Abstract: Image processing systems and methods are provided for extrinsic calibration of a plurality of image sensors. A logic circuit receives image data for an omnidirectional object from image sensors spaced apart and imaging at least a portion of a region of interest. The logic circuit combines the image data from the image sensors to generate a calibration matrix for the image sensors and to determine a matrix transformation data based on (i) reference image data and (ii) a three-dimensional model of the reference object. The logic circuit modifies the calibration matrix into an enhanced calibration matrix by applying the matrix transformation data to the calibration matrix, where the enhanced calibration matrix can be used to calibrate the plurality of image sensors.

Abstract: Methods, systems and apparatus for segmenting objects are provided. A controller: receives, from one or more sensors, a 3D representation of a scene that includes an object represented by a 3D model; determines an orientation of a 2D image in the 3D representation by matching the 2D image with a corresponding region of the 3D representation; determines a first portion of the 3D representation that corresponds to a subset of the 3D model of the object from: the orientation of the 2D image in the 3D representation; and predetermined matching data representative of a matching of the 2D image with a respective corresponding region of the 3D model, each of the 3D model, the 2D image, and the predetermined matching data stored in a memory accessible to the controller; segments the first portion of the 3D representation from a second portion of the 3D representation.

Abstract: Methods, systems, and apparatus for segmenting and dimensioning objects are disclosed. An example method disclosed herein includes determining a first sensor of a plurality of sensors toward which a vehicle is moving based on image data generating by the plurality of sensors; designating the first sensor as a reference sensor; combining the image data from the plurality of sensors to generate combined image data representative of the vehicle and an object carried by the vehicle, the combining based on reference sensor; generating a plurality of clusters based on the combined image data; and identifying a first one of the clusters nearest the reference sensor as the object.

Abstract: Dimensions of an object associated with an electro-optically readable code are estimated by aiming a handheld device at a scene containing the object supported on a base surface. A scanner on the device scans the scene over a field of view to obtain a position of a reference point of the code associated with the object, and reads the code. A dimensioning sensor on the device captures a three-dimensional (3D) point cloud of data points of the scene in automatic response to the reading of the code. A controller clusters the point cloud into data clusters, locates the reference point of the code in one of the data clusters, extracts from the point cloud the data points of the one data cluster belonging to the object, and processes the extracted data points belonging to the object to estimate the dimensions of the object.

Abstract: A method and apparatus for receiving a depth frame from a depth sensor oriented towards an open end of a shipping container, the depth frame comprising a plurality of grid elements that each have a respective depth value, identifying one or more occlusions in the depth frame, correcting the one or more occlusions in the depth frame using one or more temporally proximate depth frames, and outputting the corrected depth frame for fullness estimation.

Abstract: A non-parametric method of, and system for, dimensioning an object of arbitrary shape, captures a three-dimensional (3D) point cloud of data points over a field of view containing the object and a base surface on which the object is positioned, detects a base plane indicative of the base surface from the point cloud, extracts the data points of the object from the point cloud, processes the extracted data points of the object to obtain a convex hull, and fits a bounding box of minimum volume to enclose the convex hull. The bounding box has a pair of mutually orthogonal planar faces, and the fitting is performed by orienting one of the faces to be generally perpendicular to the base plane, and by simultaneously orienting the other of the faces to be generally parallel to the base plane.

Abstract: Dimensions of an object associated with an electro-optically readable code are estimated by aiming a handheld device at a scene containing the object supported on a base surface. A scanner on the device scans the scene over a field of view to obtain a position of a reference point of the code associated with the object, and reads the code. A dimensioning sensor on the device captures a three-dimensional (3D) point cloud of data points of the scene in automatic response to the reading of the code. A controller clusters the point cloud into data clusters, locates the reference point of the code in one of the data clusters, extracts from the point cloud the data points of the one data cluster belonging to the object, and processes the extracted data points belonging to the object to estimate the dimensions of the object.

Abstract: Dimensions of an object associated with an electro-optically readable code are estimated by aiming a handheld device at a scene containing the object supported on a base surface. A scanner on the device scans the scene over a field of view to obtain a position of a reference point of the code associated with the object, and reads the code. A dimensioning sensor on the device captures a three-dimensional (3D) point cloud of data points of the scene in automatic response to the reading of the code. A controller clusters the point cloud into data clusters, locates the reference point of the code in one of the data clusters, extracts from the point cloud the data points of the one data cluster belonging to the object, and processes the extracted data points belonging to the object to estimate the dimensions of the object.

Abstract: A non-parametric method of, and system for, dimensioning an object of arbitrary shape, captures a three-dimensional (3D) point cloud of data points over a field of view containing the object and a base surface on which the object is positioned, detects a base plane indicative of the base surface from the point cloud, extracts the data points of the object from the point cloud, processes the extracted data points of the object to obtain a convex hull, and fits a bounding box of minimum volume to enclose the convex hull. The bounding box has a pair of mutually orthogonal planar faces, and the fitting is performed by orienting one of the faces to be generally perpendicular to the base plane, and by simultaneously orienting the other of the faces to be generally parallel to the base plane.

Abstract: Devices and methods that match audio signatures to programming content stored in a remote database are disclosed. In one aspect of an embodiment, audio that includes primary audio from a device that outputs media content to one or more users is analyzed, in order to identify a presence or absence of corruption, and an audio signature is generated for an interval of time. In an aspect of a further embodiment, content being watched by a user is identified using a query audio signature and a message indicating the presence or absence of corruption.

Abstract: Authentication in a system includes presenting information to a user containing a partial sequence of a passcode along with distractors. The user is challenged to identify the partial sequence from among the information in order to gain access to the system.

Abstract: An embodiment takes the form of a method carried out by a package-loading system. The system includes a processor and data storage containing instructions executable by the processor for carrying out the method. The method includes identifying a current package to be loaded by a user into a cargo container, and determining a target position in the cargo container for placement by the user of the identified current package. The method further includes providing for the user a visual indication of the determined target position.

Abstract: A technique for real-time trailer utilization measurement includes a three-dimensional depth monitor operable to monitor loading of a trailer and a processor operable to determine trailer utilization in real-time during loading of the trailer using image information from the monitor. A graphical user interface can receive utilization information from the processor and display a visual representation of real-time loading of the trailer. Utilization is a ratio of cumulative package volume to currently loaded volume of the trailer, wherein the cumulative package volume is determined from dimensional scans of packages to be loaded in the trailer and the currently loaded volume is determined by the monitor.

Abstract: A technique for trailer loading assessment includes imaging loading of a trailer using a monitor. A next step includes detecting loading incidents related to package stacking quality during loading of the trailer using image information from the monitor. A next step includes bookmarking detected loading incidents. A next step includes scoring loading incidents. A next step includes displaying, on a graphical user interface, a visual representation of the loading incidents. The monitor can be an infrared three-dimensional depth camera operable to measure distance to a stacked wall of loaded packages, and a video camera operable to provide an optical image to detect loading incidents.

Abstract: Devices and methods that match audio signatures to programming content stored in a remote database.

Abstract: Authentication in a system includes presenting information to a user containing a partial sequence of a passcode along with distractors. The user is challenged to identify the partial sequence from among the information in order to gain access to the system.

Abstract: Disclosed are techniques that allow the user of a mobile device to select an avatar within a virtual world presented on the display screen of the mobile device. In some embodiments, a user manipulates a thumbwheel. As the thumbwheel is turned, the avatars on the display screen are highlighted one after another. The user then presses a thumbwheel button to select a desired avatar. Some embodiments allow the user to select more than one avatar at a time. Several highlighting techniques are available. In some embodiments, the user uses speech commands instead of a thumbwheel to highlight the avatars one by one. Speech input is also used to select one or more avatars. Some devices support a touch-screen interface. Embodiments for these devices allow the user to select an avatar by, for example, drawing an arc enclosing the avatar.

Abstract: A method (100) and apparatus (300) for displaying operational information about an electronic device, that determines a change of an operational status of the electronic device, maps the operational status to at least one of an appearance characteristic and an action of an avatar (205, 210, 215, 220) related to the operational status changes the at least one of the appearance characteristic and action of the avatar in a manner related to the change of the operational status, and presents the avatar on a display (345) of the electronic device.

Abstract: A method and apparatus for providing communication between a sending terminal and one or more receiving terminals in a communication network. The media content of a signal transmitted by the sending terminal is detected and one or more of a voice stream, an avatar control parameter stream and a video stream are generated from the media content. At least one of the voice stream, the avatar control parameter stream and the video stream are selected as an output to be transmitted to the receiving terminal. The selection may be based on user preference, channel capacity, terminal capabilities or the load status of a network server performing the selection. The network server may be operable to generate synthetic video from the voice input, a natural video input and/or incoming avatar control parameters.