91848 results about "Computer vision" patented technology

A method and apparatus for displaying the evolution of an electronic document (e.g. word-processing document, portable-document-format file, spreadsheet, drawing, and the like), containing tracked changes, is disclosed. In accordance with the disclosed method and apparatus, the revisions of an electronic document may be treated as parent frames. In between the parent frames, child frames may be constructed from the combined images of their parent frames. To form a child frame, an image of a parent frame has a degree of translucency as it is combined with the translucent image of the other parent frame, such that every child frame contains traces of the images of both its parent frames. An input device (e.g. keyboard, mouse, touchpad, stylus, voice activation, and the like) may be used to control the frame visible to the user at any one time. The user may use the input device to traverse the frames at various speeds and in either direction, creating the visual illusion that a certain revision of the document is being morphed into its future revisions—or stripped off its changes as it is morphed into previous revisions—depending on the direction chosen by the user.

There is described an indicia reading terminal that can be operative to capture a succession of frames of image data and that can be operative so that a certain frame of the succession of frames is subject to quality evaluation processing where a result of the quality evaluation processing is responsive to one or more of an incidence and sharpness of edge representations of the frame of image data.

A method for obtaining an image indicia includes performing one or more exposures of an imager to capture one or more images, and controlling active portions of an aiming pattern to inhibit capture of the aiming pattern in the one or more captured images or removing the aiming pattern from the one or more captured images. An attempted may be made to decode one or more decodable indicia utilizing the one or more captured images.

A method for providing an output image, the method includes: determining an importance value for each input pixels out of multiple input pixels of an input image; applying on each of the multiple input pixels a conversion process that is responsive to the importance value of the input pixel to provide multiple output pixels that form the output image; wherein the input image differs from the output image.

Methods for recognizing gestures made by a conductive object on a touch-sensor pad and for cursor motion are disclosed. Tapping, drags, pushes, extended drags and variable drags gestures are recognized by analyzing the position, pressure, and movement of the conductive object on the sensor pad during the time of a suspected gesture, and signals are sent to a host indicating the occurrence of these gestures. Signals indicating the position of a conductive object and distinguishing between the peripheral portion and an inner portion of the touch-sensor pad are also sent to the host.

A method of operating a dimensioning system to determine dimensional information for objects is disclosed. A number of images are acquired. Objects in at least one of the acquired images are computationally identified. One object represented in the at least one of the acquired images is computationally initially selected as a candidate for processing. An indication of the initially selected object is provided to a user. At least one user input indicative of an object selected for processing is received. Dimensional data for the object indicated by the received user input is computationally determined.

Methods for recognizing gestures made by a conductive object on a touch-sensor pad are disclosed. Tapping, pushing, hopping, and zigzag gestures are recognized by analyzing the position, pressure, and movement of the conductive object on the sensor pad during the time of a suspected gesture, and signals are sent to a host indicating the occurrence of these gestures. Signals for compensating for unintended motion of the conductive object on the touch-sensor pad during the gestures are also sent to the host.

A system (100) and method (200) for providing location-specific image information is provided. The method can include capturing (202) an image of an object from a mobile device (110), determining (204) a location of the mobile device, recognizing (206) the object from a database of images from the location, and retrieving (208) location-specific information associated with the object. A camera zoom (402), camera focus (412), and compass heading (422) can also be included for reducing a search scope. The method can include recognizing (306) a building in the image, identifying (320) a business associated with the building, retrieving an advertisement associated with the business, and overlaying the advertisement at a location of the building in the image. A list of contacts can also be retrieved (326) from an address of the recognized building and displayed on the mobile device.

A system for tele-operating a robot in an environment includes a user interface for controlling the tele-operation of the robot, an imaging device associated with the robot for providing image information representative of the environment around the robot, means for transmitting the image information to the user interface, means for converting the image information to a user-perceptible image at the user interface, means for designating one or more waypoints located anywhere in the user-perceptible image towards which the robot will move, the waypoint in the user-perceptible image towards which the robot will first move being designated as the active waypoint using an icon, means for automatically converting the location of the active waypoint in the user-perceptible image into a target location having x, y, and z coordinates in the environment of the robot, means for providing real-time instructions to the robot from the user interface to move the robot from the robot's current location in the environment to the x, y, and z coordinates of the target location in the environment, and means for moving the icon representing the active waypoint in the user-perceptible image to a new location in the user-perceptible image while the robot is executing the real-time instruction, wherein the location-converting means automatically converts the new location of the icon representing the active waypoint into a new target location having x, y, and z coordinates in the environment of the robot towards which the robot will move.

An interactive video window display system. A projector projects a visual image. A screen displays the visual image, wherein the projector projects the visual image onto a back side of the screen for presentation to a user on a front side of the screen, and wherein the screen is adjacent to a window. An illuminator illuminates an object on a front side of the window. A camera detects interaction of an illuminated object with the visual image, wherein the screen is at least partially transparent to light detectable by the camera, allowing the camera to detect the illuminated object through the screen. A computer system directs the projector to change the visual image in response to the interaction. The projector, the camera, the illuminator, and the computer system are located on the same side of the window.

The present invention includes methods, devices, systems, circuits and associated computer executable code for detecting and predicting the position and trajectory of surgical tools. According to some embodiments of the present invention, images of a surgical tool within or in proximity to a patient may be captured by a radiographic imaging system. The images may be processed by associated processing circuitry to determine and predict position, orientation and trajectory of the tool based on 3D models of the tool, geometric calculations and mathematical models describing the movement and deformation of surgical tools within a patient body.

There are provided an image memory which stores one image of a subject, an image fetch section which takes in an image from the image memory to another memory or register in a predetermined unit, a control section which takes charge of the overall control, a face characteristic storage section which stores a plurality of characteristics of a face, a recognition and judgment section which recognizes a face from the data from the image fetch section and the data from the face characteristic storage section and judges each portion, an edge detector which detects an edge detection value from the result data thereof, and an output section which outputs the final judgment result to the outside.

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.

A system for surgical imaging and display of tissue structures of a patient, including a display and an image processor for displaying such images in coordination with a tool image to facilitate manipulation of the tool during the surgical procedure. The system is configured for use with a fluoroscope such that at least one image in the display is derived from the fluoroscope at the time of surgery. A fixture is affixed to an imaging side of the fluoroscope for providing patterns of an of array markers that are imaged in each fluoroscope image. A tracking assembly having a plurality of tracking elements is operative to determine positions of said fixture and the patient. One of the tracking elements is secured against motion with respect to the fixture so that determining a position of the tracking element determines a position of all the markers in a single measurement.

Method for obtaining information about objects in an environment around a vehicle in which infrared light is emitted into a portion of the environment and received and the distance between the vehicle and objects from which the infrared light is reflected is measured. An identification of each object from which light is reflected is determined and a three-dimensional representation of the portion of the environment is created based on the measured distance and the determined identification of the object. Icons representative of the objects and their position relative to the vehicle are displayed on a display visible to the driver based on the three-dimensional representation. Additionally or alternatively to the display of icons, a vehicular system can be controlled or adjusted based on the relative position and optionally velocity of the vehicle and objects in the environment around the vehicle to avoid collisions.

Tapping gestures for selecting text on a device having a touch-sensitive screen are disclosed. A single tap gesture causes a portion of a character string to be selected. A double tap gesture causes the entire character string to be selected. A tap and hold gesture causes the device to enter a cursor mode wherein the placement of a cursor relative to the characters in the character string can be adjusted. In text selection mode, a finger can be used to move the cursor from a cursor start position to a cursor end position to select text therebetween.

An apparatus and method of encoding and communicating symbols is provided. A user encodes a symbol using a sliding motion of a fingertip in relation to a proximity and touch-detecting glance pad. The user imagines a polygon on the surface of the pad. The user makes an encoding touch generally coextensive with one of the sides of the polygon in either a clockwise or counterclockwise direction. The glance pad detects the motion and infers the intent of the user, assigning a symbol to the encoding touch.