摘要:
Techniques from computer vision and computer graphics are combined to robustly track a target (e.g., a user) and perform a function based upon the image and/or the identity attributed to the target's face. Three primary modules are used to track a user's head: depth estimation, color segmentation, and pattern classification. The combination of these three techniques allows for robust performance despite unknown background, crowded conditions, and rapidly changing pose or expression of the user. Each of the modules can also provide an identity classification module with valuable information so that the identity of a user can be estimated. With an estimate of the position of a target in 3-D and the target's identity, applications such as individualized computer programs or graphics techniques to distort and/or morph the shape or apparent material properties of the user's face can be performed. The system can track and respond to a user's face in real-time using completely passive and non-invasive techniques.
摘要:
A method and system for estimating the three dimensional position of an object in a three dimensional physical space. Specifically, the method discloses capturing a plurality of images of a human form within the three dimensional (3D) physical space. Each of the plurality of images is captured from a different viewpoint location of the human form. At least one image capturing device calibrated within the 3D physical space is used to capture the images. A plurality of silhouettes of the human form is extracted from the plurality of images. A plurality of contours of an object of the human form is obtained from the plurality of silhouettes. A location of the object within the 3D physical space is determined from an object model of the object based on the plurality of contours.
摘要:
A large scale multi-user, multi-touch system with a specialized zone-based user interface including methods for space management and spatial apportioning of audio cues. The system comprises a multi-touch display component fabricated in dimensions sufficient for at least a plurality of users and for displaying projected images and for receiving multi-touch input. The apparatus includes a plurality of image projectors, a plurality of cameras for sensing multi-touch input and the apparatus includes interface software for managing user space. The interface software implements techniques for managing multiple users using the same user interface component by allocating physical spaces within the multi-touch display component and coordinating movement of displayed objects between the physical spaces. Embodiments include a plurality of audio transducers and methods for performing audio spatialization using the plurality of audio transducers corresponding to the physical spaces, apportioning of volume levels to the audio transducers based on movement of a displayed object.
摘要:
A large scale multi-user, multi-touch system with a specialized zone-based user interface including methods for space management and spatial apportioning of audio cues. The system comprises a multi-touch display component fabricated in dimensions sufficient for at least a plurality of users and for displaying projected images and for receiving multi-touch input. The apparatus includes a plurality of image projectors, a plurality of cameras for sensing multi-touch input and the apparatus includes interface software for managing user space. The interface software implements techniques for managing multiple users using the same user interface component by allocating physical spaces within the multi-touch display component and coordinating movement of displayed objects between the physical spaces. Embodiments include a plurality of audio transducers and methods for performing audio spatialization using the plurality of audio transducers corresponding to the physical spaces, apportioning of volume levels to the audio transducers based on movement of a displayed object.
摘要:
Position data is generated. The position data describes real-time positions of each of one or more billiard balls moving on a playing surface of a billiard table. Imagery is displayed on the playing surface. The imagery dynamically responds to the position data as the one or more billiard balls move on the playing surface.
摘要:
A method includes determining a first blend map for a first projector, the first blend map including a first plurality of attenuation factors corresponding to a region of overlap between first and second images projected by the first projector and a second projector, respectively, on a display surface, applying the first blend map to a white level measurement map that includes a plurality of white level measurement values measured from a first plurality of captured images, applying a smoothing function to the white level measurement map to generate a white level target map, and determining a scale map for the first projector from the white level measurement map and the white level target map.
摘要:
Segmentation of background and foreground objects in an image is based upon the joint use of range and color data. Range-based data is largely independent of color image data, and hence not adversely affected by the limitations associated with color-based segmentation, such as shadows and similarly colored objects. Furthermore, color segmentation is complementary to range measurement in those cases where reliable range data cannot be obtained. These complementary sets of data are used to provide a multidimensional background estimation. The segmentation of a foreground object in a given frame of an image sequence is carried out by comparing the image frames with background statistics relating to range and normalized color, using the sets of statistics in a complementary manner. A background model is determined by estimating using a multidimensional histogram, recording pixel values, configuring the pixel values into a cluster, and selecting a largest cluster as representing the background model.
摘要:
Dense range data obtained at real-time rates is employed to estimate the pose of an articulated figure. In one approach, the range data is used in combination with a model of connected patches. Each patch is the planar convex hull of two circles, and a recursive procedure is carried out to determine an estimate of pose which most closely correlates to the range data. In another aspect of the invention, the dense range data is used in conjunction with image intensity information to improve pose tracking performance. The range information is used to determine the shape of an object, rather than assume a generic model or estimate structure from motion. In this aspect of the invention, a depth constraint equation, which is a counterpart to the classic brightness change constraint equation, is employed. Both constraints are used to jointly solve for motion estimates.
摘要:
Embodiments of the present invention recite a system for providing product consulting using a transmitted image. In one embodiment, the present invention comprises an image capture device for capturing an image of a user and a reference color set. In embodiments of the present invention, the image capture device does not require a provided infrastructure when capturing the image. The system further comprises a categorizing system for determining at least one data category from data comprising the image. A result generator generates a result based upon the determining of the categorizing system. The system further comprises a result reporting system for conveying the product consultation to the user when the result is conveyed.
摘要:
Identification of starting and ending times of commercial breaks and commercials within those commercial breaks found in audiovisual content is disclosed. A solution to a “batch optimization” problem is used in which commercial locations within a set of audiovisual content are detected as a group by choosing a set of commercial locations which optimizes a cost function which can include considerations of, for example, 1) one or more cues, 2) relative locations of commercials within the audiovisual content, and/or 3) probability models based on statistics obtained regarding characteristics of typical commercial and commercial breaks. Optimization can be done over the total set of commercial location decisions, rather than on a per-commercial basis. Additionally, the cost function can be iteratively evaluated and many more types of cues and combinations of cues can be used in detection of commercials.