring availability of themultimedia console100. Theaudio processing unit123 and anaudio codec132 form a corresponding audio processing pipeline with high fidelity and stereo processing. Audio data is carried between theaudio processing unit123 and theaudio codec132 via a communication link. The audio processing pipeline outputs data to the A/V port140 for reproduction by an external audio player or device having audio capabilities.
• The front panel I/O subassembly130 supports the functionality of thepower button150 and theeject button152, as well as any LEDs (light emitting diodes) or other indicators exposed on the outer surface of themultimedia console100. A systempower supply module136 provides power to the components of themultimedia console100. Afan138 cools the circuitry within themultimedia console100.
• TheCPU101,GPU108,memory controller110, and various other components within themultimedia console100 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, such architectures can include a Peripheral Component Interconnects (PCI) bus, PCI-Express bus, etc.
• When themultimedia console100 is powered ON, application data may be loaded from thesystem memory143 intomemory112 and/orcaches102,104 and executed on theCPU101. The application may present a graphical user interface that provides a consistent user experience when navigating to different media types available on themultimedia console100. In operation, applications and/or other media contained within the media drive144 may be launched or played from the media drive144 to provide additional functionalities to themultimedia console100.
• Themultimedia console100 may be operated as a standalone system by simply connecting the system to a television or other display. In this standalone mode, themultimedia console100 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 thenetwork interface124 or thewireless adapter148, themultimedia console100 may further be operated as a participant in a larger network community.
• When themultimedia console100 is powered ON, a set amount of hardware resources are reserved for system use by the multimedia console operating system. These resources may include a reservation of memory (e.g., 16 MB), CPU and GPU cycles (e.g., 5%), networking bandwidth (e.g., 8 kbs), etc. Because these resources are reserved at system boot time, the reserved resources do not exist from the application's view.
• In particular, the memory reservation preferably is 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, an idle thread will consume any unused cycles.
• With regard to the GPU reservation, lightweight messages generated by the 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 an overlay depends on the overlay area size and the overlay preferably scales with screen resolution. Where a full user interface is used by the concurrent system application, it is preferable to use a resolution independent of application resolution. A scaler may be used to set this resolution such that the need to change frequency and cause a TV resynch is eliminated.
• After themultimedia console100 boots and system resources are reserved, concurrent system applications execute to provide system functionalities. The system functionalities 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 system application threads versus gaming application threads. The system applications are preferably scheduled to run on theCPU101 at predetermined times and intervals in order to provide a consistent system resource view to the application. The scheduling is to minimize cache disruption for the gaming application running on the console.
• When a concurrent system application requires audio, audio processing is scheduled asynchronously to the gaming application due to time sensitivity. A multimedia console application manager (described below) controls the gaming application audio level (e.g., mute, attenuate) when system applications are active.
• Input devices (e.g., controllers142(1) and142(2)) are shared by gaming applications and system applications. The input devices are not reserved resources, but are to be switched between system applications and the gaming application such that each will have a focus of the device. The application manager preferably controls the switching of input stream, without knowledge the gaming application's knowledge and a driver maintains state information regarding focus switches. Thecameras26,28 andcapture device20 may define additional input devices for theconsole100 viaUSB controller126 or other interface.
• FIG. 4 illustrates another example embodiment of acomputing system220 that may be thecomputing system12 shown inFIGS. 1A-2 used to track motion and/or animate (or otherwise update) an avatar or other on-screen object displayed by an application. Thecomputing system environment220 is only one example of a suitable computing system and is not intended to suggest any limitation as to the scope of use or functionality of the presently disclosed subject matter. Neither should thecomputing system220 be interpreted as having any dependency or requirement relating to any one or combination of components illustrated in theexemplary operating system220. In some embodiments the various depicted computing elements may include circuitry configured to instantiate specific aspects of the present disclosure. For example, the term circuitry used in the disclosure can include specialized hardware components configured to perform function(s) by firmware or switches. In other examples embodiments the term circuitry can include a general purpose processing unit, memory, etc., configured by software instructions that embody logic operable to perform function(s). 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. Since one skilled in the art can appreciate that the state of the art has evolved to a point where there is little difference between hardware, software, or a combination of hardware/software, the selection of hardware versus software to effectuate specific functions is a design choice left to an implementer. More specifically, one of skill in the art can appreciate that a software process can be transformed into an equivalent hardware structure, and a hardware structure can itself be transformed into an equivalent software process. Thus, the selection of a hardware implementation versus a software implementation is one of design choice and left to the implementer.
• Computing system220 comprises acomputer241, which typically includes a variety of computer readable media. Computer readable media can be any available media that can be accessed bycomputer241 and includes both volatile and nonvolatile media, removable and non-removable media. Thesystem memory222 includes computer storage media in the form of volatile and/or nonvolatile memory such as read only memory (ROM)223 and random access memory (RAM)260. A basic input/output system224 (BIOS), containing the basic routines that help to transfer information between elements withincomputer241, such as during start-up, is typically stored in ROM223.RAM260 typically contains data and/or program modules that are immediately accessible to and/or presently being operated on by processingunit259. By way of example, and not limitation,FIG. 4 illustratesoperating system225,application programs226,other program modules227, andprogram data228.
• Thecomputer241 may also include other removable/non-removable, volatile/nonvolatile computer storage media. By way of example only,FIG. 4 illustrates ahard disk drive238 that reads from or writes to non-removable, nonvolatile magnetic media, amagnetic disk drive239 that reads from or writes to a removable, nonvolatile magnetic disk254, and anoptical disk drive240 that reads from or writes to a removable, nonvolatileoptical disk253 such as a CD ROM 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. Thehard disk drive238 is typically connected to the system bus221 through an non-removable memory interface such asinterface234, andmagnetic disk drive239 andoptical disk drive240 are typically connected to the system bus221 by a removable memory interface, such asinterface235.
• The drives and their associated computer storage media discussed above and illustrated inFIG. 4, provide storage of computer readable instructions, data structures, program modules and other data for thecomputer241. InFIG. 4, for example,hard disk drive238 is illustrated as storingoperating system258,application programs257,other program modules256, andprogram data255. Note that these components can either be the same as or different fromoperating system225,application programs226,other program modules227, andprogram data228.Operating system258,application programs257,other program modules256, andprogram data255 are given different numbers here to illustrate that, at a minimum, they are different copies. A user may enter commands and information into thecomputer241 through input devices such as akeyboard251 andpointing device252, 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 theprocessing unit259 through auser input interface236 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). Thecameras26,28 andcapture device20 may define additional input devices for theconsole100 that connect viauser input interface236. Amonitor242 or other type of display device is also connected to the system bus221 via an interface, such as avideo interface232. In addition to the monitor, computers may also include other peripheral output devices such asspeakers244 andprinter243, which may be connected through a outputperipheral interface233.Capture Device20 may connect tocomputing system220 via outputperipheral interface233,network interface237, or other interface.
• Thecomputer241 may operate in a networked environment using logical connections to one or more remote computers, such as aremote computer246. Theremote computer246 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 thecomputer241, although only amemory storage device247 has been illustrated inFIG. 4. The logical connections depicted 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, thecomputer241 is connected to theLAN245 through a network interface oradapter237. When used in a WAN networking environment, thecomputer241 typically includes amodem250 or other means for establishing communications over theWAN249, such as the Internet. Themodem250, which may be internal or external, may be connected to the system bus221 via theuser input interface236, or other appropriate mechanism. In a networked environment, program modules depicted relative to thecomputer241, or portions thereof, may be stored in the remote memory storage device. By way of example, and not limitation,FIG. 4 illustrates application programs248 as residing onmemory device247. 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.
• As explained above,capture device20 provides RGB images and depth images tocomputing system12. The depth image may be a plurality of observed pixels where each observed pixel has an observed depth value. For example, 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 have a depth value such as a length or distance in, for example, centimeters, millimeters, or the like of an object in the captured scene from the capture device.
• FIG. 5 illustrates an example embodiment of a depth image that may be received atcomputing system12 fromcapture device20. According to an example embodiment, the depth image may be an image and/or frame of a scene captured by, for example, the 3-D camera26 and/or theRGB camera28 of thecapture device20 described above with respect toFIG. 2. As shown inFIG. 5, the depth image may include a human target corresponding to, for example, a user such as theuser18 described above with respect toFIGS. 1A and 1B and one or more non-human targets such as a wall, a table, a monitor, or the like in the captured scene. As described above, the depth image may include a plurality of observed pixels where each observed pixel has an observed depth value associated therewith. For example, the depth image400 may include a two-dimensional (2-D) pixel area of the captured scene where each pixel at particular X-value and Y-value in the 2-D pixel area may have a depth value such as a length or distance in, for example, centimeters, millimeters, or the like of a target or object in the captured scene from the capture device.
• In one embodiment, the depth image may be colorized or grayscale such that different colors or shades of the pixels of the depth image correspond to and/or visually depict different distances of thetargets404 from thecapture device20. Upon receiving the image, one or more high-variance and/or noisy depth values may be removed and/or smoothed from the depth image; 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 image.
• FIG. 6 provides another view/representation of a depth image (not corresponding to the same example asFIG. 5). The view ofFIG. 6 shows the depth data for each pixel as an integer that represents the distance of the target to capturedevice20 for that pixel. The example depth image ofFIG. 6 shows 24×24 pixels; however, it is likely that a depth image of greater resolution would be used.
• FIG. 7 is a flow chart describing one embodiment of a process for operatingcapture device20. Instep402, a depth image and a visual image are captured by any of the sensors incapture device20 described herein, or other suitable sensors known in the art. In one embodiment, the depth image is captured separately from the visual image. In some implementations, the depth image and visual image are captured at the same time, while in other implementations they are captured sequentially or at different times. In other embodiments, the depth image is captured with the visual image or combined with the visual image as one image file so that each pixel has an R value, a G value, a B value and a Z value (distance). Instep404, the depth image and the visual image are transmitted tocomputing system12. In one embodiment, the depth image and visual image are transmitted at 30 frames per second. In some examples, the depth image is transmitted separately from the visual image. In other embodiments, the depth image and visual image can be transmitted together.
• FIG. 8 is a flowchart describing one embodiment of a process for operatingcomputing system12 to use depth images to track and identify objects (users and other objects) in order to update an application based on the objects identified and tracked. The process ofFIG. 8 is performed in response to capturingdevice20 transmitting a depth image and visual image to computing system12 (step404 ofFIG. 7); therefore, the process ofFIG. 8 is performed many times. In one embodiment, the process ofFIG. 8 is performed 30 times a second. In other embodiments, the process ofFIG. 8 can be performed more or less than 30 times per second based on or independent from the frame rate of the depth images. Instep460 ofFIG. 8,computing system12 will receive a new depth image from capturingdevice20 in response to step404 ofFIG. 7. This depth image is provided to the depth image processing andobject reporting module194.
• Instep462 ofFIG. 8, a motion image is created based on the newly received depth image and a reference image. The reference image is typically in the same format as the depth image. In one embodiment, the reference image as a single static image of a scene taken prior to the motion. In another embodiment, the reference image is a moving average of the most recent N frames of depth images which provides an estimate of the typical depth position for every pixel in the depth image sequence. If the reference image is a moving average, then the reference image will update over time. The average can either be a uniform average across the sequence length, an exponential decay average, or other weighted average using an external weighting system. Comparing the current depth image to the moving average allows the system to adapt to gradual changes in the scene, as well as automatically adapt to a moving capture device without a reinitialization step. In one embodiment, the reference image is based on 4 seconds of depth images; therefore, if the frame rate is 30 frames per second then the reference image is based on the most recent 120 depth images.
• The reference image is updated based on each new depth image is received. In one example, it will take 120 frames before the reference image is established. In other embodiments, the reference image will be established with the first depth image and then each additional depth image will be added to the reference image until there are 120 depth images received, then the reference image will be updated by the most recent 120 images.
• The Equation (1) below provides one example of a formula for creating a reference image:
• $\begin{array}{cc}\mathrm{new}\mathrm{average}-\frac{t*\left(\mathrm{old}\mathrm{average}\right)+\mathrm{new}\mathrm{data}}{t+1}& \mathrm{Equation}\left(1\right)\end{array}$
• Equation (1) is used to operate on each pixel of the reference image. The variable “t” is the number of frames included in the reference image. In one example, 120 frames are included (4 seconds of video at 30 frames per second). The variable “old average” is the pixel value in the reference image for the particular pixel under consideration. The variable “new data” is the corresponding pixel value in the new depth image received. The output “new average” is the new pixel value of the updated reference image.Equation 1 is performed for every pixel of the reference image. In this manner, the reference image is re-created each time it is updated.
• In one alternative, the value of t in Equation (1) can be different if the motion is backward versus forward. For a particular pixel, the value of t can be 120 if the motion is forward and the value of t can be 30 if the motion is backward.
• When using Equation (1), the system does not need to keep a buffer of the previous 120 frames of depth images. Only the current new depth image needs to be stored in a buffer as well as the reference image. If the system used a straight averaging process, then a buffer would need to keep the last 120 frames of depth images.
• Step462 includes creating a motion image based on the new depth image received instep460 and the reference image discussed above. As explained above, in one embodiment, the depth image and the reference image have the same number of pixels. The motion image created instep462 is also a file (or other data structure) with the same number of pixels in the same format as the depth image and reference image. In one embodiment, the motion image is created by subtracting the new depth image from the reference image on a pixel by pixel basis. Thus, a corresponding pixel in the depth image is subtracted from the corresponding pixel in the reference image and the result is stored as the corresponding pixel the motion image.
• If the pixel value in the new depth image is the same as the pixel value in the reference image, then there is no motion detected for the pixel. If the difference between the reference image and the new depth image is positive, then there is motion towardscapture device20. If the difference between the reference image and the depth image is negative, then there is motion away from thecapture device20.
• In one embodiment, the process for creating the motion image will compare a threshold to the difference between the reference image and new depth image, on a pixel-by-pixel basis, so that small variations will not be detected as motion. Additionally, some embodiments will discard backward motion data (away from the camera) and only report forward motion (toward the camera). In some implementation, the system will track the magnitude of the motion (e.g., the difference between the reference image pixel and depth image pixel), while in other embodiments, the system will only store a Boolean value in the motion image to indicate whether there is motion or not.
• FIG. 9 is a flowchart describing one embodiment or a process for creating a motion image based on the new depth image received and the reference image that includes subtracting pixels, using a threshold and discarding backward motion. Thus, the process ofFIG. 9 is one example implementation ofstep462 ofFIG. 8. Instep500 ofFIG. 9, the system will access a pixel that has not already been operated on in the depth image. Instep502, the system will access the corresponding pixel in the reference image. Instep504, the system will subtract the pixels by subtracting the pixel in the new depth image from the pixel in the reference image. If the resulting magnitude is negative, then a zero is inserted into the corresponding pixel in the motion image instep514 because the system is discarding backward motion. If the difference in pixels was not negative, then instep508 it is determined whether the difference is greater than a threshold (e.g. 2 centimeters per meter). If the difference is not greater than the threshold, then in step514 a zero is added to the corresponding pixel in the motion image because the difference is not great enough to be classified as forward motion. This technique helps reduce noise. If the difference is greater than the threshold, then the system will conclude that there is motion if forward motion (e.g., toward the camera), and instep510, the difference data is inserted in corresponding pixel in the motion image. In another embodiment, rather than adding the difference data, a Boolean value (e.g., 1) is added to the motion image instep510. Instep512, it is determined whether there are more pixels in the depth image that need to be operated on. If there are no more pixels in the depth image to be operated on, then the process ofFIG. 9 is complete. If there are more pixels in the depth image to operate on, the process moves back to step500 and accesses the next pixel in the depth image that has not been operated on. At the end of the process ofFIG. 9, the motion image is created and includes either a 1 or 0 at each pixel. A zero means no motion (or discarded backward motion). A 1 for a pixel value indicates that there was forward motion for that pixel.
• FIG. 10 shows one example of a motion image created using the process ofFIG. 9. As can be seen, some of the pixels have adata value 1 indicating that those pixels represent forward motion. The pixels for which there is no motion would have data zero; however, to make the drawing easier to read, the zeros have been left blank.
• In the above discussion, the comparison between the newly received depth image and the reference image is a simple subtracting and thresholding of values. More sophisticated embodiments may use mean squared error, standard deviation, difference of means or other statistical measures to compare the two data sets. This comparison may be done at the image level, pixel level or some other intermediate granularity of the image.
• In the above discussion, there was only one reference image that was maintained and compared against the newly received depth images. In other embodiments, the system can use more than one reference image. For example, the system can create and maintain two or more reference images that averaged the depth data over differing, or even randomized, time constants. Comparison against multiple reference images can increase likelihood that moving objects will be properly identified. In such an embodiment, the new depth image is compared against multiple reference images. Any motion detected from any other comparisons will be used to add a 1 to the appropriate pixel in the created motion image. Other schemes for comparing multiple reference images to a depth image can also be used.
• Looking back atFIG. 8, after the motion image is created instep462, the reference image is updated instep464 based on the new depth image that was just received in the most recent iteration ofstep460. As discussed above, in one embodiment, the reference image is a moving average of the most recent N frames of depth images. Since the new depth image is received, the average must move based on the newly received frame. Therefore, Equation (1) is used on each pixel of the reference image with “old average” being the data from the existing reference image and “new data” being the data from the newly received depth image. Equation (1) is performed for each pixel of the reference image to update the existing reference image to create a newly updated reference image instep464.
• Once regions of the depth image have been identified as moving, it is useful to segment them into individual groups and track their locations over time. If multiple objects are detected by the system, the output is a collection of pixels that have been identified as moving. To group these pixels into individual objects, the system can use a method of segmentation or grouping called connected component analysis. Neighboring pixels that are also identified as moving are considered connected and therefore part of the same group. Once all of the pixels have been accounted for, the result is a set of groups that represent potential moving objects in the scene. Alternative methods determining which pixels of part of the same group can also be used such as thresholding Euclidian 3D distance or surface distance. Another alternative is to use clustering methods where a fixed number of groups are hypothesized, pixels are associated with each hypothetical group, and then the overall hypothesis is scored based on how well it explained the data. Another method is to maintain the probability that a pixel belongs to each possible group rather than directly associating it with a single group. This may be valuable in scenarios where the tracking system that maintains group assignment between frames can handle ambiguity in pixel association making it more robust in some application scenarios.
• Looking back atFIG. 8, step466 ofFIG. 8 includes grouping the pixels of the motion image that represent motion (e.g., store data1). In one embodiment, the pixels are grouped based on proximity to each other.FIG. 11 is a flowchart describing one embodiment of a process for grouping pixels of motion image based on proximity. Thus,FIG. 8 is one example implementation ofstep466 ofFIG. 8. Instep702, the system will access an ungrouped pixel in the motion image that indicates motion (e.g., has data1). Instep704, the system will identify all connected pixels that include the pixel accessed instep702 as one group. For example, if a pixel has thedata1, the system looks for all pixels that neighbor that pixel that are alsodata1, and of those neighbors withdata1, the system will look for all their neighboring pixels that also havedata1, and so on, until all connected contiguous and continuouspixels showing data1 are grouped into a group. Then instep706, the system determines whether there are any ungrouped pixels that have not been considered yet. If so, the process moves back to step702 and accesses another ungrouped pixel and attempts to find connected pixels. If, instep706, it is determined that there are no more ungrouped pixels, then instep708, the system will identify the center of each group. Whenstep708 is performed, each of the pixels is in a group. It is possible that some groups will only have one pixel. For groups that have more than one pixel, the system will determine the geometric center of the group and identify the x and y coordinate (in pixel space) of that group. Note thatFIG. 10 shows the motion image with the pixels grouped. For example, a first set of pixels are grouped as depicted byoval602 and a second set of pixels are grouped as depicted byoval604.
• Groups containing a small number of pixels may be the result of noise in the depth image that exceeds the threshold limit in the motion detection step. To further filter out interference from noise, one embodiment may require a minimum pixel count or minimum physical size of a group to perform further motion analysis.
• Looking back atFIG. 8, after the pixels of the motion image are grouped instep466, the groups are associated with objects being tracked instep468. It is often valuable to track those objects over time and build an understanding that a moving object in one image is the same object in the following image. In one embodiment, the system will create object history data which stores information about the motion of objects being tracked. For example, this object history data can store an identification of all of the various objects being tracked and prior positions of the objects in the motion image. There are many methods for tracking the objects that can be used. No one particular method for tracking is required. In one example, a spatial likelihood tracking approach can be used that records the positions of each object over time and reassociates new motion with whatever object it is most likely to be. One example is to associate movement with the closest identified object in the previous image in the sequence. Alternative embodiments include predicting the trajectory of the moving object based on recent movements. The system can also model movement when the object is known to be a subcomponent of a larger object, such as an arm or a larger body.
• FIGS. 12 and 13 provide two embodiments of processes for associating groups of pixels in the motion image with objects being tracked (step468 ofFIG. 8). The process ofFIG. 12 associates groups of pixels with objects by associating a group with the closest identified object in the previous image in the sequence. Instep804 ofFIG. 12, the system will access the object history data discussed above. Thus, the system will have information about all the objects previously tracked and their positions in the previous motion images. The object history data can be stored in any suitable type of data structure. Instep806, the system will attempt to associate the center of each group in the current motion image with the object of closest proximity in the most recent motion image. In some embodiments, there will be a threshold distance so that the association must be reasonable. For example, if the closest object is halfway across the image, that may not be a reasonable association and will be discarded. The particular threshold used for the association will vary based on implementation and experimentation.
• In some embodiments, the depth image process andclient reporting module194 performing the association of step840 will make use of the information ingestures library190 or astructure data192 to associate groups with objects. For example, based on known shapes, the system can correlate a group with an existing object. If an object being tracked is a person, external structure data can be used to identify the shape of a person which will help the system better associate a group of pixels in the motion image with the person. Additionally, if the system knows it has previously been tracking a person with an arm moving, theexternal structure data192 and thegestures library190 could teach the system about probable movement of an arm, leg or other body part so the system can more readily identify the object. Similarly, the system may be able to recognize an inanimate object such as a ball or tennis racket based on references or templates instructure data192.
• Step806 attempts to assign every group to an object being tracked. In some embodiments, some groups may not be assignable. In one embodiment, any group that cannot be assigned to an object will be assumed to be a new object. Instep808, any unassociated groups have new objects created and these unassociated groups are assigned to the new objects.
• If moving objects come into close proximity to each other they may appear to merge into a single region. In some applications, it may be desirable to try to separate the single region back into the individual objects based on previous observation. One embodiment includes segmenting the pixels based on their proximity to the center of the previous objects. Pixels are associated with whatever previous objects they were closest to. The distance metric may be as simple as Euclidian distance, surface distance or other representation of distance.
• Instep810, the system determines whether two objects from a previous motion image have merged in the current motion image. That is, if there are two objects in the previous motion image and the current image has only one object in a similar or proximal location as the two objects in the previous image, the system can determine that the two objects have merged. If the system determines that there have not been objects that have merged, then the process continues at step812 and the object history data discussed above is updated so that all groups in the current motion image have their center coordinates (x,y) used to update the position of the objects being tracked. If, instep810, the system determines that the two objects have merged, then the objects are separated by grouping the pixels based on proximity to the separate objects in the previous motion images instep814. In step816, the separated groups are assigned to the appropriate objects from the previous motion image. In step812, after step816, the objects history data is updated so that all groups in the current motion image have their center coordinates (x,y) used to update the position of the objects being tracked.
• FIG. 13 is another embodiment of associating groups to objects (step468 ofFIG. 8) that is based on predicting the trajectory of moving objects using the object history data. Instep850 ofFIG. 13, the system will access the object history data discussed above. Instep852, using that data, the system can predict the trajectory for each object being tracked. The system knows the x and y coordinates in the motion images for previous positions of the object. This data can be used to determine a trajectory and predict where those objects should be in the current motion image. Instep854, the system attempts to associate the center of each of the groups in the current image with the predicted trajectories. The system can also use thestructure data192 andgesture library190 discussed above to predict the trajectories. Instep858, any object that was not associated instep854 is assigned to be a new object instep858. Instep860, the system determines whether two objects have merged, as discussed above. If no objects have merged, then the object history data is updated instep862 to include the information from the current motion image. If two objects have merged (step860), then instep864 those groups are separated as discussed above with respect to step814. Instep866, the newly separated groups are assigned to the previous objects (same as step816). Instep862, the object history data is updated, as discussed above.
• Looking back atFIG. 8, after associating the groups with objects being tracked the information about the objects is reported to the application instep470. In one example embodiment, steps460-470 are performed by depth image processing andobject reporting module194. Instep470, depth image processing andobject reporting module194 reports toapplication196 an identification of all the objects it is tracking and the (X, Y) positions of each of those objects in the current motion image. Instep472,application196 will update based on the reported object information fromstep470. The tracking of the objects can be mapped directly to cursor control, where moving along the perpendicular plane defines the two dimensional position of the cursor and movement and depth can trigger other events. In such an embodiment, step470 would also include reporting depth (distance) information for each object. For example, the depth values for all the pixels in the group associated with the object can be averaged and that data can be the depth number reported for the particular object. Alternatively, all of the depth values can be reported to the application or the depth value for the center of each group can be reported.
• In other embodiments, each object can correlate to an image being displayed on a monitor as part of a video game or other software application. When any of the objects move,application196 will update the positions of the images on the monitor for the object that moved. For example, if a person moves, the person's avatar in the video game may move. If person throws the ball, an image of the ball may move in the video game. There are many different ways an application can update itself based on the motion of the tracked objects. No particular way for updating the application is required for the technology described herein.
• The object history data may also incorporate information about neighboring objects or the structure of a larger object provided by an external system (e.g. structure data192). For example, if a moving object is identified to be the left arm of a human body or a human head, the system can infer that a certain set of pixels pertains to the left hand. Other variations can also be implemented.
• Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. It is intended that the scope of the invention be defined by the claims appended hereto.

Claims (20)

1. A method for using depth images to sense motion, comprising:

creating a reference image that includes foreground data and background data based on multiple previous depth images;

receiving a new depth image;

creating a motion image based on the new depth image and the reference image;

identifying one or more objects in the motion image;

using position information for the identified one or more objects to update an application; and

updating the reference image based on the new depth image.

2. The method ofclaim 1, wherein:

the creating the motion image includes subtracting the new depth image from the reference image to create a set of difference data, identifying difference data greater than a threshold as motion data that includes forward motion data and backward motion data, and discarding the backward motion data.

3. The method ofclaim 1, wherein:

the identifying one or more objects in the motion image includes grouping pixels of the motion image to form one or more groups of pixels, associating each of the one or more groups of pixels with one or more objects identified in object history data, and updating the object history data; and

the using position information for the identified one or more objects to update the application includes reporting the one or more objects and positions for the one or more objects to the application.

4. The method ofclaim 3, wherein:

the grouping of pixels is based on identifying connecting pixels.

5. The method ofclaim 3, wherein:

the grouping of pixels is based on proximity to previously identified objects.

6. The method ofclaim 1, wherein:

the identifying one or more objects in the motion image includes grouping pixels of the motion image to form two or more groups of pixels, associating each of the two or more groups of pixels with two or more objects identified in object history data, and updating the object history data; and

the using position information for the identified one or more objects to update the application includes reporting the two or more objects and positions for the two or more objects to the application.

7. The method ofclaim 1, wherein:

the identifying one or more objects in the motion image includes grouping pixels of the motion image to an initial group of pixels, determining that the initial group of pixels represents two objects, splitting the initial group of pixels into a first group of pixels and a second group of pixels, associating the first group of pixels with a first object based on object history data, and associating the second group of pixels with a second object based on object history data.

8. The method ofclaim 1, wherein:

the identifying one or more objects in the motion image includes grouping pixels of the motion image to form two or more groups of pixels, predicting a trajectory of an object and identifying the group of pixels closest to the predicted trajectory.

9. The method ofclaim 1, wherein:

the identifying one or more objects in the motion image includes using object history data and structure information about items in real space in order to identify the one or more objects.

10. The method ofclaim 1, wherein:

the updating the reference image includes performing a weighted averaging function on the reference image and the new depth image; and

the creating the reference image include performing the weighted averaging function on previous depth images.

11. The method ofclaim 1, wherein:

the using position information for the identified one or more objects to update the application includes changing the position of an image in a video display in response to the position information.

12. The method ofclaim 1, wherein:

the creating the motion image includes subtracting the new depth image from the reference image to create a set of difference data, identifying difference data greater than a threshold as motion data that includes forward motion data and backward motion data, and discarding the backward motion data;

the identifying one or more objects in the motion image includes grouping pixels of the motion image to form one or more groups of pixels, associating each of the one or more groups of pixels with one or more objects identified in object history data, and updating the object history data;

the using position information for the identified one or more objects to update the application includes reporting the one or more objects and positions for the one or more objects to the application; and

the using position information for the identified one or more objects to update the application includes changing the position of an image in a video display in response to the position information.

13. An apparatus that uses depth images to sense motion, comprising:

a communication interface that receives depth images;

one or more storage devices that store depth images;

a display interface; and

one or more processors in communication with the one or more storage devices and the display interface, the one or more processors access a new depth image received from the communication interface and identify motion based comparing the new depth image to a reference image stored in the one or more storage devices, the one or more processors create a motion image representing identified motion, the one or more processors group pixels of the motion image and associate one or more groups of pixels with one or more objects identified in object history data stored in the one or more storage devices, the one or more processors use position information for the identified one or more objects to update an application running on the apparatus and provide signals on the display interface that indicate the update to the application.

14. The apparatus ofclaim 13, wherein:

the display interface connects to a video monitor;

the one or more processors use the position information for the identified one or more objects to update a position of an image on the video monitor; and

the image is displayed by the application.

15. The apparatus ofclaim 13, wherein:

the reference image includes foreground and background data based on multiple previous depth images.

16. The apparatus ofclaim 13, wherein:

the one or more processors determine that a particular group of pixels represents two objects, split the particular group of pixels into a first group of pixels and a second group of pixels, associate the first group of pixels with a first object based on object history data, and associate the second group of pixels with a second object based on object history data.

17. The apparatus ofclaim 13, wherein:

the one or more processors also use structure information about items in real space in order to associate the one or more groups of pixels with the one or more objects.

18. A method for using depth images to sense motion, comprising:

receiving a new depth image;

identifying motion based on comparing the new depth image to a reference image;

creating a motion image representing identified forward motion, and discarding identified backward motion when creating the motion image;

identifying one or more objects in the motion image; and

reporting the identified one or more objects in the motion image.

19. The method ofclaim 18, further comprising:

creating the reference image that includes foreground data and background data based on multiple previous depth images.

20. The method ofclaim 18, wherein:

the reporting the identified one or more objects includes reporting objects and positions of the objects to an application that uses the position to create video.

Images