Abstract: A method for using structured light in a handheld projection device is provided that includes projecting a structured light pattern in at least one portion of a frame being projected by the handheld projection device, wherein the at least one portion of the frame is a subset of the frame, capturing an image of the projected frame, computing scene depth information based on the structured light pattern in the captured image, and using the scene depth information in processing of a subsequent frame of the video stream.

Abstract: An apparatus and method are provided to determine the occurrence and location of an interaction with an interface, particularly with an image of a user interface that may be projected or otherwise produced on a surface. The apparatus uses one or more single-element sensors (such as a photodiode) to sense and capture light readings of a scene, the readings corresponding to a plurality of structured light images injected within the presentation of the interface. The readings are compared to a baseline set of readings to determine the occurrence and location of an interaction event by an obstacle (i.e., a finger or a stylus) such as a touch event or a movement of the obstacle.

Abstract: A method is provided that includes generating coefficients of a scene adaptive filter (SAF) based on differences between values of neighboring pixels in a representative two dimensional (2D) image, and applying the SAF to a plurality of corresponding 2D images.

Abstract: A first depth map is generated in response to a first stereoscopic image from a camera. The first depth map includes first pixels having valid depths and second pixels having invalid depths. A second depth map is generated in response to a second stereoscopic image from the camera. The second depth map includes third pixels having valid depths and fourth pixels having invalid depths. A first segmentation mask is generated in response to the first pixels and the third pixels. A second segmentation mask is generated in response to the second pixels and the fourth pixels. In response to the first and second segmentation masks, a determination is made of whether the second stereoscopic image includes a change in comparison to the first stereoscopic image.

Abstract: A query is generated for determining a correlation between an advertisement and a person who interacted with a merchant. The query includes an image of the person. In response to the query, a determination is made about whether the correlation exists between the image and a face that has given attention to the advertisement. In response to determining that the correlation exists, a report of the correlation is generated for the merchant.

Abstract: A method for video stream processing in a video chain is provided that includes transmitting a video stream in the video chain, receiving, by a first video node in the video chain, a region of interest (ROI) command from a second video node in the video chain, wherein the ROI command includes an ROI type indicator, and performing, by the first video node, the ROI command according to the ROI type indicator.

Abstract: At least first nodes and second nodes of a decision tree are stored within a memory of an information handling system. The first nodes include a first parent node and first remaining nodes that descend from the first parent node. The second nodes include a second parent node and second remaining nodes that descend from the second parent node. The first nodes are grouped into a first packed node stored in first physically contiguous locations of the memory. The first nodes are sequenced in the first physically contiguous locations according to respective depth levels of the first nodes within the decision tree. The second nodes are grouped into a second packed node stored in second physically contiguous locations of the memory. The second nodes are sequenced in the second physically contiguous locations according to respective depth levels of the second nodes within the decision tree.

Abstract: In response to a query of a decision tree, a first packed node of the decision tree is copied from a system memory into a direct memory access (“DMA”) memory. In response to copying the first packed node from the system memory into the DMA memory, copying is initiated of a second packed node of the decision tree from the system memory into the DMA memory, up to a limit of then-currently available space within the DMA memory. Concurrently with copying the second packed node from the system memory into the DMA memory, the first packed node is evaluated in the DMA memory. In response to evaluating the first packed node, the second packed node is evaluated in the DMA memory without waiting for additional copying of the second packed node from the system memory into the DMA memory.

Abstract: A method and apparatus for enabling an interactive surface. The method includes determining pixels of a depth image relating to an object at least one of touching or in close proximity to a related surface, differentiating between a small and a larger cluster of pixels, determining smaller cluster of pixels to be a level1 blob and the larger cluster of pixels to be a level2 blob and declaring the level1 blob an object touching the surface, and computing the coordinates of the level1 blob and repeating the process to enable the interactive surface.

Abstract: A method and apparatus for depth-fill algorithm for low-complexity stereo vision. The method includes utilizing right and left images of a stereo camera to estimate depth of the scene, wherein the estimated depth relates to each pixel of the image, and updating a depth model with the current depth utilizing the estimated depth of the scene.

Abstract: A method of clutter elimination in digital images is provided that includes identifying a foreground blob in an image, determining a depth of the foreground blob, and indicating that the foreground blob is clutter when the depth indicates that the foreground blob is too close to be an object of interest. Methods for obstruction detection in depth images such as those captured by stereoscopic cameras and structured light cameras are also provided.

Abstract: A method of processing a digital video sequence is provided that includes detecting a foreground object in an image captured by a depth camera, determining three-dimensional (3D) coordinates of the foreground object, and comparing the 3D coordinates to a 3D video tripwire to determine if the foreground object has crossed the 3D video tripwire. A method of defining a 3D video tripwire is also provided.

Abstract: A method of analyzing a depth image in a digital system is provided that includes detecting a foreground object in a depth image, wherein the depth image is a top-down perspective of a scene, and performing data extraction and classification on the foreground object using depth information in the depth image.

Abstract: A method and apparatus for stereo-based proximity warning system for vehicle safety. The method comprising capturing a right and a left image utilizing the right and left of stereo cameras, performing stereo analysis and depth computation for comparing and determining the depth deviation between the current depth image with the depth model, updating the depth model when there is minimal or no deviation, otherwise, performing morphological operations for clean-up and connected components analysis, and determining if the object is too close to be safe utilizing the component analysis, and generating a warning when the object is too close.

Abstract: A method and apparatus for projecting enhanced information on a white-board. The method includes capturing an image of information on a white-board, analyzing the captured image and determining the type of enhancement needed for the information displayed, enhancing the information in the image according to the determined type of enhancement, and projecting the enhanced information on the white-board.

Abstract: A method, apparatus and system of an improved mouse-pen device. The method includes projecting structured light pattern, measuring the intensity of the projected light, determining the improved mouse-pen location with respect to a projector, determining the next structured light pattern to infer the position and shape of the light sensing cone of the improved mouse-pen device utilizing the light intensity data and location with respect to the projector, and determining the three position of the improved mouse-pen device utilizing the inferred position and shape.

Abstract: A method and apparatus for camera calibration. The method is for disparity estimation of the camera calibration and includes collecting statistical information from at least one disparity image, inferring sub-pixel misalignment between a left view and a right view of the camera, and utilizing the collected statistical information and the inferred sub-pixel misalignment for calibration refinement.

Abstract: A method of improving stereo video viewing comfort is provided that includes capturing a video sequence of eyes of an observer viewing a stereo video sequence on a stereoscopic display, estimating gaze direction of the eyes from the video sequence, and manipulating stereo images in the stereo video sequence based on the estimated gaze direction, whereby viewing comfort of the observer is improved.